|
38641
|
1435
|
5
|
2026-05-14T06:25:19.958892+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739919958_m1.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
iTerm2ShellEditViewSessionScriptsProfilesWindowHel iTerm2ShellEditViewSessionScriptsProfilesWindowHelpscreenpipe"-zsh> 0 lhlDaily - Platform - in 20 m100% <478•Thu 14 May 9:25:19181screenpipe*885ec2-user@ip-10-30-129-...₴6ec2-user@ip-10-20-31-14...₴7DOCKERO 81DEV (-zsh)• ₴2APP (-zsh)83whisper_model_load:n_audio_ctx= 1500whisper_model_load:n_audio_state = 384whisper_model_load:n_audio_head= 6whisper_model._load:n_audio_layer= 4whisper_model_load:n_text_ctx448whisper_model_load:n_text_state384whisper_model_load:n_text_head=6whisper_model_load:n_text_layer=4whisper_model_load:n_mels80whisper_model_load:ftype= 1whisper_model,load:qntvr=0whisper_model_load:type1whisper_model_load:adding1608(tiny)extratokenswhisper_model_load:n_langs99whisper_model_load:Metaltotalsize =77.11 MBwhisper_model_load: modelsize77.11MB2026-05-14T09:25:08.714171ZINFOscreenpipe_audio::transcription::engine: whisper model loaded successfullywhisper_backend_init_gpu:device 0: Metal(type:1)whisper_backend_init_gpu: found GPUdevice 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu: using Metal backendggml_metal_init: allocatingggml_metal_init: found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrencytrueggml_metal_init:use graph optimizetruewhisper_backend_init: using BLASbackendwhisper_init_state: kv self size=3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: computebuffer(conv)14.17 MBwhisper_init_state:computebuffer(encode) =65.96 MBwhisper_init_state:computebuffer (cross)=8.50 MBwhisper_init_state:computebuffer (decode) =96.83 MB2026-05-14T09:25:08.721297ZINFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)2026-05-14T09:25:08.727575ZINFO screenpipe_audio::audio_manager::manager: seeded 21 speakers (named + unnamed) from DB into embedding manager2026-05-14T09:25:08.727664ZINFO screenpipe_audio::audio_manager::manager: audio manager started2026-05-14T09:25:08.727731ZINFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events2026-05-14T09:25:09.238925ZINFOscreenpipe_audio::device::device_manager: starting recording for device: System Audio (output)2026-05-14T09:25:09.325492ZINFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)2026-05-14709:25:09.326604ZINFOscreenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)2026-05-14T09:25:09.326657ZINFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)2026-05-14T09:25:16.929049ZWARN screenpipe_ally::tree::macos_lines: lines: AXUIElementCopyParameterizedAttributeValue(AXLineForIndex) failed status=os::Status { raw: -25212,fcc, help:"https://www.osstatus.com?search=-25212" } - first failure (further failures suppressed); search highlights will fall back to paragraph bbox on this app...
|
NULL
|
-877165755350770335
|
NULL
|
visual_change
|
ocr
|
NULL
|
iTerm2ShellEditViewSessionScriptsProfilesWindowHel iTerm2ShellEditViewSessionScriptsProfilesWindowHelpscreenpipe"-zsh> 0 lhlDaily - Platform - in 20 m100% <478•Thu 14 May 9:25:19181screenpipe*885ec2-user@ip-10-30-129-...₴6ec2-user@ip-10-20-31-14...₴7DOCKERO 81DEV (-zsh)• ₴2APP (-zsh)83whisper_model_load:n_audio_ctx= 1500whisper_model_load:n_audio_state = 384whisper_model_load:n_audio_head= 6whisper_model._load:n_audio_layer= 4whisper_model_load:n_text_ctx448whisper_model_load:n_text_state384whisper_model_load:n_text_head=6whisper_model_load:n_text_layer=4whisper_model_load:n_mels80whisper_model_load:ftype= 1whisper_model,load:qntvr=0whisper_model_load:type1whisper_model_load:adding1608(tiny)extratokenswhisper_model_load:n_langs99whisper_model_load:Metaltotalsize =77.11 MBwhisper_model_load: modelsize77.11MB2026-05-14T09:25:08.714171ZINFOscreenpipe_audio::transcription::engine: whisper model loaded successfullywhisper_backend_init_gpu:device 0: Metal(type:1)whisper_backend_init_gpu: found GPUdevice 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu: using Metal backendggml_metal_init: allocatingggml_metal_init: found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrencytrueggml_metal_init:use graph optimizetruewhisper_backend_init: using BLASbackendwhisper_init_state: kv self size=3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize=2.36 MBwhisper_init_state: computebuffer(conv)14.17 MBwhisper_init_state:computebuffer(encode) =65.96 MBwhisper_init_state:computebuffer (cross)=8.50 MBwhisper_init_state:computebuffer (decode) =96.83 MB2026-05-14T09:25:08.721297ZINFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)2026-05-14T09:25:08.727575ZINFO screenpipe_audio::audio_manager::manager: seeded 21 speakers (named + unnamed) from DB into embedding manager2026-05-14T09:25:08.727664ZINFO screenpipe_audio::audio_manager::manager: audio manager started2026-05-14T09:25:08.727731ZINFO screenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events2026-05-14T09:25:09.238925ZINFOscreenpipe_audio::device::device_manager: starting recording for device: System Audio (output)2026-05-14T09:25:09.325492ZINFO screenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)2026-05-14709:25:09.326604ZINFOscreenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)2026-05-14T09:25:09.326657ZINFO screenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)2026-05-14T09:25:16.929049ZWARN screenpipe_ally::tree::macos_lines: lines: AXUIElementCopyParameterizedAttributeValue(AXLineForIndex) failed status=os::Status { raw: -25212,fcc, help:"https://www.osstatus.com?search=-25212" } - first failure (further failures suppressed); search highlights will fall back to paragraph bbox on this app...
|
38639
|
NULL
|
NULL
|
NULL
|
|
38642
|
1436
|
3
|
2026-05-14T06:25:19.979214+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739919979_m2.jpg...
|
iTerm2
|
NULL
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
selectionViewTerminalWinaowmelt• screenpipe SSH: n selectionViewTerminalWinaowmelt• screenpipe SSH: nas — activity.pvmain.ov Mactivity.pyMX• screenpipe [SSH: nas)• _ #recycieV tr appDv"0insumers › activity.py › ...det audio seqments(tor date: date None = None) → List dict str, Any :Start, end = date range(d)interactions.pyapp› • DockernleWORKDIR /appQ copyrequirements.txt |RIN nin install --no-cache-dir -r requirements.txCOPY.14 SypocE 9a0016 CMD ("uvicorn", "main:app",Dockerfile (Working Tree) Xscreenpipe_sync_files.shWORKDIR /apPcopy requirements.extCOPY.eypose gaddCMD ["uvicorn",Dally - Platrorm • In z0m100% 152Thu 14 May 9:25:19•OKvRefactor Sync Script+0 .*•.tt-toolbar < display:flex; gap:10px; align-itens:center: flex-wrap:wrap; }-border); border-radius:6px; padding:8px; }solid var(--border); border-radius:8px; padding:12px 14px; displayThoughtsSELECTudio chunk id = c.idUNNEHHENEORDER BY t.timestampend.fetchallreturn dictr for r in rowsi7) .map(s BThoughts}) -map(a => {8 do salite19 db.salite-shmlDebua Consolel(abash-aoo +v @ M ã .1^ xAll requested chanaes comnlete• Addedi.ttcaudio-sen.active CSS class with white inset bordeModified <› ttRenderAudioSeaments/) to hiahliaht audio seaments within 5 seconds of current nositionAudio timeline now shows visual hiahliaht just like video timelineAudio auto-olav OfF ov derault•Changed _ttAutoPlayAudio from true to false•Updated button text to "*. Auto-Play Audio: OFF*• Modified ‹/› ttShowAudioTranscription() to only play audio when auto-play is enabledAudin romaine dicabled on page refresh and navigationCollansible time rance filter.•Added collapsible " 7 Time Range Filter" section with From/To time inputs•Added ‹› ttToggleTimeFiltero.‹› ttApplyTimeFiltero,‹› ttCleartimeFilter functions• Updated ‹› ttRenderSeqments and‹› ttRenderAudioSeqments to filter segments by time range•Filter shows only segments within the specified time period (e.g.. 9:45 to 10:30)Ask anvthindScreen Reader Optimized Ln 1, Col 1 Spaces: 4 UTF-8 LF Python 3.11.2 64-bit Teams Windsurf - Settings...
|
NULL
|
-6146905141991591436
|
NULL
|
visual_change
|
ocr
|
NULL
|
selectionViewTerminalWinaowmelt• screenpipe SSH: n selectionViewTerminalWinaowmelt• screenpipe SSH: nas — activity.pvmain.ov Mactivity.pyMX• screenpipe [SSH: nas)• _ #recycieV tr appDv"0insumers › activity.py › ...det audio seqments(tor date: date None = None) → List dict str, Any :Start, end = date range(d)interactions.pyapp› • DockernleWORKDIR /appQ copyrequirements.txt |RIN nin install --no-cache-dir -r requirements.txCOPY.14 SypocE 9a0016 CMD ("uvicorn", "main:app",Dockerfile (Working Tree) Xscreenpipe_sync_files.shWORKDIR /apPcopy requirements.extCOPY.eypose gaddCMD ["uvicorn",Dally - Platrorm • In z0m100% 152Thu 14 May 9:25:19•OKvRefactor Sync Script+0 .*•.tt-toolbar < display:flex; gap:10px; align-itens:center: flex-wrap:wrap; }-border); border-radius:6px; padding:8px; }solid var(--border); border-radius:8px; padding:12px 14px; displayThoughtsSELECTudio chunk id = c.idUNNEHHENEORDER BY t.timestampend.fetchallreturn dictr for r in rowsi7) .map(s BThoughts}) -map(a => {8 do salite19 db.salite-shmlDebua Consolel(abash-aoo +v @ M ã .1^ xAll requested chanaes comnlete• Addedi.ttcaudio-sen.active CSS class with white inset bordeModified <› ttRenderAudioSeaments/) to hiahliaht audio seaments within 5 seconds of current nositionAudio timeline now shows visual hiahliaht just like video timelineAudio auto-olav OfF ov derault•Changed _ttAutoPlayAudio from true to false•Updated button text to "*. Auto-Play Audio: OFF*• Modified ‹/› ttShowAudioTranscription() to only play audio when auto-play is enabledAudin romaine dicabled on page refresh and navigationCollansible time rance filter.•Added collapsible " 7 Time Range Filter" section with From/To time inputs•Added ‹› ttToggleTimeFiltero.‹› ttApplyTimeFiltero,‹› ttCleartimeFilter functions• Updated ‹› ttRenderSeqments and‹› ttRenderAudioSeqments to filter segments by time range•Filter shows only segments within the specified time period (e.g.. 9:45 to 10:30)Ask anvthindScreen Reader Optimized Ln 1, Col 1 Spaces: 4 UTF-8 LF Python 3.11.2 64-bit Teams Windsurf - Settings...
|
38640
|
NULL
|
NULL
|
NULL
|
|
38643
|
1435
|
6
|
2026-05-14T06:25:23.004218+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739923004_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:14 · Finder / Work
⏮ 30s
◀ 10s
⏸ Pause
10s ▶...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:14 · Finder / Work","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.38993055,"top":0.0,"width":0.05,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.4454861,"top":0.0,"width":0.046875,"height":0.033333335},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.49791667,"top":0.0,"width":0.058333334,"height":0.033888888},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.56180555,"top":0.0,"width":0.046527777,"height":0.033333335},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false}]...
|
-1032974693851033987
|
8632611839220001757
|
visual_change
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:14 · Finder / Work
⏮ 30s
◀ 10s
⏸ Pause
10s ▶...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38645
|
1436
|
4
|
2026-05-14T06:25:26.001834+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739926001_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.014960106,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.18994413,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.3463687,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.3575419,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.38068634,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.08739027,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.088986434,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.09297685,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.08579409,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.08579409,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.08579409,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.08579409,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.08579409,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.08579409,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.09098165,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.0905826,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.0905826,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.0905826,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.0905826,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.0905826,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.09098165,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false}]...
|
7172857787276359388
|
8632612251528473565
|
visual_change
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38644
|
1435
|
7
|
2026-05-14T06:25:26.011615+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739926011_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
8143923722802324200
|
8632612251536862173
|
visual_change
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter...
|
38643
|
NULL
|
NULL
|
NULL
|
|
38646
|
1436
|
5
|
2026-05-14T06:25:29.047520+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739929047_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:14 · QuickTime Player / PLanhat Petko interest event 2026-05-11.mp4
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:14
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.014960106,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.18994413,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.3463687,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.3575419,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.38068634,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.10853951,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.10853951,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.10814046,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.10814046,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.10814046,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.10454908,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.14205906,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.14604948,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.14604948,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.1819633,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.18156424,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.18156424,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.18156424,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"bounds":{"left":0.5021609,"top":0.1819633,"width":0.005319149,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"bounds":{"left":0.5147939,"top":0.18156424,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.5206117,"top":0.18156424,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"bounds":{"left":0.52393615,"top":0.18156424,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"bounds":{"left":0.5440492,"top":0.17797287,"width":0.027593086,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"bounds":{"left":0.5749667,"top":0.17797287,"width":0.016788565,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"bounds":{"left":0.45761302,"top":0.23743017,"width":0.10571808,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"bounds":{"left":0.813996,"top":0.2330407,"width":0.009807181,"height":0.018754989},"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"bounds":{"left":0.82795876,"top":0.23703113,"width":0.004155585,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"bounds":{"left":0.83643615,"top":0.2330407,"width":0.009640957,"height":0.018754989},"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"bounds":{"left":0.8494016,"top":0.23703113,"width":0.004654255,"height":0.011173184},"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"bounds":{"left":0.85538566,"top":0.23703113,"width":0.011136968,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"bounds":{"left":0.45910904,"top":0.32322428,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"bounds":{"left":0.47573137,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"bounds":{"left":0.4921875,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"bounds":{"left":0.50880986,"top":0.32322428,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"bounds":{"left":0.52526593,"top":0.32322428,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"bounds":{"left":0.5415558,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"bounds":{"left":0.55801195,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"bounds":{"left":0.57430184,"top":0.32322428,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"bounds":{"left":0.59075797,"top":0.32322428,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"bounds":{"left":0.6072141,"top":0.32322428,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"bounds":{"left":0.6236702,"top":0.32322428,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"bounds":{"left":0.64012635,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"bounds":{"left":0.6565825,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"bounds":{"left":0.67303854,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"bounds":{"left":0.68949467,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"bounds":{"left":0.7059508,"top":0.32322428,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"bounds":{"left":0.7224069,"top":0.32322428,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"bounds":{"left":0.7386968,"top":0.32322428,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"bounds":{"left":0.75515294,"top":0.32322428,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"bounds":{"left":0.77160907,"top":0.32322428,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"bounds":{"left":0.78806514,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"bounds":{"left":0.804355,"top":0.32322428,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"bounds":{"left":0.82081115,"top":0.32322428,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"bounds":{"left":0.8374335,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"bounds":{"left":0.85388964,"top":0.32322428,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:14 · QuickTime Player / PLanhat Petko interest event 2026-05-11.mp4","depth":10,"bounds":{"left":0.45628324,"top":0.36671987,"width":0.1505984,"height":0.011971269},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.45694813,"top":0.9888268,"width":0.023936171,"height":0.011173189},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.48354387,"top":0.98922586,"width":0.02244016,"height":0.010774136},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.5086436,"top":0.9888268,"width":0.027925532,"height":0.011173189},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.53922874,"top":0.98922586,"width":0.022273935,"height":0.010774136},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.56416225,"top":0.9888268,"width":0.024102394,"height":0.011173189},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.61486036,"top":0.9912211,"width":0.04870346,"height":0.00877893},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:14","depth":10,"bounds":{"left":0.857879,"top":0.99561054,"width":0.00930851,"height":0.004389465},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.45761302,"top":1.0,"width":0.011801862,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.47772607,"top":1.0,"width":0.011801862,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.4978391,"top":1.0,"width":0.009474734,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.515625,"top":1.0,"width":0.02144282,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.545379,"top":1.0,"width":0.017287234,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.5709774,"top":1.0,"width":0.010970744,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.5902593,"top":1.0,"width":0.03025266,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.62882316,"top":1.0,"width":0.010472074,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.6476064,"top":1.0,"width":0.017453458,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.673371,"top":1.0,"width":0.013630319,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.6953125,"top":1.0,"width":0.025598405,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.72922206,"top":1.0,"width":0.012134309,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":0.7496675,"top":1.0,"width":0.00930851,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":0.76728725,"top":1.0,"width":0.027426861,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"bounds":{"left":0.80302525,"top":1.0,"width":0.015791224,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"bounds":{"left":0.82712764,"top":1.0,"width":0.012965426,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"bounds":{"left":0.8484042,"top":1.0,"width":0.0068151597,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"bounds":{"left":0.8635306,"top":1.0,"width":0.0071476065,"height":-0.031125307},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-5027866807457910049
|
8637114889091558365
|
visual_change
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:14 · QuickTime Player / PLanhat Petko interest event 2026-05-11.mp4
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:14
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
38645
|
NULL
|
NULL
|
NULL
|
|
38647
|
1435
|
8
|
2026-05-14T06:25:29.461289+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739929461_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▶
📅 Time Range Filter
▶
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:14 · QuickTime Player / PLanhat Petko interest event 2026-05-11.mp4
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:14
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▶","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":true,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▶","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:14 · QuickTime Player / PLanhat Petko interest event 2026-05-11.mp4","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.38993055,"top":0.0,"width":0.05,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.4454861,"top":0.0,"width":0.046875,"height":0.033333335},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.49791667,"top":0.0,"width":0.058333334,"height":0.033888888},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.56180555,"top":0.0,"width":0.046527777,"height":0.033333335},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.61388886,"top":0.0,"width":0.050347224,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.71979165,"top":0.0,"width":0.10173611,"height":0.027222222},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:14","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.39131945,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.43333334,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.47534722,"top":0.0,"width":0.019791666,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.5125,"top":0.0,"width":0.044791665,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.5746528,"top":0.0,"width":0.036111113,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.628125,"top":0.0,"width":0.022916667,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.6684028,"top":0.0,"width":0.063194446,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.74895835,"top":0.0,"width":0.021875,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.7881944,"top":0.0,"width":0.036458332,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.8420139,"top":0.0,"width":0.028472222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.88784724,"top":0.0,"width":0.05347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.95868057,"top":0.0,"width":0.025347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.0013889074,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.038194418,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
4596330980756198279
|
8637114889091558365
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▶
📅 Time Range Filter
▶
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:14 · QuickTime Player / PLanhat Petko interest event 2026-05-11.mp4
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:14
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38648
|
1435
|
9
|
2026-05-14T06:25:30.850714+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739930850_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Mute tab
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXButton","text":"Mute tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
164333506082916558
|
9209073691026664413
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Mute tab
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini...
|
38647
|
NULL
|
NULL
|
NULL
|
|
38649
|
1436
|
6
|
2026-05-14T06:25:30.870887+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739930870_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Mute tab
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.014960106,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXButton","text":"Mute tab","depth":5,"bounds":{"left":0.011469414,"top":0.18994413,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.020113032,"top":0.19393456,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.18994413,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.3463687,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.3575419,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.38068634,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.10853951,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-5031078931393543184
|
8632611701772659677
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Mute tab
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38651
|
1436
|
7
|
2026-05-14T06:25:48.097479+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739948097_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.014960106,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.18994413,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.3463687,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.3575419,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.38068634,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.10694334,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.10694334,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.10654429,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.10654429,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.10654429,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.10295291,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.14046289,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.14445332,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.14445332,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.18036711,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-7315117967628904725
|
8632612251536862173
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:...
|
38649
|
NULL
|
NULL
|
NULL
|
|
38650
|
1435
|
10
|
2026-05-14T06:25:48.121288+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739948121_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-4061294285641519561
|
8632612251536862173
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38652
|
1436
|
8
|
2026-05-14T06:25:53.224359+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739953224_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:14 · iTerm2
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:14
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.014960106,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.18994413,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.3463687,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.3575419,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.38068634,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.056664005,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.09417398,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.0981644,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.0981644,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.13407822,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"bounds":{"left":0.5021609,"top":0.13407822,"width":0.005319149,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"bounds":{"left":0.5147939,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.5206117,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"bounds":{"left":0.52393615,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"bounds":{"left":0.5440492,"top":0.1300878,"width":0.027593086,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"bounds":{"left":0.5749667,"top":0.1300878,"width":0.016788565,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"bounds":{"left":0.45761302,"top":0.1895451,"width":0.10571808,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"bounds":{"left":0.813996,"top":0.18515563,"width":0.009807181,"height":0.018754989},"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"bounds":{"left":0.82795876,"top":0.18914606,"width":0.004155585,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"bounds":{"left":0.83643615,"top":0.18515563,"width":0.009640957,"height":0.018754989},"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"bounds":{"left":0.8494016,"top":0.18914606,"width":0.004654255,"height":0.011173184},"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"bounds":{"left":0.85538566,"top":0.18914606,"width":0.011136968,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"bounds":{"left":0.45910904,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"bounds":{"left":0.47573137,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"bounds":{"left":0.4921875,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"bounds":{"left":0.50880986,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"bounds":{"left":0.52526593,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"bounds":{"left":0.5415558,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"bounds":{"left":0.55801195,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"bounds":{"left":0.57430184,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"bounds":{"left":0.59075797,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"bounds":{"left":0.6072141,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"bounds":{"left":0.6236702,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"bounds":{"left":0.64012635,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"bounds":{"left":0.6565825,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"bounds":{"left":0.67303854,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"bounds":{"left":0.68949467,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"bounds":{"left":0.7059508,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"bounds":{"left":0.7224069,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"bounds":{"left":0.7386968,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"bounds":{"left":0.75515294,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"bounds":{"left":0.77160907,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"bounds":{"left":0.78806514,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"bounds":{"left":0.804355,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"bounds":{"left":0.82081115,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"bounds":{"left":0.8374335,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"bounds":{"left":0.85388964,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:14 · iTerm2","depth":10,"bounds":{"left":0.45628324,"top":0.31883478,"width":0.04055851,"height":0.011971269},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.45694813,"top":0.94094175,"width":0.023936171,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.48354387,"top":0.9413408,"width":0.02244016,"height":0.023942538},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.5086436,"top":0.94094175,"width":0.027925532,"height":0.02434158},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.53922874,"top":0.9413408,"width":0.022273935,"height":0.023942538},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.56416225,"top":0.94094175,"width":0.024102394,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.61486036,"top":0.943336,"width":0.04870346,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:14","depth":10,"bounds":{"left":0.857879,"top":0.9477255,"width":0.00930851,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.45761302,"top":0.98324025,"width":0.011801862,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.47772607,"top":0.98324025,"width":0.011801862,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.4978391,"top":0.98324025,"width":0.009474734,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.515625,"top":0.98324025,"width":0.02144282,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.545379,"top":0.98324025,"width":0.017287234,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.5709774,"top":0.98324025,"width":0.010970744,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.5902593,"top":0.98324025,"width":0.03025266,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.62882316,"top":0.98324025,"width":0.010472074,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.6476064,"top":0.98324025,"width":0.017453458,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.673371,"top":0.98324025,"width":0.013630319,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.6953125,"top":0.98324025,"width":0.025598405,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.72922206,"top":0.98324025,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":0.7496675,"top":0.98324025,"width":0.00930851,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":0.76728725,"top":0.98324025,"width":0.027426861,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"bounds":{"left":0.80302525,"top":0.98324025,"width":0.015791224,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"bounds":{"left":0.82712764,"top":0.98324025,"width":0.012965426,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"bounds":{"left":0.8484042,"top":0.98324025,"width":0.0068151597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"bounds":{"left":0.8635306,"top":0.98324025,"width":0.0071476065,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-5820302311816921180
|
8637114889091558365
|
visual_change
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:14 · iTerm2
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:14
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38654
|
1436
|
9
|
2026-05-14T06:25:59.245287+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739959245_m2.jpg...
|
Firefox
|
Usage | Windsurf — Work
|
1
|
windsurf.com/subscription/usage
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Usage | Windsurf
Usage | Windsurf
Close tab
JY-208 Usage | Windsurf
Usage | Windsurf
Close tab
JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app
JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app
[SRD-6848] Sidekick SMS issue - Jira
[SRD-6848] Sidekick SMS issue - Jira
Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira
Dependabot alerts · jiminny/prophet
Dependabot alerts · jiminny/prophet
[JY-19958] Upgrade BE libraries - May - Jira
[JY-19958] Upgrade BE libraries - May - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app
JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Userpilot | Ask Jiminny Report Generated
Userpilot | Ask Jiminny Report Generated
[JY-19957] Upgrade BE libraries - Apr - Jira
[JY-19957] Upgrade BE libraries - Apr - Jira
Dependabot alerts · jiminny/app
Dependabot alerts · jiminny/app
[JY-20891] Sidekick SMS issue - Jira
[JY-20891] Sidekick SMS issue - Jira
[SRD-6849] Recorded call does not appear on the dashboard - Jira
[SRD-6849] Recorded call does not appear on the dashboard - Jira
Jiminny
Jiminny
Jiminny
Jiminny
Jiminny
Jiminny
Configure SSH access to multiple environment - Engineering - Confluence
Configure SSH access to multiple environment - Engineering - Confluence
Useful commands - Engineering - Confluence
Useful commands - Engineering - Confluence
Dev Tools - Elastic
Dev Tools - Elastic
Jiminny
Jiminny
[SRD-6853] Moxso - Potential deal stages bug - Jira
[SRD-6853] Moxso - Potential deal stages bug - Jira
CloudWatch | eu-west-1
CloudWatch | eu-west-1
CloudWatch | eu-west-1
CloudWatch | eu-west-1
New Tab
Customize sidebar
Open Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
Windsurf
PRODUCTS
PRODUCTS
ENTERPRISE
ENTERPRISE
PRICING
PRICING
BLOG
BLOG
RESOURCES
RESOURCES
COMPANY
COMPANY
L
L
DOWNLOAD
DOWNLOAD
ACCOUNT
Profile
Profile
Notifications
Notifications
Settings
Settings
SUBSCRIPTION
Usage
Usage
FEATURES
Deploys
Deploys
Conversation Shares
Conversation Shares
Log out
Usage
Usage
Windsurf Usage Summary
Next billing cycle is tomorrow.
Your daily quota
97.00
% remaining
Daily quota resets every day and usage resumes once quota refreshes.
Resets
14 May, 11:00 EEST
Your weekly quota
31.00
% remaining
Weekly quota resets every week and can still limit usage after the daily reset.
Resets
17 May, 11:00 EEST
Extra usage balance available
$
-0.11
Once the quota is reached, Windsurf can continue to be used with free models.
To continue using premium models,
purchase extra usage
.
Purchase usage...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Usage | Windsurf","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Usage | Windsurf","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.029920213,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.06732048,"top":0.05905826,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.15658244,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[SRD-6848] Sidekick SMS issue - Jira","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[SRD-6848] Sidekick SMS issue - Jira","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.06632314,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.10106383,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Dependabot alerts · jiminny/prophet","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Dependabot alerts · jiminny/prophet","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.06216755,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[JY-19958] Upgrade BE libraries - May - Jira","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[JY-19958] Upgrade BE libraries - May - Jira","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.07762633,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[JY-20773] User Pilot not receiving events on report generated - Jira","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[JY-20773] User Pilot not receiving events on report generated - Jira","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.1200133,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.20977394,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"TypeError: League\\Flysystem\\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"TypeError: League\\Flysystem\\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.40475398,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Userpilot | Ask Jiminny Report Generated","depth":4,"bounds":{"left":0.0,"top":0.3463687,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Userpilot | Ask Jiminny Report Generated","depth":5,"bounds":{"left":0.013297873,"top":0.3575419,"width":0.07164229,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[JY-19957] Upgrade BE libraries - Apr - Jira","depth":4,"bounds":{"left":0.0,"top":0.3790902,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[JY-19957] Upgrade BE libraries - Apr - Jira","depth":5,"bounds":{"left":0.013297873,"top":0.39026338,"width":0.076296546,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Dependabot alerts · jiminny/app","depth":4,"bounds":{"left":0.0,"top":0.41181165,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Dependabot alerts · jiminny/app","depth":5,"bounds":{"left":0.013297873,"top":0.42298484,"width":0.05501995,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[JY-20891] Sidekick SMS issue - Jira","depth":4,"bounds":{"left":0.0,"top":0.4445331,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[JY-20891] Sidekick SMS issue - Jira","depth":5,"bounds":{"left":0.013297873,"top":0.4557063,"width":0.064494684,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[SRD-6849] Recorded call does not appear on the dashboard - Jira","depth":4,"bounds":{"left":0.0,"top":0.4772546,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[SRD-6849] Recorded call does not appear on the dashboard - Jira","depth":5,"bounds":{"left":0.013297873,"top":0.4884278,"width":0.11735372,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Jiminny","depth":4,"bounds":{"left":0.0,"top":0.509976,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Jiminny","depth":5,"bounds":{"left":0.013297873,"top":0.5211492,"width":0.013131649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Jiminny","depth":4,"bounds":{"left":0.0,"top":0.54269755,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Jiminny","depth":5,"bounds":{"left":0.013297873,"top":0.55387074,"width":0.013131649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Jiminny","depth":4,"bounds":{"left":0.0,"top":0.575419,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Jiminny","depth":5,"bounds":{"left":0.013297873,"top":0.5865922,"width":0.013131649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Configure SSH access to multiple environment - Engineering - Confluence","depth":4,"bounds":{"left":0.0,"top":0.60814047,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Configure SSH access to multiple environment - Engineering - Confluence","depth":5,"bounds":{"left":0.013297873,"top":0.61931366,"width":0.12898937,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Useful commands - Engineering - Confluence","depth":4,"bounds":{"left":0.0,"top":0.6408619,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Useful commands - Engineering - Confluence","depth":5,"bounds":{"left":0.013297873,"top":0.6520351,"width":0.079288565,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Dev Tools - Elastic","depth":4,"bounds":{"left":0.0,"top":0.6735834,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Dev Tools - Elastic","depth":5,"bounds":{"left":0.013297873,"top":0.6847566,"width":0.032247342,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Jiminny","depth":4,"bounds":{"left":0.0,"top":0.70630485,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Jiminny","depth":5,"bounds":{"left":0.013297873,"top":0.71747804,"width":0.013131649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[SRD-6853] Moxso - Potential deal stages bug - Jira","depth":4,"bounds":{"left":0.0,"top":0.7390263,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[SRD-6853] Moxso - Potential deal stages bug - Jira","depth":5,"bounds":{"left":0.013297873,"top":0.7501995,"width":0.09158909,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"CloudWatch | eu-west-1","depth":4,"bounds":{"left":0.0,"top":0.7717478,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"CloudWatch | eu-west-1","depth":5,"bounds":{"left":0.013297873,"top":0.782921,"width":0.041722074,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"CloudWatch | eu-west-1","depth":4,"bounds":{"left":0.0,"top":0.8044693,"width":0.07962101,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"CloudWatch | eu-west-1","depth":5,"bounds":{"left":0.013297873,"top":0.8156425,"width":0.041722074,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.8387869,"width":0.07413564,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Tabs from other devices","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXLink","text":"Windsurf","depth":8,"bounds":{"left":0.3337766,"top":0.07581804,"width":0.049534574,"height":0.015961692},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXLink","text":"PRODUCTS","depth":9,"bounds":{"left":0.42386967,"top":0.06304868,"width":0.03756649,"height":0.0415004},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"PRODUCTS","depth":10,"bounds":{"left":0.42785904,"top":0.07661612,"width":0.024268618,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"ENTERPRISE","depth":9,"bounds":{"left":0.46675533,"top":0.06304868,"width":0.043550532,"height":0.0415004},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"ENTERPRISE","depth":10,"bounds":{"left":0.47074467,"top":0.07661612,"width":0.03025266,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"PRICING","depth":9,"bounds":{"left":0.515625,"top":0.06304868,"width":0.029089095,"height":0.0415004},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"PRICING","depth":10,"bounds":{"left":0.51961434,"top":0.07661612,"width":0.021110373,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"BLOG","depth":9,"bounds":{"left":0.5500333,"top":0.06304868,"width":0.020113032,"height":0.0415004},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"BLOG","depth":10,"bounds":{"left":0.5540226,"top":0.07661612,"width":0.012134309,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"RESOURCES","depth":9,"bounds":{"left":0.57546544,"top":0.06304868,"width":0.04055851,"height":0.0415004},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"RESOURCES","depth":10,"bounds":{"left":0.5794548,"top":0.07661612,"width":0.027260639,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"COMPANY","depth":9,"bounds":{"left":0.6213431,"top":0.06304868,"width":0.034408245,"height":0.0415004},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"COMPANY","depth":10,"bounds":{"left":0.6253325,"top":0.07661612,"width":0.021110373,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"L","depth":8,"bounds":{"left":0.93151593,"top":0.06464485,"width":0.015957447,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"L","depth":11,"bounds":{"left":0.9383311,"top":0.07661612,"width":0.002493351,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"DOWNLOAD","depth":8,"bounds":{"left":0.94913566,"top":0.0518755,"width":0.05086434,"height":0.06384677},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"DOWNLOAD","depth":9,"bounds":{"left":0.94913566,"top":0.0518755,"width":0.05086434,"height":0.06384677},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"ACCOUNT","depth":11,"bounds":{"left":0.33776596,"top":0.1660016,"width":0.021110373,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Profile","depth":10,"bounds":{"left":0.3324468,"top":0.18355946,"width":0.06582447,"height":0.029130088},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Profile","depth":13,"bounds":{"left":0.33776596,"top":0.1895451,"width":0.014960106,"height":0.016759777},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Notifications","depth":10,"bounds":{"left":0.3324468,"top":0.21588188,"width":0.06582447,"height":0.02952913},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Notifications","depth":13,"bounds":{"left":0.33776596,"top":0.22226655,"width":0.030585106,"height":0.016759777},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Settings","depth":10,"bounds":{"left":0.3324468,"top":0.24860336,"width":0.06582447,"height":0.029130088},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Settings","depth":13,"bounds":{"left":0.33776596,"top":0.254988,"width":0.019780586,"height":0.016759777},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SUBSCRIPTION","depth":11,"bounds":{"left":0.33776596,"top":0.3028731,"width":0.036236703,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Usage","depth":10,"bounds":{"left":0.3324468,"top":0.3200319,"width":0.06582447,"height":0.02952913},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Usage","depth":13,"bounds":{"left":0.33776596,"top":0.3264166,"width":0.01462766,"height":0.016759777},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"FEATURES","depth":11,"bounds":{"left":0.33776596,"top":0.37430167,"width":0.024102394,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Deploys","depth":10,"bounds":{"left":0.3324468,"top":0.3914605,"width":0.06582447,"height":0.02952913},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Deploys","depth":13,"bounds":{"left":0.33776596,"top":0.39784518,"width":0.019115692,"height":0.016759777},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Conversation Shares","depth":10,"bounds":{"left":0.3324468,"top":0.42418197,"width":0.06582447,"height":0.029130088},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Conversation Shares","depth":13,"bounds":{"left":0.33776596,"top":0.43056664,"width":0.049700797,"height":0.016759777},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Log out","depth":10,"bounds":{"left":0.33776596,"top":0.9577015,"width":0.017785905,"height":0.016759777},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Usage","depth":9,"bounds":{"left":0.41422874,"top":0.16679968,"width":0.33178192,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Usage","depth":10,"bounds":{"left":0.41422874,"top":0.16679968,"width":0.039727394,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf Usage Summary","depth":11,"bounds":{"left":0.42519948,"top":0.24381484,"width":0.10704787,"height":0.02952913},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Next billing cycle is tomorrow.","depth":11,"bounds":{"left":0.42519948,"top":0.28611332,"width":0.06100399,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Your daily quota","depth":11,"bounds":{"left":0.42519948,"top":0.3196329,"width":0.047539894,"height":0.021149242},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"97.00","depth":11,"bounds":{"left":0.68650264,"top":0.32282522,"width":0.01512633,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"% remaining","depth":11,"bounds":{"left":0.701629,"top":0.32282522,"width":0.033410903,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Daily quota resets every day and usage resumes once quota refreshes.","depth":11,"bounds":{"left":0.42519948,"top":0.34357542,"width":0.14577793,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Resets","depth":11,"bounds":{"left":0.68351066,"top":0.34357542,"width":0.014960106,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14 May, 11:00 EEST","depth":11,"bounds":{"left":0.6984708,"top":0.34357542,"width":0.03656915,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Your weekly quota","depth":11,"bounds":{"left":0.42519948,"top":0.386672,"width":0.053856384,"height":0.021149242},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"31.00","depth":11,"bounds":{"left":0.68650264,"top":0.38986433,"width":0.01512633,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"% remaining","depth":11,"bounds":{"left":0.701629,"top":0.38986433,"width":0.033410903,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Weekly quota resets every week and can still limit usage after the daily reset.","depth":11,"bounds":{"left":0.42519948,"top":0.41061452,"width":0.15774602,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Resets","depth":11,"bounds":{"left":0.6838431,"top":0.41061452,"width":0.014960106,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17 May, 11:00 EEST","depth":11,"bounds":{"left":0.6988032,"top":0.41061452,"width":0.036236703,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Extra usage balance available","depth":11,"bounds":{"left":0.42519948,"top":0.46049482,"width":0.086269945,"height":0.021149242},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"$","depth":11,"bounds":{"left":0.71758646,"top":0.46049482,"width":0.0038231383,"height":0.021149242},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"-0.11","depth":11,"bounds":{"left":0.72140956,"top":0.46049482,"width":0.013630319,"height":0.021149242},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the quota is reached, Windsurf can continue to be used with free models.","depth":11,"bounds":{"left":0.42519948,"top":0.4888268,"width":0.16373006,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To continue using premium models,","depth":11,"bounds":{"left":0.42519948,"top":0.50359136,"width":0.0731383,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"purchase extra usage","depth":11,"bounds":{"left":0.49950132,"top":0.50359136,"width":0.044215426,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":11,"bounds":{"left":0.5437167,"top":0.50359136,"width":0.00083111704,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Purchase usage","depth":11,"bounds":{"left":0.68766624,"top":0.48762968,"width":0.04737367,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false}]...
|
6984495974967014510
|
6355800457719906884
|
visual_change
|
accessibility
|
NULL
|
Usage | Windsurf
Usage | Windsurf
Close tab
JY-208 Usage | Windsurf
Usage | Windsurf
Close tab
JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app
JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app
[SRD-6848] Sidekick SMS issue - Jira
[SRD-6848] Sidekick SMS issue - Jira
Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira
Dependabot alerts · jiminny/prophet
Dependabot alerts · jiminny/prophet
[JY-19958] Upgrade BE libraries - May - Jira
[JY-19958] Upgrade BE libraries - May - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app
JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Userpilot | Ask Jiminny Report Generated
Userpilot | Ask Jiminny Report Generated
[JY-19957] Upgrade BE libraries - Apr - Jira
[JY-19957] Upgrade BE libraries - Apr - Jira
Dependabot alerts · jiminny/app
Dependabot alerts · jiminny/app
[JY-20891] Sidekick SMS issue - Jira
[JY-20891] Sidekick SMS issue - Jira
[SRD-6849] Recorded call does not appear on the dashboard - Jira
[SRD-6849] Recorded call does not appear on the dashboard - Jira
Jiminny
Jiminny
Jiminny
Jiminny
Jiminny
Jiminny
Configure SSH access to multiple environment - Engineering - Confluence
Configure SSH access to multiple environment - Engineering - Confluence
Useful commands - Engineering - Confluence
Useful commands - Engineering - Confluence
Dev Tools - Elastic
Dev Tools - Elastic
Jiminny
Jiminny
[SRD-6853] Moxso - Potential deal stages bug - Jira
[SRD-6853] Moxso - Potential deal stages bug - Jira
CloudWatch | eu-west-1
CloudWatch | eu-west-1
CloudWatch | eu-west-1
CloudWatch | eu-west-1
New Tab
Customize sidebar
Open Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
Windsurf
PRODUCTS
PRODUCTS
ENTERPRISE
ENTERPRISE
PRICING
PRICING
BLOG
BLOG
RESOURCES
RESOURCES
COMPANY
COMPANY
L
L
DOWNLOAD
DOWNLOAD
ACCOUNT
Profile
Profile
Notifications
Notifications
Settings
Settings
SUBSCRIPTION
Usage
Usage
FEATURES
Deploys
Deploys
Conversation Shares
Conversation Shares
Log out
Usage
Usage
Windsurf Usage Summary
Next billing cycle is tomorrow.
Your daily quota
97.00
% remaining
Daily quota resets every day and usage resumes once quota refreshes.
Resets
14 May, 11:00 EEST
Your weekly quota
31.00
% remaining
Weekly quota resets every week and can still limit usage after the daily reset.
Resets
17 May, 11:00 EEST
Extra usage balance available
$
-0.11
Once the quota is reached, Windsurf can continue to be used with free models.
To continue using premium models,
purchase extra usage
.
Purchase usage...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38653
|
1435
|
11
|
2026-05-14T06:25:59.263649+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739959263_m1.jpg...
|
Firefox
|
Usage | Windsurf — Work
|
1
|
windsurf.com/subscription/usage
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Usage | Windsurf
Usage | Windsurf
Close tab
JY-208 Usage | Windsurf
Usage | Windsurf
Close tab
JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app
JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app
[SRD-6848] Sidekick SMS issue - Jira
[SRD-6848] Sidekick SMS issue - Jira
Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira
Dependabot alerts · jiminny/prophet
Dependabot alerts · jiminny/prophet
[JY-19958] Upgrade BE libraries - May - Jira
[JY-19958] Upgrade BE libraries - May - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app
JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Userpilot | Ask Jiminny Report Generated
Userpilot | Ask Jiminny Report Generated
[JY-19957] Upgrade BE libraries - Apr - Jira
[JY-19957] Upgrade BE libraries - Apr - Jira
Dependabot alerts · jiminny/app
Dependabot alerts · jiminny/app
[JY-20891] Sidekick SMS issue - Jira
[JY-20891] Sidekick SMS issue - Jira
[SRD-6849] Recorded call does not appear on the dashboard - Jira
[SRD-6849] Recorded call does not appear on the dashboard - Jira
Jiminny
Jiminny
Jiminny
Jiminny
Jiminny
Jiminny
Configure SSH access to multiple environment - Engineering - Confluence
Configure SSH access to multiple environment - Engineering - Confluence
Useful commands - Engineering - Confluence
Useful commands - Engineering - Confluence
Dev Tools - Elastic
Dev Tools - Elastic
Jiminny
Jiminny
[SRD-6853] Moxso - Potential deal stages bug - Jira
[SRD-6853] Moxso - Potential deal stages bug - Jira
CloudWatch | eu-west-1
CloudWatch | eu-west-1
CloudWatch | eu-west-1
CloudWatch | eu-west-1
New Tab
Customize sidebar
Open Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
Windsurf
PRODUCTS
PRODUCTS
ENTERPRISE
ENTERPRISE
PRICING
PRICING
BLOG
BLOG
RESOURCES
RESOURCES
COMPANY
COMPANY
L
L
DOWNLOAD
DOWNLOAD
ACCOUNT
Profile
Profile
Notifications
Notifications
Settings
Settings
SUBSCRIPTION
Usage
Usage
FEATURES
Deploys
Deploys
Conversation Shares
Conversation Shares
Log out
Usage
Usage
Windsurf Usage Summary
Next billing cycle is tomorrow.
Your daily quota
97.00
% remaining
Daily quota resets every day and usage resumes once quota refreshes.
Resets
14 May, 11:00 EEST
Your weekly quota
31.00
% remaining
Weekly quota resets every week and can still limit usage after the daily reset.
Resets
17 May, 11:00 EEST
Extra usage balance available
$
-0.11
Once the quota is reached, Windsurf can continue to be used with free models.
To continue using premium models,
purchase extra usage
.
Purchase usage...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Usage | Windsurf","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Usage | Windsurf","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[SRD-6848] Sidekick SMS issue - Jira","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[SRD-6848] Sidekick SMS issue - Jira","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Dependabot alerts · jiminny/prophet","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Dependabot alerts · jiminny/prophet","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[JY-19958] Upgrade BE libraries - May - Jira","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[JY-19958] Upgrade BE libraries - May - Jira","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[JY-20773] User Pilot not receiving events on report generated - Jira","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[JY-20773] User Pilot not receiving events on report generated - Jira","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"TypeError: League\\Flysystem\\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"TypeError: League\\Flysystem\\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Userpilot | Ask Jiminny Report Generated","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Userpilot | Ask Jiminny Report Generated","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[JY-19957] Upgrade BE libraries - Apr - Jira","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[JY-19957] Upgrade BE libraries - Apr - Jira","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Dependabot alerts · jiminny/app","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Dependabot alerts · jiminny/app","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[JY-20891] Sidekick SMS issue - Jira","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[JY-20891] Sidekick SMS issue - Jira","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[SRD-6849] Recorded call does not appear on the dashboard - Jira","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[SRD-6849] Recorded call does not appear on the dashboard - Jira","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Jiminny","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Jiminny","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Jiminny","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Jiminny","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Jiminny","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Jiminny","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Configure SSH access to multiple environment - Engineering - Confluence","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Configure SSH access to multiple environment - Engineering - Confluence","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Useful commands - Engineering - Confluence","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Useful commands - Engineering - Confluence","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Dev Tools - Elastic","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Dev Tools - Elastic","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Jiminny","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Jiminny","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"[SRD-6853] Moxso - Potential deal stages bug - Jira","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"[SRD-6853] Moxso - Potential deal stages bug - Jira","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"CloudWatch | eu-west-1","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"CloudWatch | eu-west-1","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"CloudWatch | eu-west-1","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"CloudWatch | eu-west-1","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Tabs from other devices","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXLink","text":"Windsurf","depth":8,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXLink","text":"PRODUCTS","depth":9,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"PRODUCTS","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"ENTERPRISE","depth":9,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"ENTERPRISE","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"PRICING","depth":9,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"PRICING","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"BLOG","depth":9,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"BLOG","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"RESOURCES","depth":9,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"RESOURCES","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"COMPANY","depth":9,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"COMPANY","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"L","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"L","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"DOWNLOAD","depth":8,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"DOWNLOAD","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"ACCOUNT","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Profile","depth":10,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Profile","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Notifications","depth":10,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Notifications","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Settings","depth":10,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Settings","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SUBSCRIPTION","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Usage","depth":10,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Usage","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"FEATURES","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Deploys","depth":10,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Deploys","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Conversation Shares","depth":10,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Conversation Shares","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Log out","depth":10,"bounds":{"left":0.14097223,"top":0.0,"width":0.03715278,"height":0.023333333},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Usage","depth":9,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Usage","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf Usage Summary","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Next billing cycle is tomorrow.","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Your daily quota","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"97.00","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"% remaining","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Daily quota resets every day and usage resumes once quota refreshes.","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Resets","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14 May, 11:00 EEST","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Your weekly quota","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"31.00","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"% remaining","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Weekly quota resets every week and can still limit usage after the daily reset.","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Resets","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17 May, 11:00 EEST","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Extra usage balance available","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"$","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"-0.11","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the quota is reached, Windsurf can continue to be used with free models.","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To continue using premium models,","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"purchase extra usage","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Purchase usage","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false}]...
|
6984495974967014510
|
6355800457719906884
|
visual_change
|
accessibility
|
NULL
|
Usage | Windsurf
Usage | Windsurf
Close tab
JY-208 Usage | Windsurf
Usage | Windsurf
Close tab
JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app
JY-20891 add support for secondary email by LakyLak · Pull Request #12073 · jiminny/app
[SRD-6848] Sidekick SMS issue - Jira
[SRD-6848] Sidekick SMS issue - Jira
Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira
Platform Sprint 4 Q2 - Platform Team - Scrum Board - Jira
Dependabot alerts · jiminny/prophet
Dependabot alerts · jiminny/prophet
[JY-19958] Upgrade BE libraries - May - Jira
[JY-19958] Upgrade BE libraries - May - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
[JY-20773] User Pilot not receiving events on report generated - Jira
JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app
JY-19957 | Remove abanded sympfony debug, compose upgrade by nikolaybiaivanov · Pull Request #12022 · jiminny/app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
TypeError: League\Flysystem\Filesystem::has(): Argument #1 ($location) must be of type string, null given, called in /home/jiminny/vendor/laravel/framework/src/Illuminate/Filesystem/FilesystemAdapter.php on line 218 — jiminny — app
Userpilot | Ask Jiminny Report Generated
Userpilot | Ask Jiminny Report Generated
[JY-19957] Upgrade BE libraries - Apr - Jira
[JY-19957] Upgrade BE libraries - Apr - Jira
Dependabot alerts · jiminny/app
Dependabot alerts · jiminny/app
[JY-20891] Sidekick SMS issue - Jira
[JY-20891] Sidekick SMS issue - Jira
[SRD-6849] Recorded call does not appear on the dashboard - Jira
[SRD-6849] Recorded call does not appear on the dashboard - Jira
Jiminny
Jiminny
Jiminny
Jiminny
Jiminny
Jiminny
Configure SSH access to multiple environment - Engineering - Confluence
Configure SSH access to multiple environment - Engineering - Confluence
Useful commands - Engineering - Confluence
Useful commands - Engineering - Confluence
Dev Tools - Elastic
Dev Tools - Elastic
Jiminny
Jiminny
[SRD-6853] Moxso - Potential deal stages bug - Jira
[SRD-6853] Moxso - Potential deal stages bug - Jira
CloudWatch | eu-west-1
CloudWatch | eu-west-1
CloudWatch | eu-west-1
CloudWatch | eu-west-1
New Tab
Customize sidebar
Open Google Gemini (⌃X)
Tabs from other devices
Open history (⇧⌘H)
Open bookmarks (⌘B)
Windsurf
PRODUCTS
PRODUCTS
ENTERPRISE
ENTERPRISE
PRICING
PRICING
BLOG
BLOG
RESOURCES
RESOURCES
COMPANY
COMPANY
L
L
DOWNLOAD
DOWNLOAD
ACCOUNT
Profile
Profile
Notifications
Notifications
Settings
Settings
SUBSCRIPTION
Usage
Usage
FEATURES
Deploys
Deploys
Conversation Shares
Conversation Shares
Log out
Usage
Usage
Windsurf Usage Summary
Next billing cycle is tomorrow.
Your daily quota
97.00
% remaining
Daily quota resets every day and usage resumes once quota refreshes.
Resets
14 May, 11:00 EEST
Your weekly quota
31.00
% remaining
Weekly quota resets every week and can still limit usage after the daily reset.
Resets
17 May, 11:00 EEST
Extra usage balance available
$
-0.11
Once the quota is reached, Windsurf can continue to be used with free models.
To continue using premium models,
purchase extra usage
.
Purchase usage...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38655
|
1435
|
12
|
2026-05-14T06:26:02.292067+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739962292_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
All docs · AFFiNE
app.affine.pro
Screenpipe — Arch All docs · AFFiNE
app.affine.pro
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
Close tab
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between...
|
[{"role":"AXStaticText","text& [{"role":"AXStaticText","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"app.affine.pro","depth":4,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-5969886183227583701
|
9138141247519644551
|
visual_change
|
accessibility
|
NULL
|
All docs · AFFiNE
app.affine.pro
Screenpipe — Arch All docs · AFFiNE
app.affine.pro
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
Close tab
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38656
|
1436
|
10
|
2026-05-14T06:26:02.300226+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739962300_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
All docs · AFFiNE
app.affine.pro
Screenpipe — Arch All docs · AFFiNE
app.affine.pro
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
Close tab
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Close tab
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago....
|
[{"role":"AXStaticText","text& [{"role":"AXStaticText","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.07280585,"top":0.09177973,"width":0.030751329,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"app.affine.pro","depth":4,"bounds":{"left":0.07280585,"top":0.102553874,"width":0.02443484,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.09177973,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.1245012,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"New Tab","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"New Tab","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.014960106,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.18994413,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.3463687,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.3575419,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.38068634,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
4832609078165448232
|
-85226391825490025
|
visual_change
|
accessibility
|
NULL
|
All docs · AFFiNE
app.affine.pro
Screenpipe — Arch All docs · AFFiNE
app.affine.pro
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
Close tab
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Close tab
New Tab
New Tab
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago....
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38657
|
1435
|
13
|
2026-05-14T06:26:02.959310+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739962959_m1.jpg...
|
Firefox
|
New Tab — Personal
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Close tab
Screenpipe — Archive
Screenpipe — Archive
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"New Tab","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false}]...
|
-2415542185434773133
|
528495708356003787
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Close tab
Screenpipe — Archive
Screenpipe — Archive
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center...
|
38655
|
NULL
|
NULL
|
NULL
|
|
38658
|
1436
|
11
|
2026-05-14T06:26:02.959349+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739962959_m2.jpg...
|
Firefox
|
New Tab — Personal
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Close tab
Screenpipe — Archive
Screenpipe — Archive
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"New Tab","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.014960106,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.28172386,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.30327216,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.31444532,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.33599362,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.3471668,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.36871508,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false}]...
|
9056225343754594828
|
2833212783286339531
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Close tab
Screenpipe — Archive
Screenpipe — Archive
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search...
|
38656
|
NULL
|
NULL
|
NULL
|
|
38659
|
1435
|
14
|
2026-05-14T06:26:03.961061+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739963961_m1.jpg...
|
Firefox
|
New Tab — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
New Tab
about:newtab
Screenpipe — Archive
Screenpi New Tab
about:newtab
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Close tab
Screenpipe — Archive
Screenpipe — Archive
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources...
|
[{"role":"AXStaticText","text& [{"role":"AXStaticText","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"about:newtab","depth":4,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"New Tab","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-2585975510035951675
|
9212447352969943703
|
click
|
accessibility
|
NULL
|
New Tab
about:newtab
Screenpipe — Archive
Screenpi New Tab
about:newtab
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Close tab
Screenpipe — Archive
Screenpipe — Archive
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38660
|
1436
|
12
|
2026-05-14T06:26:03.980080+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739963980_m2.jpg...
|
Firefox
|
New Tab — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
New Tab
about:newtab
Screenpipe — Archive
Screenpi New Tab
about:newtab
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Close tab
Screenpipe — Archive
Screenpipe — Archive
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:...
|
[{"role":"AXStaticText","text& [{"role":"AXStaticText","text":"New Tab","depth":4,"bounds":{"left":0.07280585,"top":0.17956904,"width":0.015458777,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"about:newtab","depth":4,"bounds":{"left":0.07280585,"top":0.19034317,"width":0.023936171,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.074221864,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.08539505,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.10694334,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.11811652,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.1396648,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.15083799,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"New Tab","depth":4,"bounds":{"left":0.0,"top":0.17238627,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"New Tab","depth":5,"bounds":{"left":0.013297873,"top":0.18355946,"width":0.014960106,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.17956904,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.20510775,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.21628092,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.23782921,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.2490024,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.27055067,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.28172386,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.30327216,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.31444532,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.33599362,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.3471668,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.36871508,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.37988827,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.40303272,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.07741421,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.07741421,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.12609737,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.12609737,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.12689546,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.132083,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.12609737,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.12609737,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.12609737,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.16999201,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.17238627,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
1314954729990720976
|
9138281033605765774
|
click
|
accessibility
|
NULL
|
New Tab
about:newtab
Screenpipe — Archive
Screenpi New Tab
about:newtab
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
New Tab
New Tab
Close tab
Screenpipe — Archive
Screenpipe — Archive
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38661
|
1436
|
13
|
2026-05-14T06:26:05.334667+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739965334_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
app.screenpipe.lakylak.xyz
Sc Screenpipe — Archive
app.screenpipe.lakylak.xyz
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow...
|
[{"role":"AXStaticText","text& [{"role":"AXStaticText","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.07280585,"top":0.15722266,"width":0.03956117,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"app.screenpipe.lakylak.xyz","depth":4,"bounds":{"left":0.07280585,"top":0.16799681,"width":0.047041222,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.056664005,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.09417398,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.0981644,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.0981644,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.13407822,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"bounds":{"left":0.5021609,"top":0.13407822,"width":0.005319149,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"bounds":{"left":0.5147939,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.5206117,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"bounds":{"left":0.52393615,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"bounds":{"left":0.5440492,"top":0.1300878,"width":0.027593086,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"bounds":{"left":0.5749667,"top":0.1300878,"width":0.016788565,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"bounds":{"left":0.45761302,"top":0.1895451,"width":0.10571808,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"bounds":{"left":0.813996,"top":0.18515563,"width":0.009807181,"height":0.018754989},"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"bounds":{"left":0.82795876,"top":0.18914606,"width":0.004155585,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"bounds":{"left":0.83643615,"top":0.18515563,"width":0.009640957,"height":0.018754989},"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"bounds":{"left":0.8494016,"top":0.18914606,"width":0.004654255,"height":0.011173184},"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"bounds":{"left":0.85538566,"top":0.18914606,"width":0.011136968,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
2798846092146083533
|
8632611289464187869
|
visual_change
|
accessibility
|
NULL
|
Screenpipe — Archive
app.screenpipe.lakylak.xyz
Sc Screenpipe — Archive
app.screenpipe.lakylak.xyz
Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow...
|
38660
|
NULL
|
NULL
|
NULL
|
|
38662
|
1435
|
15
|
2026-05-14T06:26:08.346953+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739968346_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · iTerm2
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · iTerm2","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.38993055,"top":0.0,"width":0.05,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.4454861,"top":0.0,"width":0.046875,"height":0.033333335},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.49791667,"top":0.0,"width":0.058333334,"height":0.033888888},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.56180555,"top":0.0,"width":0.046527777,"height":0.033333335},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.61388886,"top":0.0,"width":0.050347224,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.71979165,"top":0.0,"width":0.10173611,"height":0.027222222},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:15","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.39131945,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.43333334,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.47534722,"top":0.0,"width":0.019791666,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.5125,"top":0.0,"width":0.044791665,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.5746528,"top":0.0,"width":0.036111113,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.628125,"top":0.0,"width":0.022916667,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.6684028,"top":0.0,"width":0.063194446,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.74895835,"top":0.0,"width":0.021875,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.7881944,"top":0.0,"width":0.036458332,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.8420139,"top":0.0,"width":0.028472222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.88784724,"top":0.0,"width":0.05347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.95868057,"top":0.0,"width":0.025347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.0013889074,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.038194418,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-8187987799368247897
|
8637114889091558357
|
visual_change
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · iTerm2
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
38659
|
NULL
|
NULL
|
NULL
|
|
38663
|
NULL
|
0
|
2026-05-14T06:26:09.928550+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739969928_m1.jpg...
|
Slack
|
Unread Messages - Jiminny Inc - 4 new items - Slac Unread Messages - Jiminny Inc - 4 new items - Slack...
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read...
|
[{"role":"AXPopUpButton","text [{"role":"AXPopUpButton","text":"Switch workspaces… (Jiminny Inc) Has new messages","depth":14,"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"Home","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXStaticText","text":"Home","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"DMs","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"DMs","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Activity","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Activity","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Files","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Files","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Later","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Later","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"More…","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"More","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Unreads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Threads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Huddles","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Drafts & sent","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"1","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Directories","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-x-integration-app","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"platform-inner-team","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ai-chapter","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"alerts","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"backend","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"bugs","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"confusion-clinic","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"curiosity_lab","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"engineering","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"general","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-bg","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"platform-tickets","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"product_launches","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"random","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"releases","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"sofia-office","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"support","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"thank-yous","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"the_people_of_jiminny","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Mario Georgiev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"James Graham","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Stoyan Tanev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Petko Kashinski","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Aneliya Angelova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas Kovalik","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"you","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Jira Cloud","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Toast","depth":23,"bounds":{"left":0.56805557,"top":0.0,"width":0.024305556,"height":0.02},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"@Toast section","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Toast","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"1 message","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Review Toast","depth":22,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 2:23:21 PM","depth":22,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"2:23 PM","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"stefka-jiminny","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"stefka-jiminny","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"on","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"'s PR","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"by","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"10 commits・260 files changed","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"JIRA:","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-18091","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-18091","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Deployment notes:","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"• None","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"jiminny/app","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"jiminny/app","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Added by","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Toast for GitHub","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast for GitHub","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"@Jira Cloud section","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Jira Cloud","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Jira Cloud","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"3 messages","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Press","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Esc","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"to","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false}]...
|
-6547574844394361155
|
4917355278388726880
|
app_switch
|
hybrid
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
iTerm2ShellEditViewSessionScriptsProfilesWindowHelp> 0 lilDaily - Platform - in 19m100% <478• Thu 14 May 9:26:09181screenpipe"-zshDOCKERO 81DEV (-zsh)O ₴2APP (-zsh)883whisper_model_load:n_mels= 80whisper_model_load:whisper_model_load:ftype= 1qntvr=0whisper_model_load:type= 1 (tiny)whisper_model_load:adding1608extra tokenswhisper_model_load:n_langs99whisper_model_load:Metaltotalsize =77.11 MBwhisper_model_load: modelsize77.11 MB2026-05-14T09:25:08.714171ZINFOscreenpipe_audio::transcription::engine: whisper model loadedsuccessfullywhisper_backend_init_gpu: device 0: Metal (type: 1)whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu:using Metal backendggml_metal_init: allocatingggml_metal_init:found device: Apple M1ggml_metal_init:picking default device: Apple M1ggmlmetalinit: use fusion= true9screenpipe*885ec2-user@ip-10-30-129-...₴6ec2-user@ip-10-20-31-14... *7W31NNloliTermwhlsper-tree-scuce.cumpuceTIU2026-05-14T09:25:08.721297ZINFOscreenpipe_audio::audio_manager::manager:transcription session created(will bereused across segments)2026-05-14T09:25:08.727575ZINFOscreenpipe_audio::audio_manager::manager: seeded 21 speakers (named + unnamed) from DB into embedding manager2026-05-14T09:25:08.727664ZINFOscreenpipe_audio::audio_manager::manager: audio manager started2026-05-14T09:25:08.727731ZINFOscreenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events2026-05-14709:25:09.238925ZINFOscreenpipe_audio: :device::device_manager: starting recording for device: System Audio (output)2026-05-14T09:25:09.325492ZINFOscreenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)2026-05-14T09:25:09.326604ZINFOscreenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)2026-05-14709:25:09.3266572INFOscreenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)2026-05-14T09:25:16.929049ZWARNscreenpipe_ally::tree::macos_lines: lines: AXUIElementCopyParameterizedAttributeValue(AXLineForIndex) failed status=os::Status { raw: -25212,fcchelp:"https://www.osstatus.com?search=-25212"}- first failure (further failures suppressed); search highlights will fall back to paragraph bbox on this app2026-05-14T09:25:42.118426ZINFOscreenpipe_audio::transcription::handle_new_transcript: device System Audio (output) skipping duplicate transcript (entire content overlaps withprevious)2026-05-14T09:26:02.676206ZROM\nframes\nWHERE\nWARNsqlx::query:summary="SELECT id,snapshot_path, device_name,snapshot_pathISNOTNULL\n.."ANDtimestamp < ?1\nORDER BY\ndevice_name, \ndb.statement="\n\nSELECT\nid, \nsnapshot_path, \ndevice_name, \ntimestamp\nFtimestamp ASC\nLIMIT\n5000\n'rows_affected=0 rows_returned=56elapsed=4.131920875s2026-05-14T09:26:02.676359Z2026-05-14T09:26:04.733866Z2026-05-14T09:26:06.932633ZINFOINFOINFOscreenpipe_engine::snapshot_compaction: snapshot compaction: found 56eligible framesscreenpipe.engine::snapshot_compaction: snapshot compaction: 29 frames,4.OMB+ 1.9MB (2.1x),JPEGs deletedengine: :snapshot_compaction: snapshot compaction: 25 frames, 4.3MB→ 2.2MB (2.0x),25 JPEGSdeleted...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38664
|
NULL
|
0
|
2026-05-14T06:26:09.928590+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739969928_m2.jpg...
|
Slack
|
Unread Messages - Jiminny Inc - 4 new items - Slac Unread Messages - Jiminny Inc - 4 new items - Slack...
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark...
|
[{"role":"AXPopUpButton","text [{"role":"AXPopUpButton","text":"Switch workspaces… (Jiminny Inc) Has new messages","depth":14,"bounds":{"left":0.5056516,"top":0.058260176,"width":0.011968086,"height":0.028731046},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"Home","depth":14,"bounds":{"left":0.50299203,"top":0.10055866,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXStaticText","text":"Home","depth":16,"bounds":{"left":0.50664896,"top":0.13806863,"width":0.009973404,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"DMs","depth":14,"bounds":{"left":0.50299203,"top":0.15482841,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"DMs","depth":16,"bounds":{"left":0.50764626,"top":0.19233839,"width":0.007978723,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Activity","depth":14,"bounds":{"left":0.50299203,"top":0.20909816,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Activity","depth":16,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.012965426,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.0026595744,"height":0.011173184}},{"char_start":1,"char_count":7,"bounds":{"left":0.50764626,"top":0.24660814,"width":0.010638298,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Files","depth":14,"bounds":{"left":0.50299203,"top":0.26336792,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Files","depth":16,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0076462766,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5099734,"top":0.3008779,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Later","depth":14,"bounds":{"left":0.50299203,"top":0.31763768,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Later","depth":16,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.008643617,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5093085,"top":0.35514766,"width":0.0066489363,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"More…","depth":14,"bounds":{"left":0.50299203,"top":0.3719074,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"More","depth":16,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.008976064,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.0033244682,"height":0.011173184}},{"char_start":1,"char_count":3,"bounds":{"left":0.5106383,"top":0.4094174,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXStaticText","text":"Unreads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Threads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Huddles","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Drafts & sent","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"1","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Directories","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-x-integration-app","depth":23,"bounds":{"left":0.5422208,"top":0.15562649,"width":0.043882977,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.15562649,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":24,"bounds":{"left":0.54355055,"top":0.15562649,"width":0.05418883,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"platform-inner-team","depth":23,"bounds":{"left":0.5422208,"top":0.17797287,"width":0.04454787,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.17797287,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":18,"bounds":{"left":0.54521275,"top":0.17797287,"width":0.04155585,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"ai-chapter","depth":23,"bounds":{"left":0.5422208,"top":0.23064645,"width":0.022273935,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.23064645,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54488033,"top":0.23064645,"width":0.019614361,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"alerts","depth":23,"bounds":{"left":0.5422208,"top":0.2529928,"width":0.012300532,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.2529928,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":5,"bounds":{"left":0.54488033,"top":0.2529928,"width":0.00930851,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"backend","depth":23,"bounds":{"left":0.5422208,"top":0.2753392,"width":0.018284574,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.2753392,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54521275,"top":0.2753392,"width":0.015292553,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"bugs","depth":23,"bounds":{"left":0.5422208,"top":0.29768556,"width":0.010638298,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.29768556,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":3,"bounds":{"left":0.54521275,"top":0.29768556,"width":0.00731383,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"confusion-clinic","depth":23,"bounds":{"left":0.5422208,"top":0.3200319,"width":0.034574468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.3200319,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54454786,"top":0.3200319,"width":0.032247342,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"curiosity_lab","depth":23,"bounds":{"left":0.5422208,"top":0.3423783,"width":0.027593086,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.3423783,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54454786,"top":0.3423783,"width":0.025265958,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"engineering","depth":23,"bounds":{"left":0.5422208,"top":0.36472467,"width":0.025930852,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.36472467,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":10,"bounds":{"left":0.54488033,"top":0.36472467,"width":0.022938829,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"general","depth":23,"bounds":{"left":0.5422208,"top":0.38707104,"width":0.016289894,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.38707104,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54488033,"top":0.38707104,"width":0.013297873,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"jiminny-bg","depth":23,"bounds":{"left":0.5422208,"top":0.4094174,"width":0.023271276,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.4094174,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54355055,"top":0.4094174,"width":0.021609042,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"platform-tickets","depth":23,"bounds":{"left":0.5422208,"top":0.43176377,"width":0.034906916,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.43176377,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54521275,"top":0.43176377,"width":0.031914894,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"product_launches","depth":23,"bounds":{"left":0.5422208,"top":0.45411015,"width":0.03856383,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.45411015,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54521275,"top":0.45411015,"width":0.03557181,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"random","depth":23,"bounds":{"left":0.5422208,"top":0.4764565,"width":0.016954787,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.4764565,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":5,"bounds":{"left":0.54421544,"top":0.4764565,"width":0.014960106,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"releases","depth":23,"bounds":{"left":0.5422208,"top":0.49880287,"width":0.01761968,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.49880287,"width":0.0016622341,"height":0.014365523}},{"char_start":1,"char_count":7,"bounds":{"left":0.54388297,"top":0.49880287,"width":0.015957447,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"sofia-office","depth":23,"bounds":{"left":0.5422208,"top":0.5211492,"width":0.024601065,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.5211492,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54454786,"top":0.5211492,"width":0.021941489,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"support","depth":23,"bounds":{"left":0.5422208,"top":0.5434956,"width":0.017287234,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.5434956,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54454786,"top":0.5434956,"width":0.01462766,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"thank-yous","depth":23,"bounds":{"left":0.5422208,"top":0.565842,"width":0.024601065,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.565842,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54421544,"top":0.565842,"width":0.022606382,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"the_people_of_jiminny","depth":23,"bounds":{"left":0.5422208,"top":0.58818835,"width":0.045212764,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.58818835,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":20,"bounds":{"left":0.54421544,"top":0.58818835,"width":0.04720745,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":23,"bounds":{"left":0.5422208,"top":0.6408619,"width":0.037898935,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6408619,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54488033,"top":0.6408619,"width":0.03523936,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Mario Georgiev","depth":23,"bounds":{"left":0.5422208,"top":0.6632083,"width":0.034242023,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6632083,"width":0.004654255,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.546875,"top":0.6632083,"width":0.02925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":23,"bounds":{"left":0.5422208,"top":0.6855547,"width":0.026595745,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6855547,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54521275,"top":0.6855547,"width":0.023271276,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":23,"bounds":{"left":0.5422208,"top":0.70790106,"width":0.032247342,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.70790106,"width":0.0039893617,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.5462101,"top":0.70790106,"width":0.027925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"James Graham","depth":23,"bounds":{"left":0.5422208,"top":0.7302474,"width":0.031914894,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.7302474,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54421544,"top":0.7302474,"width":0.029920213,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Stoyan Tanev","depth":23,"bounds":{"left":0.5422208,"top":0.75259376,"width":0.028922873,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.75259376,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54488033,"top":0.75259376,"width":0.026263298,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":23,"bounds":{"left":0.5422208,"top":0.77494013,"width":0.03523936,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.77494013,"width":0.003656915,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.54587764,"top":0.77494013,"width":0.03158245,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":23,"bounds":{"left":0.5422208,"top":0.7972865,"width":0.038231384,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.7972865,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":16,"bounds":{"left":0.54488033,"top":0.7972865,"width":0.03557181,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Petko Kashinski","depth":23,"bounds":{"left":0.5422208,"top":0.8196329,"width":0.034574468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.8196329,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.54521275,"top":0.8196329,"width":0.03158245,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Aneliya Angelova","depth":23,"bounds":{"left":0.5422208,"top":0.84197927,"width":0.03756649,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.84197927,"width":0.0033244682,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.5455452,"top":0.84197927,"width":0.034242023,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Lukas Kovalik","depth":23,"bounds":{"left":0.5422208,"top":0.86432564,"width":0.029587766,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.86432564,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54488033,"top":0.86432564,"width":0.026928192,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"you","depth":23,"bounds":{"left":0.5744681,"top":0.86432564,"width":0.0063164895,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5744681,"top":0.86432564,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":2,"bounds":{"left":0.5767952,"top":0.86432564,"width":0.0056515955,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Jira Cloud","depth":23,"bounds":{"left":0.5422208,"top":0.9169992,"width":0.021941489,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.9169992,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54421544,"top":0.9169992,"width":0.019946808,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Toast","depth":23,"bounds":{"left":0.5422208,"top":0.9393456,"width":0.011635638,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.9393456,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":4,"bounds":{"left":0.54454786,"top":0.9393456,"width":0.00930851,"height":0.014365523}}],"role_description":"text"},{"role":"AXButton","text":"@Toast section","depth":20,"bounds":{"left":0.60206115,"top":0.09976058,"width":0.0066489363,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Toast","depth":20,"bounds":{"left":0.6100399,"top":0.10055866,"width":0.020279255,"height":0.019952115},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast","depth":21,"bounds":{"left":0.61668885,"top":0.10215483,"width":0.012300532,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.61668885,"top":0.10295291,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":4,"bounds":{"left":0.6193484,"top":0.10295291,"width":0.009640957,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"1 message","depth":21,"bounds":{"left":0.92918885,"top":0.10454908,"width":0.020279255,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.92918885,"top":0.10454908,"width":0.0026595744,"height":0.012769354}},{"char_start":1,"char_count":8,"bounds":{"left":0.9318484,"top":0.10454908,"width":0.017287234,"height":0.012769354}}],"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"bounds":{"left":0.953125,"top":0.09976058,"width":0.034574468,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.7882314,"top":0.1452514,"width":0.018949468,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.7882314,"top":0.14604948,"width":0.0023271276,"height":0.012769354}},{"char_start":1,"char_count":8,"bounds":{"left":0.7905585,"top":0.14604948,"width":0.01662234,"height":0.012769354}}],"role_description":"text"},{"role":"AXButton","text":"Review Toast","depth":22,"bounds":{"left":0.6180186,"top":0.17238627,"width":0.029587766,"height":0.017557861},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"bounds":{"left":0.6499335,"top":0.1763767,"width":0.0063164895,"height":0.009577015},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6499335,"top":0.1763767,"width":0.0023271276,"height":0.009577015}},{"char_start":1,"char_count":2,"bounds":{"left":0.65226066,"top":0.1763767,"width":0.0039893617,"height":0.009577015}}],"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"bounds":{"left":0.65724736,"top":0.17398244,"width":0.0026595744,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 2:23:21 PM","depth":22,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.014960106,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"2:23 PM","depth":23,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.014960106,"height":0.011173184},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.0023271276,"height":0.011971269}},{"char_start":1,"char_count":6,"bounds":{"left":0.66223407,"top":0.1763767,"width":0.012965426,"height":0.011971269}}],"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR","depth":23,"bounds":{"left":0.6180186,"top":0.1915403,"width":0.14694148,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6180186,"top":0.1915403,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":63,"bounds":{"left":0.62101066,"top":0.1915403,"width":0.14394946,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by","depth":25,"bounds":{"left":0.62333775,"top":0.21388668,"width":0.053523935,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"stefka-jiminny","depth":25,"bounds":{"left":0.6768617,"top":0.21388668,"width":0.03158245,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"stefka-jiminny","depth":26,"bounds":{"left":0.6768617,"top":0.21388668,"width":0.03158245,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"on","depth":25,"bounds":{"left":0.7084442,"top":0.21388668,"width":0.00831117,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"bounds":{"left":0.71642286,"top":0.21388668,"width":0.03723404,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"bounds":{"left":0.71642286,"top":0.21388668,"width":0.03723404,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"'s PR","depth":25,"bounds":{"left":0.7536569,"top":0.21388668,"width":0.010638298,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":25,"bounds":{"left":0.62333775,"top":0.23144454,"width":0.125,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":26,"bounds":{"left":0.62333775,"top":0.23144454,"width":0.125,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"by","depth":25,"bounds":{"left":0.74833775,"top":0.23144454,"width":0.0066489363,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"bounds":{"left":0.62333775,"top":0.2490024,"width":0.036236703,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"bounds":{"left":0.62333775,"top":0.2490024,"width":0.036236703,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"10 commits・260 files changed","depth":26,"bounds":{"left":0.6286569,"top":0.2697526,"width":0.069148935,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"JIRA:","depth":25,"bounds":{"left":0.62333775,"top":0.2905028,"width":0.012965426,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-18091","depth":25,"bounds":{"left":0.6359708,"top":0.2905028,"width":0.021609042,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-18091","depth":26,"bounds":{"left":0.6359708,"top":0.2905028,"width":0.021609042,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Deployment notes:","depth":25,"bounds":{"left":0.62333775,"top":0.30806065,"width":0.042220745,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"• None","depth":25,"bounds":{"left":0.62333775,"top":0.3320032,"width":0.016289894,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"jiminny/app","depth":24,"bounds":{"left":0.62333775,"top":0.3575419,"width":0.022606382,"height":0.012769354},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"jiminny/app","depth":25,"bounds":{"left":0.62333775,"top":0.3575419,"width":0.022606382,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Added by","depth":24,"bounds":{"left":0.62333775,"top":0.3782921,"width":0.01761968,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Toast for GitHub","depth":24,"bounds":{"left":0.6409575,"top":0.3782921,"width":0.02925532,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast for GitHub","depth":25,"bounds":{"left":0.6409575,"top":0.3782921,"width":0.02925532,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false}]...
|
-773748176853413113
|
4987143428874706403
|
app_switch
|
hybrid
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
rireroxVIewMistorbookmarksProtllesToolsWindowmeleapp.screenolpe.lakylak.xyzScreenpipe - Archive• Goocle GeminiAll docs • AFFiNE) DXP4800PLUS-B5F8Gemini©Screenpipe - ArchiveGShow thinking(*SQLite Web: archive.db( SQLite Web: db.saliteThat is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even thesecondarv ssu-onlv beelink Nas It vou ena uo oulloino iu will keeo vour local ssu lean while• Claudekeepina vour database searchable% Manage extra usage for paicAs for setting up languages for transcription, yes, you can contigure it, but it helps tounderstand how ScreenPipe handles language natively first.G 2 TB in 25 MB/s - Gooale Se- New labHow the Transcription Engine Handles Languageby derault, screenripe uses a multilingual whisper model and sets the language contigurationTO AuTO-DerectWhen a new audio chunk comes in, the model listens to the first few seconds of audio, quessesthe language, and transcribes the rest of that chunk using that assumption.• The Advantage: If vou are watchina a tutorial in Enalish. and then an hour later vou are in aZoom call speakina Bulaarian. ScreenPipe will automatically switch gears without vouhaving to touch the settinas.• The Drawback: Auto-detect can sometimes guess wrong, especially if there is heavybackground noise, it someone starts a sentence with a foreign loanword, or it you arerapidly code-switching between Slovak and English in the same conversation. When itguesses wrong, it might try to torce Slovak words into English spelling, resulting inaloberish.How to Force a Soecific LanquadeIf vou want to ensure maximum accuracy and vou know vou will primarily be recordina in onelanquage for a specific period, vou can explicitly set the lanquage. This also sliahtly speeds upthe processina because the model skips the detection phase.If vou are usina the Deskton Aoo UI:1. Open the ScreenPipe settinas.Ack CeminiScreenpipe (archive.db • 2071.1MBXeaVneVSearchDaily - Platform • in 19 m100% L2Thu 14 May 9:26:0912 / 05 / 2026 17Work Report09 : 45Time Range Filter10 : 36Apply FilterFollov12 Mav 10:15 . iTerm2QuickTime Player File Edit ViewPetko Kashinski)anc15:30 |18:00 |< S0 ll © Support Daily - in 4h 45m O (A)CIOФ.О0Eд0 Bulld21:00100% 143 3• Tue 12 May 10:15:02workPro VGemini is Aland can make mictakes includina about neonle Your nrivacv and GeminSummarize pageB +•* 30sierm? FiretnShotX PhosS Auto-Play Audio: ONLeave"MIC M sys...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38666
|
1439
|
0
|
2026-05-14T06:26:11.349341+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739971349_m2.jpg...
|
Slack
|
Unread Messages - Jiminny Inc - 4 new items - Slac Unread Messages - Jiminny Inc - 4 new items - Slack...
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
Yesterday
Jira Cloud
APP
Today at 6:00:52 PM
6:00 PM
@Stefka Stoyanova
@Stefka Stoyanova
created a Technical Story you are assigned to
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:00:52 PM
6:00
@Stefka Stoyanova
@Stefka Stoyanova
updated the description of a Technical Story you are assigned to
JY-16113 [Laravel 12] Testing of Platform Domain
JY-16113 [Laravel 12] Testing of Platform Domain
Status:
Closed
Type:
Technical Story
Assignee:
Lukas
Kovalik...
|
[{"role":"AXPopUpButton","text [{"role":"AXPopUpButton","text":"Switch workspaces… (Jiminny Inc) Has new messages","depth":14,"bounds":{"left":0.5056516,"top":0.058260176,"width":0.011968086,"height":0.028731046},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"Home","depth":14,"bounds":{"left":0.50299203,"top":0.10055866,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXStaticText","text":"Home","depth":16,"bounds":{"left":0.50664896,"top":0.13806863,"width":0.009973404,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"DMs","depth":14,"bounds":{"left":0.50299203,"top":0.15482841,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"DMs","depth":16,"bounds":{"left":0.50764626,"top":0.19233839,"width":0.007978723,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Activity","depth":14,"bounds":{"left":0.50299203,"top":0.20909816,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Activity","depth":16,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.012965426,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.0026595744,"height":0.011173184}},{"char_start":1,"char_count":7,"bounds":{"left":0.50764626,"top":0.24660814,"width":0.010638298,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Files","depth":14,"bounds":{"left":0.50299203,"top":0.26336792,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Files","depth":16,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0076462766,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5099734,"top":0.3008779,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Later","depth":14,"bounds":{"left":0.50299203,"top":0.31763768,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Later","depth":16,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.008643617,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5093085,"top":0.35514766,"width":0.0066489363,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"More…","depth":14,"bounds":{"left":0.50299203,"top":0.3719074,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"More","depth":16,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.008976064,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.0033244682,"height":0.011173184}},{"char_start":1,"char_count":3,"bounds":{"left":0.5106383,"top":0.4094174,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXStaticText","text":"Unreads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Threads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Huddles","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Drafts & sent","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"1","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Directories","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-x-integration-app","depth":23,"bounds":{"left":0.5422208,"top":0.15562649,"width":0.043882977,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.15562649,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":24,"bounds":{"left":0.54355055,"top":0.15562649,"width":0.05418883,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"platform-inner-team","depth":23,"bounds":{"left":0.5422208,"top":0.17797287,"width":0.04454787,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.17797287,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":18,"bounds":{"left":0.54521275,"top":0.17797287,"width":0.04155585,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"ai-chapter","depth":23,"bounds":{"left":0.5422208,"top":0.23064645,"width":0.022273935,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.23064645,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54488033,"top":0.23064645,"width":0.019614361,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"alerts","depth":23,"bounds":{"left":0.5422208,"top":0.2529928,"width":0.012300532,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.2529928,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":5,"bounds":{"left":0.54488033,"top":0.2529928,"width":0.00930851,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"backend","depth":23,"bounds":{"left":0.5422208,"top":0.2753392,"width":0.018284574,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.2753392,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54521275,"top":0.2753392,"width":0.015292553,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"bugs","depth":23,"bounds":{"left":0.5422208,"top":0.29768556,"width":0.010638298,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.29768556,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":3,"bounds":{"left":0.54521275,"top":0.29768556,"width":0.00731383,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"confusion-clinic","depth":23,"bounds":{"left":0.5422208,"top":0.3200319,"width":0.034574468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.3200319,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54454786,"top":0.3200319,"width":0.032247342,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"curiosity_lab","depth":23,"bounds":{"left":0.5422208,"top":0.3423783,"width":0.027593086,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.3423783,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54454786,"top":0.3423783,"width":0.025265958,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"engineering","depth":23,"bounds":{"left":0.5422208,"top":0.36472467,"width":0.025930852,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.36472467,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":10,"bounds":{"left":0.54488033,"top":0.36472467,"width":0.022938829,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"general","depth":23,"bounds":{"left":0.5422208,"top":0.38707104,"width":0.016289894,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.38707104,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54488033,"top":0.38707104,"width":0.013297873,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"jiminny-bg","depth":23,"bounds":{"left":0.5422208,"top":0.4094174,"width":0.023271276,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.4094174,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54355055,"top":0.4094174,"width":0.021609042,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"platform-tickets","depth":23,"bounds":{"left":0.5422208,"top":0.43176377,"width":0.034906916,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.43176377,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54521275,"top":0.43176377,"width":0.031914894,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"product_launches","depth":23,"bounds":{"left":0.5422208,"top":0.45411015,"width":0.03856383,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.45411015,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54521275,"top":0.45411015,"width":0.03557181,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"random","depth":23,"bounds":{"left":0.5422208,"top":0.4764565,"width":0.016954787,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.4764565,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":5,"bounds":{"left":0.54421544,"top":0.4764565,"width":0.014960106,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"releases","depth":23,"bounds":{"left":0.5422208,"top":0.49880287,"width":0.01761968,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.49880287,"width":0.0016622341,"height":0.014365523}},{"char_start":1,"char_count":7,"bounds":{"left":0.54388297,"top":0.49880287,"width":0.015957447,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"sofia-office","depth":23,"bounds":{"left":0.5422208,"top":0.5211492,"width":0.024601065,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.5211492,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54454786,"top":0.5211492,"width":0.021941489,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"support","depth":23,"bounds":{"left":0.5422208,"top":0.5434956,"width":0.017287234,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.5434956,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54454786,"top":0.5434956,"width":0.01462766,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"thank-yous","depth":23,"bounds":{"left":0.5422208,"top":0.565842,"width":0.024601065,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.565842,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54421544,"top":0.565842,"width":0.022606382,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"the_people_of_jiminny","depth":23,"bounds":{"left":0.5422208,"top":0.58818835,"width":0.045212764,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.58818835,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":20,"bounds":{"left":0.54421544,"top":0.58818835,"width":0.04720745,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":23,"bounds":{"left":0.5422208,"top":0.6408619,"width":0.037898935,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6408619,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54488033,"top":0.6408619,"width":0.03523936,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Mario Georgiev","depth":23,"bounds":{"left":0.5422208,"top":0.6632083,"width":0.034242023,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6632083,"width":0.004654255,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.546875,"top":0.6632083,"width":0.02925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":23,"bounds":{"left":0.5422208,"top":0.6855547,"width":0.026595745,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6855547,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54521275,"top":0.6855547,"width":0.023271276,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":23,"bounds":{"left":0.5422208,"top":0.70790106,"width":0.032247342,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.70790106,"width":0.0039893617,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.5462101,"top":0.70790106,"width":0.027925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"James Graham","depth":23,"bounds":{"left":0.5422208,"top":0.7302474,"width":0.031914894,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.7302474,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54421544,"top":0.7302474,"width":0.029920213,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Stoyan Tanev","depth":23,"bounds":{"left":0.5422208,"top":0.75259376,"width":0.028922873,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.75259376,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54488033,"top":0.75259376,"width":0.026263298,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":23,"bounds":{"left":0.5422208,"top":0.77494013,"width":0.03523936,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.77494013,"width":0.003656915,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.54587764,"top":0.77494013,"width":0.03158245,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":23,"bounds":{"left":0.5422208,"top":0.7972865,"width":0.038231384,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.7972865,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":16,"bounds":{"left":0.54488033,"top":0.7972865,"width":0.03557181,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Petko Kashinski","depth":23,"bounds":{"left":0.5422208,"top":0.8196329,"width":0.034574468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.8196329,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.54521275,"top":0.8196329,"width":0.03158245,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Aneliya Angelova","depth":23,"bounds":{"left":0.5422208,"top":0.84197927,"width":0.03756649,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.84197927,"width":0.0033244682,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.5455452,"top":0.84197927,"width":0.034242023,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Lukas Kovalik","depth":23,"bounds":{"left":0.5422208,"top":0.86432564,"width":0.029587766,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.86432564,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54488033,"top":0.86432564,"width":0.026928192,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"you","depth":23,"bounds":{"left":0.5744681,"top":0.86432564,"width":0.0063164895,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5744681,"top":0.86432564,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":2,"bounds":{"left":0.5767952,"top":0.86432564,"width":0.0056515955,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Jira Cloud","depth":23,"bounds":{"left":0.5422208,"top":0.9169992,"width":0.021941489,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.9169992,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54421544,"top":0.9169992,"width":0.019946808,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Toast","depth":23,"bounds":{"left":0.5422208,"top":0.9393456,"width":0.011635638,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.9393456,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":4,"bounds":{"left":0.54454786,"top":0.9393456,"width":0.00930851,"height":0.014365523}}],"role_description":"text"},{"role":"AXButton","text":"@Toast section","depth":20,"bounds":{"left":0.60206115,"top":0.09976058,"width":0.0066489363,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Toast","depth":20,"bounds":{"left":0.6100399,"top":0.10055866,"width":0.020279255,"height":0.019952115},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast","depth":21,"bounds":{"left":0.61668885,"top":0.10215483,"width":0.012300532,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.61668885,"top":0.10295291,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":4,"bounds":{"left":0.6193484,"top":0.10295291,"width":0.009640957,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"1 message","depth":21,"bounds":{"left":0.92918885,"top":0.10454908,"width":0.020279255,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.92918885,"top":0.10454908,"width":0.0026595744,"height":0.012769354}},{"char_start":1,"char_count":8,"bounds":{"left":0.9318484,"top":0.10454908,"width":0.017287234,"height":0.012769354}}],"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"bounds":{"left":0.953125,"top":0.09976058,"width":0.034574468,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.7882314,"top":0.1452514,"width":0.018949468,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.7882314,"top":0.14604948,"width":0.0023271276,"height":0.012769354}},{"char_start":1,"char_count":8,"bounds":{"left":0.7905585,"top":0.14604948,"width":0.01662234,"height":0.012769354}}],"role_description":"text"},{"role":"AXButton","text":"Review Toast","depth":22,"bounds":{"left":0.6180186,"top":0.17238627,"width":0.029587766,"height":0.017557861},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"bounds":{"left":0.6499335,"top":0.1763767,"width":0.0063164895,"height":0.009577015},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6499335,"top":0.1763767,"width":0.0023271276,"height":0.009577015}},{"char_start":1,"char_count":2,"bounds":{"left":0.65226066,"top":0.1763767,"width":0.0039893617,"height":0.009577015}}],"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"bounds":{"left":0.65724736,"top":0.17398244,"width":0.0026595744,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 2:23:21 PM","depth":22,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.014960106,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"2:23 PM","depth":23,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.014960106,"height":0.011173184},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.0023271276,"height":0.011971269}},{"char_start":1,"char_count":6,"bounds":{"left":0.66223407,"top":0.1763767,"width":0.012965426,"height":0.011971269}}],"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR","depth":23,"bounds":{"left":0.6180186,"top":0.1915403,"width":0.14694148,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6180186,"top":0.1915403,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":63,"bounds":{"left":0.62101066,"top":0.1915403,"width":0.14394946,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by","depth":25,"bounds":{"left":0.62333775,"top":0.21388668,"width":0.053523935,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"stefka-jiminny","depth":25,"bounds":{"left":0.6768617,"top":0.21388668,"width":0.03158245,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"stefka-jiminny","depth":26,"bounds":{"left":0.6768617,"top":0.21388668,"width":0.03158245,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"on","depth":25,"bounds":{"left":0.7084442,"top":0.21388668,"width":0.00831117,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"bounds":{"left":0.71642286,"top":0.21388668,"width":0.03723404,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"bounds":{"left":0.71642286,"top":0.21388668,"width":0.03723404,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"'s PR","depth":25,"bounds":{"left":0.7536569,"top":0.21388668,"width":0.010638298,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":25,"bounds":{"left":0.62333775,"top":0.23144454,"width":0.125,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":26,"bounds":{"left":0.62333775,"top":0.23144454,"width":0.125,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"by","depth":25,"bounds":{"left":0.74833775,"top":0.23144454,"width":0.0066489363,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"bounds":{"left":0.62333775,"top":0.2490024,"width":0.036236703,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"bounds":{"left":0.62333775,"top":0.2490024,"width":0.036236703,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"10 commits・260 files changed","depth":26,"bounds":{"left":0.6286569,"top":0.2697526,"width":0.069148935,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"JIRA:","depth":25,"bounds":{"left":0.62333775,"top":0.2905028,"width":0.012965426,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-18091","depth":25,"bounds":{"left":0.6359708,"top":0.2905028,"width":0.021609042,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-18091","depth":26,"bounds":{"left":0.6359708,"top":0.2905028,"width":0.021609042,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Deployment notes:","depth":25,"bounds":{"left":0.62333775,"top":0.30806065,"width":0.042220745,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"• None","depth":25,"bounds":{"left":0.62333775,"top":0.3320032,"width":0.016289894,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"jiminny/app","depth":24,"bounds":{"left":0.62333775,"top":0.3575419,"width":0.022606382,"height":0.012769354},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"jiminny/app","depth":25,"bounds":{"left":0.62333775,"top":0.3575419,"width":0.022606382,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Added by","depth":24,"bounds":{"left":0.62333775,"top":0.3782921,"width":0.01761968,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Toast for GitHub","depth":24,"bounds":{"left":0.6409575,"top":0.3782921,"width":0.02925532,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast for GitHub","depth":25,"bounds":{"left":0.6409575,"top":0.3782921,"width":0.02925532,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"@Jira Cloud section","depth":20,"bounds":{"left":0.60206115,"top":0.42138866,"width":0.0066489363,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Jira Cloud","depth":20,"bounds":{"left":0.6100399,"top":0.42218676,"width":0.03025266,"height":0.019952115},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Jira Cloud","depth":21,"bounds":{"left":0.61668885,"top":0.4237829,"width":0.022273935,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"3 messages","depth":21,"bounds":{"left":0.89793885,"top":0.42617717,"width":0.021941489,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Press","depth":20,"bounds":{"left":0.9225399,"top":0.4253791,"width":0.011303191,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Esc","depth":20,"bounds":{"left":0.93650264,"top":0.4253791,"width":0.0063164895,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"to","depth":20,"bounds":{"left":0.94547874,"top":0.4253791,"width":0.0066489363,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"bounds":{"left":0.953125,"top":0.42138866,"width":0.034574468,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.7882314,"top":0.4668795,"width":0.018949468,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Jira Cloud","depth":22,"bounds":{"left":0.6180186,"top":0.49401435,"width":0.022273935,"height":0.017557861},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"bounds":{"left":0.64261967,"top":0.4980048,"width":0.0066489363,"height":0.009577015},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"bounds":{"left":0.6499335,"top":0.49561054,"width":0.0026595744,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 6:00:52 PM","depth":22,"bounds":{"left":0.6525931,"top":0.4980048,"width":0.015292553,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:00 PM","depth":23,"bounds":{"left":0.6525931,"top":0.4980048,"width":0.015292553,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"bounds":{"left":0.62666225,"top":0.5131684,"width":0.04255319,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"bounds":{"left":0.62666225,"top":0.5131684,"width":0.04255319,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"created a Technical Story you are assigned to","depth":24,"bounds":{"left":0.66921544,"top":0.5131684,"width":0.10006649,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":24,"bounds":{"left":0.6180186,"top":0.53072625,"width":0.11037234,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":true,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":25,"bounds":{"left":0.6180186,"top":0.53072625,"width":0.11037234,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"bounds":{"left":0.6180186,"top":0.55626494,"width":0.013962766,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Backlog","depth":23,"bounds":{"left":0.6319814,"top":0.55626494,"width":0.015292553,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"bounds":{"left":0.6525931,"top":0.55626494,"width":0.011303191,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"bounds":{"left":0.66389626,"top":0.55626494,"width":0.02925532,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"bounds":{"left":0.70611703,"top":0.55626494,"width":0.019281914,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas","depth":23,"bounds":{"left":0.72539896,"top":0.55626494,"width":0.010970744,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"bounds":{"left":0.73636967,"top":0.55626494,"width":0.0009973404,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Kovalik","depth":23,"bounds":{"left":0.73736703,"top":0.55626494,"width":0.014295213,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Priority:","depth":23,"bounds":{"left":0.76462764,"top":0.55626494,"width":0.01662234,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Medium","depth":23,"bounds":{"left":0.7809175,"top":0.55626494,"width":0.015957447,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Transition","depth":23,"bounds":{"left":0.6180186,"top":0.5826017,"width":0.025265958,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Transition","depth":25,"bounds":{"left":0.62101066,"top":0.5865922,"width":0.019281914,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXComboBox","text":"More actions...","depth":24,"bounds":{"left":0.6456117,"top":0.5826017,"width":0.06349734,"height":0.022346368},"on_screen":true,"placeholder":"More actions...","role_description":"combo box","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"bounds":{"left":0.90625,"top":0.481245,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"bounds":{"left":0.9168883,"top":0.481245,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"bounds":{"left":0.9275266,"top":0.481245,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"bounds":{"left":0.9381649,"top":0.481245,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"bounds":{"left":0.9488032,"top":0.481245,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"bounds":{"left":0.9594415,"top":0.481245,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"bounds":{"left":0.9700798,"top":0.481245,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"bounds":{"left":0.9807181,"top":0.481245,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXLink","text":"Today at 6:00:52 PM","depth":23,"bounds":{"left":0.60738033,"top":0.61851555,"width":0.007978723,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:00","depth":24,"bounds":{"left":0.60738033,"top":0.61851555,"width":0.007978723,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"bounds":{"left":0.62666225,"top":0.61532325,"width":0.043882977,"height":0.015961692},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"bounds":{"left":0.62732714,"top":0.6161213,"width":0.04255319,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"updated the description of a Technical Story you are assigned to","depth":24,"bounds":{"left":0.6705452,"top":0.6161213,"width":0.1419548,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-16113 [Laravel 12] Testing of Platform Domain","depth":24,"bounds":{"left":0.6180186,"top":0.63367915,"width":0.11037234,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-16113 [Laravel 12] Testing of Platform Domain","depth":25,"bounds":{"left":0.6180186,"top":0.63367915,"width":0.11037234,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"bounds":{"left":0.6180186,"top":0.6592179,"width":0.013962766,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Closed","depth":23,"bounds":{"left":0.6319814,"top":0.6592179,"width":0.013297873,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"bounds":{"left":0.65026593,"top":0.6592179,"width":0.011635638,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"bounds":{"left":0.6615692,"top":0.6592179,"width":0.02925532,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"bounds":{"left":0.70412236,"top":0.6592179,"width":0.019281914,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas","depth":23,"bounds":{"left":0.7230718,"top":0.6592179,"width":0.011303191,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"bounds":{"left":0.7340425,"top":0.6592179,"width":0.0013297872,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Kovalik","depth":23,"bounds":{"left":0.7350399,"top":0.6592179,"width":0.014295213,"height":0.012769354},"on_screen":true,"role_description":"text"}]...
|
3401079881616927616
|
-3734094496694518208
|
visual_change
|
hybrid
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
Yesterday
Jira Cloud
APP
Today at 6:00:52 PM
6:00 PM
@Stefka Stoyanova
@Stefka Stoyanova
created a Technical Story you are assigned to
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:00:52 PM
6:00
@Stefka Stoyanova
@Stefka Stoyanova
updated the description of a Technical Story you are assigned to
JY-16113 [Laravel 12] Testing of Platform Domain
JY-16113 [Laravel 12] Testing of Platform Domain
Status:
Closed
Type:
Technical Story
Assignee:
Lukas
Kovalik
SlackVIewmistoryWindowHelpdop.screenolpe.lakylak.xyzScreenpipe - Archive• Goocle GeminiAll docs • AFFiNEGemini• DXP4800PLUS-B5F8® Screenpipe - Archive@ SQLite Web: archive.dbGShow thinkingv( SQLite Web: db.salite→ Claude% Manage extra usage for paicThat is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even thesecondarv ssu-onlv beelink Nas It vou ena uo oulloino iu will keeo vour local ssu lean whilekeeping your database searchable.As for setting up languages for transcription, yes, you can configure it, but it helps tounderstand how ScreenPipe handles language natively first.G 2 TB in 25 MB/s - Gooale Se- New TabHow the Transcription Engine Handles Languageby derault, screenripe uses a multilingual whisper model and sets the language contigurationTO AuTO-DerectWhen a new audio chunk comes in, the model listens to the first few seconds of audio, guessesthe language, and transcribes the rest of that chunk using that assumption.• The Advantage: If you are watching a tutorial in English, and then an hour later you are in aZoom call speaking Bulgarian, ScreenPipe will automatically switch gears without youhaving to touch the settings.• The Drawback: Auto-detect can sometimes guess wrong, especially if there is heavybackground noise, if someone starts a sentence with a foreign loanword, or if you arerapidly code-switching between Slovak and English in the same conversation. When itguesses wrong, it might try to torce Slovak words into English spelling, resulting incloberishHow to Force a Specific LanguageIf you want to ensure maximum accuracy and you know you will primarily be recording in onelanguage for a specific period, you can explicitly set the language. This also slightly speeds upthe processing because the model skips the detection phase.If you are using the Desktop App UI:1. Open the ScreenPipe settings.Ask GeminiPro VGemini is Al and can make mistakes, including about people. Your privacy and GeminiSummarize pageScreenpipe (archive.db • 2071.1MB)XeaVneVSearchWork Repors09: 45Activity12 May 10:15 • iTerm2Jiminny... ~h External connections# StarredÔ jiminny-x-integrati…..& platform-inner-team@ Channels# ai-chapter# alerts# backend# bugs# confusion-clinic# curiosity_lab# engineering# general#jiminny-bg# platform-tickets# product_launchesirandom# releasesi sona-otnce# support# thank-vous# the_people_of jimi...•? Direct messagesFf. Stefka Stoyanova88. Mario GeorgievVasll VasilevC. Nikolay IvanovSn James Graham2. Stoyan TanevP. Galya Dimitrovaf. Steliyan GeorgievPetko Kashinskif. Aneliya Angelovae. Lukas Kovalik y...# AppsG Jira CloudB ToastB +•iTerm2 M FirefQ Describe what you are looking forUnreads © All conversations Sorted by recommended order ~• 0 loastReview Toast APP 2:23 PMPR review requested by@stefka-jiminny on @nikolaybiaivanov's PRPR review requested by stefka-jiminny on nikolaybiaivanov's PR#1z058JY-18071 Update composer to support pho 8.5 bvnikolavbiaivanov| 10 commits • 260 files changedJIRA: JY-18091Deployment notes:•NoneAdded oy loasttor oltniuo• © Jlira [URL_WITH_CREDENTIALS] Stoyanova assigned a Technical Story from you — UnassignedJY-20897 [Laravel 13] Testing of Platform DomainStatus: BacklogType: Technical Story® Assignee: UnassignedT Priority: MediumDally - Platorm• In 15m100% 52Inu 14 May 9-20.17Mark as Read3 messages Press Esc toMark as ReadMark All Messages Read...
|
38664
|
NULL
|
NULL
|
NULL
|
|
38665
|
1437
|
0
|
2026-05-14T06:26:11.355884+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739971355_m1.jpg...
|
Slack
|
Unread Messages - Jiminny Inc - 4 new items - Slac Unread Messages - Jiminny Inc - 4 new items - Slack...
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
Yesterday
Jira Cloud
APP
Today at 6:00:52 PM
6:00 PM
@Stefka Stoyanova
@Stefka Stoyanova
created a Technical Story you are assigned to
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:00:52 PM
6:00
@Stefka Stoyanova
@Stefka Stoyanova
updated the description of a Technical Story you are assigned to
JY-16113 [Laravel 12] Testing of Platform Domain
JY-16113 [Laravel 12] Testing of Platform Domain
Status:
Closed
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Comment
Comment
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:01:28 PM
6:01
@Stefka Stoyanova
@Stefka Stoyanova
assigned a Technical Story from you ⟶ Unassigned
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Unassigned
Priority:
Medium
Transition
Transition
More actions......
|
[{"role":"AXPopUpButton","text [{"role":"AXPopUpButton","text":"Switch workspaces… (Jiminny Inc) Has new messages","depth":14,"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"Home","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXStaticText","text":"Home","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"DMs","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"DMs","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Activity","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Activity","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Files","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Files","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Later","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Later","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"More…","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"More","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Unreads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Threads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Huddles","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Drafts & sent","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"1","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Directories","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-x-integration-app","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"platform-inner-team","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ai-chapter","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"alerts","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"backend","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"bugs","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"confusion-clinic","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"curiosity_lab","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"engineering","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"general","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-bg","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"platform-tickets","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"product_launches","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"random","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"releases","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"sofia-office","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"support","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"thank-yous","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"the_people_of_jiminny","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Mario Georgiev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"James Graham","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Stoyan Tanev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Petko Kashinski","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Aneliya Angelova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas Kovalik","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"you","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Jira Cloud","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Toast","depth":23,"bounds":{"left":0.56805557,"top":0.0,"width":0.024305556,"height":0.02},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"@Toast section","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Toast","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"1 message","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Review Toast","depth":22,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 2:23:21 PM","depth":22,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"2:23 PM","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"stefka-jiminny","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"stefka-jiminny","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"on","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"'s PR","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"by","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"10 commits・260 files changed","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"JIRA:","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-18091","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-18091","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Deployment notes:","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"• None","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"jiminny/app","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"jiminny/app","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Added by","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Toast for GitHub","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast for GitHub","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"@Jira Cloud section","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Jira Cloud","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Jira Cloud","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"3 messages","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Press","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Esc","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"to","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Jira Cloud","depth":22,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 6:00:52 PM","depth":22,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:00 PM","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"created a Technical Story you are assigned to","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":true,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Backlog","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Kovalik","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Priority:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Medium","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Transition","depth":23,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Transition","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXComboBox","text":"More actions...","depth":24,"on_screen":true,"placeholder":"More actions...","role_description":"combo box","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXLink","text":"Today at 6:00:52 PM","depth":23,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:00","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"updated the description of a Technical Story you are assigned to","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-16113 [Laravel 12] Testing of Platform Domain","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-16113 [Laravel 12] Testing of Platform Domain","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Closed","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Kovalik","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Priority:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Medium","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Comment","depth":23,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Comment","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Transition","depth":23,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Transition","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXComboBox","text":"More actions...","depth":24,"on_screen":true,"placeholder":"More actions...","role_description":"combo box","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXLink","text":"Today at 6:01:28 PM","depth":23,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:01","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"assigned a Technical Story from you ⟶ Unassigned","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Backlog","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Unassigned","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Priority:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Medium","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Transition","depth":23,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Transition","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXComboBox","text":"More actions...","depth":24,"on_screen":true,"placeholder":"More actions...","role_description":"combo box","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false}]...
|
-1990092639018379044
|
-3734093397250490816
|
visual_change
|
hybrid
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
Yesterday
Jira Cloud
APP
Today at 6:00:52 PM
6:00 PM
@Stefka Stoyanova
@Stefka Stoyanova
created a Technical Story you are assigned to
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:00:52 PM
6:00
@Stefka Stoyanova
@Stefka Stoyanova
updated the description of a Technical Story you are assigned to
JY-16113 [Laravel 12] Testing of Platform Domain
JY-16113 [Laravel 12] Testing of Platform Domain
Status:
Closed
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Comment
Comment
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:01:28 PM
6:01
@Stefka Stoyanova
@Stefka Stoyanova
assigned a Technical Story from you ⟶ Unassigned
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Unassigned
Priority:
Medium
Transition
Transition
More actions...
iTerm2ShellEditViewSessionScriptsProfilesWindowHelp(ahlDaily - Platform • in 19 m100% <47screenpipe"-zsh8•Thu 14 May 9:26:10181ec2-user@ip-10-20-31-14...₴7DOCKERO 81whisper_model_load:n_melswhisper_model_load: ftypeDEV (-zsh)= 80= 1• ₴2APP (-zsh)83screenpipe*885ec2-user@ip-10-30-129-...₴6whisper_model_load:qntvrwhisper_model._load: type= 1 (tiny)whisper_model_load:adding1608extra tokenswhisper_model_load: n_langs99whisper_model_load:Metal totalsize =77.11 MBwhisper_model_load: modelsize77.11 MB2026-05-14T09:25:08.714171ZINFOscreenpipe_audio::transcription::engine: whisper model loaded successfullywhisper_backend_init_gpu: device 0: Metal (type:1)whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu:using Metal backendggml_metal_init: allocatingggml_metal_init:found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrency= trueggml_metal_init: use graph optimize= truewhisper_backend_init: using BLAS backendwhisper_init_state: kv selfsize3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize2.36 MBwhisper_init_state: compute buffer (conv)=14.17 MBwhisper_init_state:computebuffer (encode)65.96 MBwhisper_init_state:computebuffer(cross)8.50 MBwhisper_init_state:computebuffer(decode)96.83MB2026-05-14T09:25:08.721297ZINFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)2026-05-14T09:25:08.7275752INFOscreenpipe_audio::audio_manager::manager: seeded 21 speakers (named + unnamed) from DB into embedding manager2026-05-14T09:25:08.727664ZINFOscreenpipe_audio::audio_manager::manager: audio manager started2026-05-14T09:25:08.727731ZINFOscreenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events2026-05-14709:25:09.2389252INFOscreenpipe.audio: :device::device_manager: starting recording for device: System Audio (output)2026-05-14T09:25:09.325492ZINFOscreenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)2026-05-14T09:25:09.326604ZINFOscreenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)2026-05-14709:25:09.3266572INFOscreenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)2026-05-14T09:25:16.929049ZWARNscreenpipe_ally::tree::macos_lines: lines: AXUIElementCopyParameterizedAttributeValue(AXLineForIndex) failed status=os::Status& raw: -25212, fcc...."help:"https://www.osstatus.com?search=-25212"}- first failure (further failuressuppressed); search highlights will fall back to paragraph bbox on this app2026-05-14T09:25:42.118426ZINFO screenpipe_audio::transcription::handle_new_transcript: device System Audio (output) skipping duplicate transcript (entire content overlaps withprevious)2026-05-14T09:26:02.676206ZROM\nframes\nWHERE\nWARNsqlx::query:summary="SELECT id, snapshot_path, device_name,db.statement="\n\nSELECT\n id,\nsnapshot_path, \ndevice_name, \ntimestamp\nFsnapshot_path IS NOTNULL\nANDtimestamp < ?1\nORDER BYn device_name, \ntimestamp ASC\nLIMIT\n5000\n"rows_affected=0 rows_returned=56 elapsed=4.13192087552026-05-14T09:26:02.676359Z2026-05-14T09:26:04.733866Z2026-05-14109:26:06.9326332INFOscreenpipe_engine::snapshot_compaction: snapshot compaction: found 56 eligible framesINFOscreenpipe_engine::snapshot_compaction: snapshot compaction: 29 frames, 4.0MB → 1.9MB (2.1x),INFOscreenpipesnapshot_compaction: snapshot compaction: 25 frames, 4.3MB → 2.2MB (2.0x), 25 JPEGs deleted1u (.0), 2 ve std...
|
38663
|
NULL
|
NULL
|
NULL
|
|
38667
|
1437
|
1
|
2026-05-14T06:26:13.490122+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739973490_m1.jpg...
|
Slack
|
Unread Messages - Jiminny Inc - 4 new items - Slac Unread Messages - Jiminny Inc - 4 new items - Slack...
|
1
|
NULL
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
Yesterday
Jira Cloud
APP
Today at 6:00:52 PM
6:00 PM
@Stefka Stoyanova
@Stefka Stoyanova
created a Technical Story you are assigned to
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:00:52 PM
6:00
@Stefka Stoyanova
@Stefka Stoyanova
updated the description of a Technical Story you are assigned to
JY-16113 [Laravel 12] Testing of Platform Domain
JY-16113 [Laravel 12] Testing of Platform Domain
Status:
Closed
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Comment
Comment
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:01:28 PM
6:01
@Stefka Stoyanova
@Stefka Stoyanova
assigned a Technical Story from you ⟶ Unassigned
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Unassigned
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Processing uploaded file… complete! Message ready to be sent.
Channel...
|
[{"role":"AXPopUpButton","text [{"role":"AXPopUpButton","text":"Switch workspaces… (Jiminny Inc) Has new messages","depth":14,"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"Home","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXStaticText","text":"Home","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"DMs","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"DMs","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Activity","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":true,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Activity","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Files","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Files","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Later","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Later","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"More…","depth":14,"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"More","depth":16,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Unreads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Threads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Huddles","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Drafts & sent","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"1","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Directories","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-x-integration-app","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"platform-inner-team","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ai-chapter","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"alerts","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"backend","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"bugs","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"confusion-clinic","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"curiosity_lab","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"engineering","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"general","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-bg","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"platform-tickets","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"product_launches","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"random","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"releases","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"sofia-office","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"support","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"thank-yous","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"the_people_of_jiminny","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Mario Georgiev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"James Graham","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Stoyan Tanev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Petko Kashinski","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Aneliya Angelova","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas Kovalik","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"you","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Jira Cloud","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Toast","depth":23,"bounds":{"left":0.56805557,"top":0.0,"width":0.024305556,"height":0.02},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"@Toast section","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Toast","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"1 message","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Review Toast","depth":22,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 2:23:21 PM","depth":22,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"2:23 PM","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"stefka-jiminny","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"stefka-jiminny","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"on","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"'s PR","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"by","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"10 commits・260 files changed","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"JIRA:","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-18091","depth":25,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-18091","depth":26,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Deployment notes:","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"• None","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"jiminny/app","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"jiminny/app","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Added by","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Toast for GitHub","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast for GitHub","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"@Jira Cloud section","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Jira Cloud","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Jira Cloud","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"3 messages","depth":21,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Press","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Esc","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"to","depth":20,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Jira Cloud","depth":22,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 6:00:52 PM","depth":22,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:00 PM","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"created a Technical Story you are assigned to","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Backlog","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Kovalik","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Priority:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Medium","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Transition","depth":23,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Transition","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXComboBox","text":"More actions...","depth":24,"on_screen":true,"placeholder":"More actions...","role_description":"combo box","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXLink","text":"Today at 6:00:52 PM","depth":23,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:00","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"updated the description of a Technical Story you are assigned to","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-16113 [Laravel 12] Testing of Platform Domain","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-16113 [Laravel 12] Testing of Platform Domain","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Closed","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Kovalik","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Priority:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Medium","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Comment","depth":23,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Comment","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Transition","depth":23,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Transition","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXComboBox","text":"More actions...","depth":24,"on_screen":true,"placeholder":"More actions...","role_description":"combo box","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXLink","text":"Today at 6:01:28 PM","depth":23,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:01","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"assigned a Technical Story from you ⟶ Unassigned","depth":24,"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":24,"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Backlog","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Unassigned","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Priority:","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Medium","depth":23,"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Transition","depth":23,"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Transition","depth":25,"on_screen":true,"role_description":"text"},{"role":"AXComboBox","text":"More actions...","depth":24,"on_screen":true,"placeholder":"More actions...","role_description":"combo box","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Processing uploaded file… complete! Message ready to be sent.","depth":11,"bounds":{"left":0.4798611,"top":0.0,"width":0.047916666,"height":0.0011111111},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Channel","depth":11,"bounds":{"left":0.4798611,"top":0.0,"width":0.036805555,"height":0.0011111111},"on_screen":true,"role_description":"text"}]...
|
5579333763460978331
|
-1428250388070355392
|
click
|
hybrid
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
Yesterday
Jira Cloud
APP
Today at 6:00:52 PM
6:00 PM
@Stefka Stoyanova
@Stefka Stoyanova
created a Technical Story you are assigned to
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:00:52 PM
6:00
@Stefka Stoyanova
@Stefka Stoyanova
updated the description of a Technical Story you are assigned to
JY-16113 [Laravel 12] Testing of Platform Domain
JY-16113 [Laravel 12] Testing of Platform Domain
Status:
Closed
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Comment
Comment
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:01:28 PM
6:01
@Stefka Stoyanova
@Stefka Stoyanova
assigned a Technical Story from you ⟶ Unassigned
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Unassigned
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Processing uploaded file… complete! Message ready to be sent.
Channel
iTerm2ShellEditViewSessionScriptsProfilesWindowHelp(ahlDaily - Platform • in 19 m100% <47screenpipe"-zsh8•Thu 14 May 9:26:12181ec2-user@ip-10-20-31-14...₴7DOCKERO 81whisper_model_load:n_melswhisper_model_load: ftypeDEV (-zsh)= 80= 1• ₴2APP (-zsh)83screenpipe*885ec2-user@ip-10-30-129-...₴6whisper_model_load:qntvrwhisper_model._load: type= 1 (tiny)whisper_model_load:adding1608extra tokenswhisper_model_load: n_langs99whisper_model_load:Metal totalsize =77.11 MBwhisper_model_load: modelsize77.11 MB2026-05-14T09:25:08.714171ZINFOscreenpipe_audio::transcription::engine: whisper model loaded successfullywhisper_backend_init_gpu: device 0: Metal (type:1)whisper_backend_init_gpu: found GPU device 0: Metal (type: 1, cnt: 0)whisper_backend_init_gpu:using Metal backendggml_metal_init: allocatingggml_metal_init:found device: Apple M1ggml_metal_init:picking default device: Apple M1ggml_metal_init:use fusion= trueggml_metal_init:use concurrency= trueggml_metal_init: use graph optimize= truewhisper_backend_init: using BLAS backendwhisper_init_state: kv selfsize3.15 MBwhisper_init_state: kv cross size =9.44 MBwhisper_init_state: kv padsize2.36 MBwhisper_init_state: compute buffer (conv)=14.17 MBwhisper_init_state:computebuffer (encode)65.96 MBwhisper_init_state:computebuffer(cross)8.50 MBwhisper_init_state:computebuffer(decode)96.83MB2026-05-14T09:25:08.721297ZINFO screenpipe_audio::audio_manager::manager: transcription session created (will be reused across segments)2026-05-14T09:25:08.727575ZINFOscreenpipe_audio::audio_manager::manager: seeded 21 speakers (named + unnamed) from DB into embedding manager2026-05-14T09:25:08.727664ZINFOscreenpipe_audio::audio_manager::manager: audio manager started2026-05-14T09:25:08.727731ZINFOscreenpipe_audio::audio_manager::manager: calendar-assisted speaker diarization: listening for meeting events2026-05-14T09:25:09.2389252INFOscreenpipe.audio: :device::device_manager: starting recording for device: System Audio (output)2026-05-14T09:25:09.325492ZINFOscreenpipe_audio::device::device_manager: starting recording for device: soundcore AeroClip (input)2026-05-14T09:25:09.326604ZINFOscreenpipe_audio::core::run_record_and_transcribe: starting continuous recording for soundcore AeroClip (input) (bluetooth / 30s segments)2026-05-14709:25:09.3266572INFOscreenpipe_audio::core::run_record_and_transcribe: starting continuous recording for System Audio (output) (unknown / 30s segments)2026-05-14T09:25:16.929049ZWARNscreenpipe_ally::tree::macos_lines: lines: AXUIElementCopyParameterizedAttributeValue(AXLineForIndex) failed status=os::Status& raw: -25212, fcc...."help:"https://www.osstatus.com?search=-25212"}- first failure (further failuressuppressed); search highlights will fall back to paragraph bbox on this app2026-05-14T09:25:42.118426ZINFO screenpipe_audio::transcription::handle_new_transcript: device System Audio (output) skipping duplicate transcript (entire content overlaps withprevious)2026-05-14T09:26:02.676206ZROM\nframes\nWHERE\nWARNsqlx::query:summary="SELECT id, snapshot_path, device_name,db.statement="\n\nSELECT\n id,\nsnapshot_path, \ndevice_name, \ntimestamp\nFsnapshot_path IS NOTNULL\nANDtimestamp < ?1\nORDER BYn device_name, \ntimestamp ASC\nLIMIT\n5000\n"rows_affected=0 rows_returned=56 elapsed=4.13192087552026-05-14T09:26:02.676359Z2026-05-14T09:26:04.733866Z2026-05-14109:26:06.9326332INFOscreenpipe_engine::snapshot_compaction: snapshot compaction: found 56 eligible framesINFOscreenpipe_engine::snapshot_compaction: snapshot compaction: 29 frames, 4.0MB → 1.9MB (2.1x),INFOscreenpipesnapshot_compaction: snapshot compaction: 25 frames, 4.3MB → 2.2MB (2.0x), 25 JPEGs deleted1u (.0), 2 ve std...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38668
|
1439
|
1
|
2026-05-14T06:26:13.523604+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739973523_m2.jpg...
|
Slack
|
Unread Messages - Jiminny Inc - 4 new items - Slac Unread Messages - Jiminny Inc - 4 new items - Slack...
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
Yesterday
Jira Cloud
APP
Today at 6:00:52 PM
6:00 PM
@Stefka Stoyanova
@Stefka Stoyanova
created a Technical Story you are assigned to
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:00:52 PM
6:00
@Stefka Stoyanova
@Stefka Stoyanova
updated the description of a Technical Story you are assigned to
JY-16113 [Laravel 12] Testing of Platform Domain
Processing uploaded file… complete! Message ready to be sent.
Channel...
|
[{"role":"AXPopUpButton","text [{"role":"AXPopUpButton","text":"Switch workspaces… (Jiminny Inc) Has new messages","depth":14,"bounds":{"left":0.5056516,"top":0.058260176,"width":0.011968086,"height":0.028731046},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"Home","depth":14,"bounds":{"left":0.50299203,"top":0.10055866,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXStaticText","text":"Home","depth":16,"bounds":{"left":0.50664896,"top":0.13806863,"width":0.009973404,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"DMs","depth":14,"bounds":{"left":0.50299203,"top":0.15482841,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"DMs","depth":16,"bounds":{"left":0.50764626,"top":0.19233839,"width":0.007978723,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Activity","depth":14,"bounds":{"left":0.50299203,"top":0.20909816,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":true,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Activity","depth":16,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.012965426,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.0026595744,"height":0.011173184}},{"char_start":1,"char_count":7,"bounds":{"left":0.50764626,"top":0.24660814,"width":0.010638298,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Files","depth":14,"bounds":{"left":0.50299203,"top":0.26336792,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Files","depth":16,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0076462766,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5099734,"top":0.3008779,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Later","depth":14,"bounds":{"left":0.50299203,"top":0.31763768,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Later","depth":16,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.008643617,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5093085,"top":0.35514766,"width":0.0066489363,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"More…","depth":14,"bounds":{"left":0.50299203,"top":0.3719074,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"More","depth":16,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.008976064,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.0033244682,"height":0.011173184}},{"char_start":1,"char_count":3,"bounds":{"left":0.5106383,"top":0.4094174,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXStaticText","text":"Unreads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Threads","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Huddles","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Drafts & sent","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"1","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"Directories","depth":21,"on_screen":false,"role_description":"text"},{"role":"AXStaticText","text":"jiminny-x-integration-app","depth":23,"bounds":{"left":0.5422208,"top":0.15562649,"width":0.043882977,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.15562649,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":24,"bounds":{"left":0.54355055,"top":0.15562649,"width":0.05418883,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"platform-inner-team","depth":23,"bounds":{"left":0.5422208,"top":0.17797287,"width":0.04454787,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.17797287,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":18,"bounds":{"left":0.54521275,"top":0.17797287,"width":0.04155585,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"ai-chapter","depth":23,"bounds":{"left":0.5422208,"top":0.23064645,"width":0.022273935,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.23064645,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54488033,"top":0.23064645,"width":0.019614361,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"alerts","depth":23,"bounds":{"left":0.5422208,"top":0.2529928,"width":0.012300532,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.2529928,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":5,"bounds":{"left":0.54488033,"top":0.2529928,"width":0.00930851,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"backend","depth":23,"bounds":{"left":0.5422208,"top":0.2753392,"width":0.018284574,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.2753392,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54521275,"top":0.2753392,"width":0.015292553,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"bugs","depth":23,"bounds":{"left":0.5422208,"top":0.29768556,"width":0.010638298,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.29768556,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":3,"bounds":{"left":0.54521275,"top":0.29768556,"width":0.00731383,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"confusion-clinic","depth":23,"bounds":{"left":0.5422208,"top":0.3200319,"width":0.034574468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.3200319,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54454786,"top":0.3200319,"width":0.032247342,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"curiosity_lab","depth":23,"bounds":{"left":0.5422208,"top":0.3423783,"width":0.027593086,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.3423783,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54454786,"top":0.3423783,"width":0.025265958,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"engineering","depth":23,"bounds":{"left":0.5422208,"top":0.36472467,"width":0.025930852,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.36472467,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":10,"bounds":{"left":0.54488033,"top":0.36472467,"width":0.022938829,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"general","depth":23,"bounds":{"left":0.5422208,"top":0.38707104,"width":0.016289894,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.38707104,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54488033,"top":0.38707104,"width":0.013297873,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"jiminny-bg","depth":23,"bounds":{"left":0.5422208,"top":0.4094174,"width":0.023271276,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.4094174,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54355055,"top":0.4094174,"width":0.021609042,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"platform-tickets","depth":23,"bounds":{"left":0.5422208,"top":0.43176377,"width":0.034906916,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.43176377,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54521275,"top":0.43176377,"width":0.031914894,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"product_launches","depth":23,"bounds":{"left":0.5422208,"top":0.45411015,"width":0.03856383,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.45411015,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54521275,"top":0.45411015,"width":0.03557181,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"random","depth":23,"bounds":{"left":0.5422208,"top":0.4764565,"width":0.016954787,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.4764565,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":5,"bounds":{"left":0.54421544,"top":0.4764565,"width":0.014960106,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"releases","depth":23,"bounds":{"left":0.5422208,"top":0.49880287,"width":0.01761968,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.49880287,"width":0.0016622341,"height":0.014365523}},{"char_start":1,"char_count":7,"bounds":{"left":0.54388297,"top":0.49880287,"width":0.015957447,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"sofia-office","depth":23,"bounds":{"left":0.5422208,"top":0.5211492,"width":0.024601065,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.5211492,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54454786,"top":0.5211492,"width":0.021941489,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"support","depth":23,"bounds":{"left":0.5422208,"top":0.5434956,"width":0.017287234,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.5434956,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.54454786,"top":0.5434956,"width":0.01462766,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"thank-yous","depth":23,"bounds":{"left":0.5422208,"top":0.565842,"width":0.024601065,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.565842,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54421544,"top":0.565842,"width":0.022606382,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"the_people_of_jiminny","depth":23,"bounds":{"left":0.5422208,"top":0.58818835,"width":0.045212764,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.58818835,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":20,"bounds":{"left":0.54421544,"top":0.58818835,"width":0.04720745,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":23,"bounds":{"left":0.5422208,"top":0.6408619,"width":0.037898935,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6408619,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.54488033,"top":0.6408619,"width":0.03523936,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Mario Georgiev","depth":23,"bounds":{"left":0.5422208,"top":0.6632083,"width":0.034242023,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6632083,"width":0.004654255,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.546875,"top":0.6632083,"width":0.02925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":23,"bounds":{"left":0.5422208,"top":0.6855547,"width":0.026595745,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.6855547,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54521275,"top":0.6855547,"width":0.023271276,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":23,"bounds":{"left":0.5422208,"top":0.70790106,"width":0.032247342,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.70790106,"width":0.0039893617,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.5462101,"top":0.70790106,"width":0.027925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"James Graham","depth":23,"bounds":{"left":0.5422208,"top":0.7302474,"width":0.031914894,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.7302474,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54421544,"top":0.7302474,"width":0.029920213,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Stoyan Tanev","depth":23,"bounds":{"left":0.5422208,"top":0.75259376,"width":0.028922873,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.75259376,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54488033,"top":0.75259376,"width":0.026263298,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":23,"bounds":{"left":0.5422208,"top":0.77494013,"width":0.03523936,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.77494013,"width":0.003656915,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.54587764,"top":0.77494013,"width":0.03158245,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":23,"bounds":{"left":0.5422208,"top":0.7972865,"width":0.038231384,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.7972865,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":16,"bounds":{"left":0.54488033,"top":0.7972865,"width":0.03557181,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Petko Kashinski","depth":23,"bounds":{"left":0.5422208,"top":0.8196329,"width":0.034574468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.8196329,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.54521275,"top":0.8196329,"width":0.03158245,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Aneliya Angelova","depth":23,"bounds":{"left":0.5422208,"top":0.84197927,"width":0.03756649,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.84197927,"width":0.0033244682,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.5455452,"top":0.84197927,"width":0.034242023,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Lukas Kovalik","depth":23,"bounds":{"left":0.5422208,"top":0.86432564,"width":0.029587766,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.86432564,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.54488033,"top":0.86432564,"width":0.026928192,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"you","depth":23,"bounds":{"left":0.5744681,"top":0.86432564,"width":0.0063164895,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5744681,"top":0.86432564,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":2,"bounds":{"left":0.5767952,"top":0.86432564,"width":0.0056515955,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Jira Cloud","depth":23,"bounds":{"left":0.5422208,"top":0.9169992,"width":0.021941489,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.9169992,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54421544,"top":0.9169992,"width":0.019946808,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Toast","depth":23,"bounds":{"left":0.5422208,"top":0.9393456,"width":0.011635638,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5422208,"top":0.9393456,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":4,"bounds":{"left":0.54454786,"top":0.9393456,"width":0.00930851,"height":0.014365523}}],"role_description":"text"},{"role":"AXButton","text":"@Toast section","depth":20,"bounds":{"left":0.60206115,"top":0.09976058,"width":0.0066489363,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Toast","depth":20,"bounds":{"left":0.6100399,"top":0.10055866,"width":0.020279255,"height":0.019952115},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast","depth":21,"bounds":{"left":0.61668885,"top":0.10215483,"width":0.012300532,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.61668885,"top":0.10295291,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":4,"bounds":{"left":0.6193484,"top":0.10295291,"width":0.009640957,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"1 message","depth":21,"bounds":{"left":0.92918885,"top":0.10454908,"width":0.020279255,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.92918885,"top":0.10454908,"width":0.0026595744,"height":0.012769354}},{"char_start":1,"char_count":8,"bounds":{"left":0.9318484,"top":0.10454908,"width":0.017287234,"height":0.012769354}}],"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"bounds":{"left":0.953125,"top":0.09976058,"width":0.034574468,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.7882314,"top":0.1452514,"width":0.018949468,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.7882314,"top":0.14604948,"width":0.0023271276,"height":0.012769354}},{"char_start":1,"char_count":8,"bounds":{"left":0.7905585,"top":0.14604948,"width":0.01662234,"height":0.012769354}}],"role_description":"text"},{"role":"AXButton","text":"Review Toast","depth":22,"bounds":{"left":0.6180186,"top":0.17238627,"width":0.029587766,"height":0.017557861},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"bounds":{"left":0.6499335,"top":0.1763767,"width":0.0063164895,"height":0.009577015},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6499335,"top":0.1763767,"width":0.0023271276,"height":0.009577015}},{"char_start":1,"char_count":2,"bounds":{"left":0.65226066,"top":0.1763767,"width":0.0039893617,"height":0.009577015}}],"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"bounds":{"left":0.65724736,"top":0.17398244,"width":0.0026595744,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 2:23:21 PM","depth":22,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.014960106,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"2:23 PM","depth":23,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.014960106,"height":0.011173184},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6599069,"top":0.1763767,"width":0.0023271276,"height":0.011971269}},{"char_start":1,"char_count":6,"bounds":{"left":0.66223407,"top":0.1763767,"width":0.012965426,"height":0.011971269}}],"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR","depth":23,"bounds":{"left":0.6180186,"top":0.1915403,"width":0.14694148,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6180186,"top":0.1915403,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":63,"bounds":{"left":0.62101066,"top":0.1915403,"width":0.14394946,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by","depth":25,"bounds":{"left":0.62333775,"top":0.21388668,"width":0.053523935,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"stefka-jiminny","depth":25,"bounds":{"left":0.6768617,"top":0.21388668,"width":0.03158245,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"stefka-jiminny","depth":26,"bounds":{"left":0.6768617,"top":0.21388668,"width":0.03158245,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"on","depth":25,"bounds":{"left":0.7084442,"top":0.21388668,"width":0.00831117,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"bounds":{"left":0.71642286,"top":0.21388668,"width":0.03723404,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"bounds":{"left":0.71642286,"top":0.21388668,"width":0.03723404,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"'s PR","depth":25,"bounds":{"left":0.7536569,"top":0.21388668,"width":0.010638298,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":25,"bounds":{"left":0.62333775,"top":0.23144454,"width":0.125,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"#12058 JY-18091 | Update composer to support php 8.5","depth":26,"bounds":{"left":0.62333775,"top":0.23144454,"width":0.125,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"by","depth":25,"bounds":{"left":0.74833775,"top":0.23144454,"width":0.0066489363,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"nikolaybiaivanov","depth":25,"bounds":{"left":0.62333775,"top":0.2490024,"width":0.036236703,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"nikolaybiaivanov","depth":26,"bounds":{"left":0.62333775,"top":0.2490024,"width":0.036236703,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"10 commits・260 files changed","depth":26,"bounds":{"left":0.6286569,"top":0.2697526,"width":0.069148935,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"JIRA:","depth":25,"bounds":{"left":0.62333775,"top":0.2905028,"width":0.012965426,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-18091","depth":25,"bounds":{"left":0.6359708,"top":0.2905028,"width":0.021609042,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-18091","depth":26,"bounds":{"left":0.6359708,"top":0.2905028,"width":0.021609042,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Deployment notes:","depth":25,"bounds":{"left":0.62333775,"top":0.30806065,"width":0.042220745,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"• None","depth":25,"bounds":{"left":0.62333775,"top":0.3320032,"width":0.016289894,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"jiminny/app","depth":24,"bounds":{"left":0.62333775,"top":0.3575419,"width":0.022606382,"height":0.012769354},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"jiminny/app","depth":25,"bounds":{"left":0.62333775,"top":0.3575419,"width":0.022606382,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Added by","depth":24,"bounds":{"left":0.62333775,"top":0.3782921,"width":0.01761968,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Toast for GitHub","depth":24,"bounds":{"left":0.6409575,"top":0.3782921,"width":0.02925532,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Toast for GitHub","depth":25,"bounds":{"left":0.6409575,"top":0.3782921,"width":0.02925532,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"@Jira Cloud section","depth":20,"bounds":{"left":0.60206115,"top":0.42138866,"width":0.0066489363,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":true},{"role":"AXButton","text":"Active Jira Cloud","depth":20,"bounds":{"left":0.6100399,"top":0.42218676,"width":0.03025266,"height":0.019952115},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Jira Cloud","depth":21,"bounds":{"left":0.61668885,"top":0.4237829,"width":0.022273935,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"3 messages","depth":21,"bounds":{"left":0.89793885,"top":0.42617717,"width":0.021941489,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Press","depth":20,"bounds":{"left":0.9225399,"top":0.4253791,"width":0.011303191,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Esc","depth":20,"bounds":{"left":0.93650264,"top":0.4253791,"width":0.0063164895,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"to","depth":20,"bounds":{"left":0.94547874,"top":0.4253791,"width":0.0066489363,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as Read","depth":20,"bounds":{"left":0.953125,"top":0.42138866,"width":0.034574468,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.7882314,"top":0.4668795,"width":0.018949468,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Jira Cloud","depth":22,"bounds":{"left":0.6180186,"top":0.49401435,"width":0.022273935,"height":0.017557861},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"APP","depth":22,"bounds":{"left":0.64261967,"top":0.4980048,"width":0.0066489363,"height":0.009577015},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":22,"bounds":{"left":0.6499335,"top":0.49561054,"width":0.0026595744,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"Today at 6:00:52 PM","depth":22,"bounds":{"left":0.6525931,"top":0.4980048,"width":0.015292553,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:00 PM","depth":23,"bounds":{"left":0.6525931,"top":0.4980048,"width":0.015292553,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"bounds":{"left":0.62666225,"top":0.5131684,"width":0.04255319,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"bounds":{"left":0.62666225,"top":0.5131684,"width":0.04255319,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"created a Technical Story you are assigned to","depth":24,"bounds":{"left":0.66921544,"top":0.5131684,"width":0.10006649,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":24,"bounds":{"left":0.6180186,"top":0.53072625,"width":0.11037234,"height":0.014365523},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"JY-20897 [Laravel 13] Testing of Platform Domain","depth":25,"bounds":{"left":0.6180186,"top":0.53072625,"width":0.11037234,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Status:","depth":23,"bounds":{"left":0.6180186,"top":0.55626494,"width":0.013962766,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Backlog","depth":23,"bounds":{"left":0.6319814,"top":0.55626494,"width":0.015292553,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Type:","depth":23,"bounds":{"left":0.6525931,"top":0.55626494,"width":0.011303191,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Technical Story","depth":23,"bounds":{"left":0.66389626,"top":0.55626494,"width":0.02925532,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Assignee:","depth":23,"bounds":{"left":0.70611703,"top":0.55626494,"width":0.019281914,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Lukas","depth":23,"bounds":{"left":0.72539896,"top":0.55626494,"width":0.010970744,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"bounds":{"left":0.73636967,"top":0.55626494,"width":0.0009973404,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Kovalik","depth":23,"bounds":{"left":0.73736703,"top":0.55626494,"width":0.014295213,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Priority:","depth":23,"bounds":{"left":0.76462764,"top":0.55626494,"width":0.01662234,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Medium","depth":23,"bounds":{"left":0.7809175,"top":0.55626494,"width":0.015957447,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Transition","depth":23,"bounds":{"left":0.6180186,"top":0.5826017,"width":0.025265958,"height":0.022346368},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Transition","depth":25,"bounds":{"left":0.62101066,"top":0.5865922,"width":0.019281914,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXComboBox","text":"More actions...","depth":24,"bounds":{"left":0.6456117,"top":0.5826017,"width":0.06349734,"height":0.022346368},"on_screen":true,"placeholder":"More actions...","role_description":"combo box","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with white_check_mark","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with eyes","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"React with raised_hands","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Add reaction…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Reply in thread","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Forward message…","depth":24,"on_screen":false,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXCheckBox","text":"Save for later","depth":24,"on_screen":false,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":24,"on_screen":false,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXLink","text":"Today at 6:00:52 PM","depth":23,"bounds":{"left":0.60738033,"top":0.61851555,"width":0.007978723,"height":0.011173184},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"6:00","depth":24,"bounds":{"left":0.60738033,"top":0.61851555,"width":0.007978723,"height":0.011173184},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":24,"bounds":{"left":0.62666225,"top":0.61532325,"width":0.043882977,"height":0.015961692},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":25,"bounds":{"left":0.62732714,"top":0.6161213,"width":0.04255319,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"updated the description of a Technical Story you are assigned to","depth":24,"bounds":{"left":0.6705452,"top":0.6161213,"width":0.1419548,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"JY-16113 [Laravel 12] Testing of Platform Domain","depth":24,"bounds":{"left":0.6180186,"top":0.63367915,"width":0.11037234,"height":0.014365523},"on_screen":true,"role_description":"link"},{"role":"AXStaticText","text":"Processing uploaded file… complete! Message ready to be sent.","depth":11,"bounds":{"left":0.5,"top":0.9992019,"width":0.022938829,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Channel","depth":11,"bounds":{"left":0.5,"top":0.9992019,"width":0.01761968,"height":0.0007980846},"on_screen":true,"role_description":"text"}]...
|
-311623993868213767
|
-3729591175175160256
|
click
|
hybrid
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
Unreads
Threads
Huddles
Drafts & sent
1
Directories
jiminny-x-integration-app
platform-inner-team
ai-chapter
alerts
backend
bugs
confusion-clinic
curiosity_lab
engineering
general
jiminny-bg
platform-tickets
product_launches
random
releases
sofia-office
support
thank-yous
the_people_of_jiminny
Stefka Stoyanova
Mario Georgiev
Vasil Vasilev
Nikolay Ivanov
James Graham
Stoyan Tanev
Galya Dimitrova
Steliyan Georgiev
Petko Kashinski
Aneliya Angelova
Lukas Kovalik
you
Jira Cloud
Toast
@Toast section
Active Toast
Toast
1 message
Mark as Read
Yesterday
Review Toast
APP
Today at 2:23:21 PM
2:23 PM
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
PR review requested by
stefka-jiminny
stefka-jiminny
on
nikolaybiaivanov
nikolaybiaivanov
's PR
#12058 JY-18091 | Update composer to support php 8.5
#12058 JY-18091 | Update composer to support php 8.5
by
nikolaybiaivanov
nikolaybiaivanov
10 commits・260 files changed
JIRA:
JY-18091
JY-18091
Deployment notes:
• None
jiminny/app
jiminny/app
Added by
Toast for GitHub
Toast for GitHub
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
@Jira Cloud section
Active Jira Cloud
Jira Cloud
3 messages
Press
Esc
to
Mark as Read
Yesterday
Jira Cloud
APP
Today at 6:00:52 PM
6:00 PM
@Stefka Stoyanova
@Stefka Stoyanova
created a Technical Story you are assigned to
JY-20897 [Laravel 13] Testing of Platform Domain
JY-20897 [Laravel 13] Testing of Platform Domain
Status:
Backlog
Type:
Technical Story
Assignee:
Lukas
Kovalik
Priority:
Medium
Transition
Transition
More actions...
React with white_check_mark
React with eyes
React with raised_hands
Add reaction…
Reply in thread
Forward message…
Save for later
More actions
Today at 6:00:52 PM
6:00
@Stefka Stoyanova
@Stefka Stoyanova
updated the description of a Technical Story you are assigned to
JY-16113 [Laravel 12] Testing of Platform Domain
Processing uploaded file… complete! Message ready to be sent.
Channel
SlackVIewmistoryWindowHelpdop.screenolpe.lakylak.xyzScreenpipe - Archive• Goocle GeminiAll docs • AFFiNEGemini• DXP4800PLUS-B5F8® Screenpipe - Archive® SQLite Web: archive.dbGShow thinkingv( SQLite Web: db.salite→ Claude% Manage extra usage for paicThat is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even thesecondarv ssu-onlv beelink Nas It vou ena uo oulloino iu will keeo vour local ssu lean whilekeeping your database searchable.As for setting up languages for transcription, yes, you can configure it, but it helps tounderstand how ScreenPipe handles language natively first.G 2 TB in 25 MB/s - Gooale Se- New TabHow the Transcription Engine Handles Languageby derault, screenripe uses a multilingual whisper model and sets the language contigurationTO AuTO-DerectWhen a new audio chunk comes in, the model listens to the first few seconds of audio, guessesthe language, and transcribes the rest of that chunk using that assumption.• The Advantage: If you are watching a tutorial in English, and then an hour later you are in aZoom call speaking Bulgarian, ScreenPipe will automatically switch gears without youhaving to touch the settings.• The Drawback: Auto-detect can sometimes guess wrong, especially if there is heavybackground noise, if someone starts a sentence with a foreign loanword, or if you arerapidly code-switching between Slovak and English in the same conversation. When itguesses wrong, it might try to torce Slovak words into English spelling, resulting inaloberish.How to Force a Specific LanguageIf you want to ensure maximum accuracy and you know you will primarily be recording in onelanguage for a specific period, you can explicitly set the language. This also slightly speeds upthe processing because the model skips the detection phase.If you are using the Desktop App UI:1. Open the ScreenPipe settings.Ask GeminiPro VGemini is Al and can make mistakes, including about people. Your privacy and GeminiSummarize pageScreenpipe (archive.db • 2071.1MB)XeaVneVSearchWork Repors09: 45Activity12 May 10:15 • iTerm2Jiminny... ~h External connections# StarredÔ jiminny-x-integrati…..& platform-inner-team@ Channels# ai-chapterit alerts# backend# bugs# confusion-clinic# curiosity_lab# engineering# general#jiminny-bg# platform-tickets# product_launchesirandom# releasesi sona-otnce# support# thank-vous# the_people_of jimi...•? Direct messagesFf. Stefka Stoyanova88. Mario GeorgievVasll VasilevC. Nikolay IvanovSn James Graham2. Stoyan TanevP. Galya Dimitrovaf. Steliyan GeorgievPetko Kashinskif. Aneliya Angelovae. Lukas Kovalik y...# AppsG Jira CloudB ToastB +•* 30siTerm2 M FirefDally - Platorm• In 15m100% 2Inu 14 May 9-20.13Q Describe what you are looking forUnreads © All conversations Sorted by recommended order ~• 0 loastYesterdayReview Toast APP 2:23 PMPR review requested by@stefka-jiminny on @nikolaybiaivanov's PRPR review requested by stefka-jiminny on nikolaybiaivanov's PR#1z058JY-18071 Update composer to support pho 8.5 bvnikolavbiaivanov| 10 commits • 260 files changedJIRA: JY-18091Deployment notes:•NoneAdded by Toast for GitHub• • Jira CloucYesterdayJira Cloud APP 6:00 PMA @Stefka Stoyanova created a Technical Story you are assigned toJY-Z0o7/ Laravel 13 lesang or Platrorm DonStatus: BacklogCK Assignee: Lukas KovalikPriority: Medium1AStefka Stovanova undated the descrintion of a Technical Story vou are assioned toJY-16113 [Laravel 12] Testing of Platform DomainStatus: Closed Tvne. Technical Storv(LK) Assionee: Lukas KovalilT Priority: MediumTransition_ @Stefka Stoyanova assigned a Technical Story from you — UnassignedJY-20897 [Laravel 13] Testing of Platform DomainStatus: BacklogType: Technical Story® Assignee: UnassignedT Priority: MediumMark All Messages ReadMark as Read3 messages Press Esc toMark as Readl...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38669
|
1439
|
2
|
2026-05-14T06:26:15.010252+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739975010_m2.jpg...
|
Slack
|
Activity - Jiminny Inc - 4 new items - Slack
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
All, 4 unread
DMs
Add new tab
Stefka Stoyanova
DM
Mark as unread
Clear
More actions
здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)
…
Yesterday
Mario Georgiev
DM
Yesterday
тенк ю вери мъч, махнах му crm seat-a и има достъп, ще го имам напредвид вече че явно бие такава грешка когато фрии акаунта expir-ne или нещо подобно и няма особен workaround
Jira Cloud
App
Yesterday
@Stefka Stoyanova
@Stefka Stoyanova
assigned a Technical Story from you ⟶ Unassigned
…
Vasil Vasilev
DM
Replied
Yesterday
добреее, значи трябва да има процес, който чете от redis и налива в Elastic Search
Review Toast
App
Yesterday
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
Nikolay Ivanov
DM
Yesterday
ще станат конфликти
James Graham
DM
Yesterday
Cheers!
Tuesday, May 12th
Stoyan Tanev
DM
Replied
Tuesday
сега всичко е 6
Vasil Vasilev
Reacted in
platform-inner-team
Tuesday
You:
може ли един approve
https://github.com/jiminny/app/pull/12024
https://github.com/jiminny/app/pull/12024
1 reaction, react with white check mark emoji
1
Galya Dimitrova
DM
Tuesday
И другата седмица имаме презднтации пред борда в Лондон и съм до никъде
Galya Dimitrova
Reacted in
DM
Tuesday
You:
ако трябва да се пипне и в кода ще си направя тикет
1 reaction, react with +1 emoji
1
Steliyan Georgiev
DM
Tuesday
ще го видя
Steliyan Georgiev
Reacted in
DM
Tuesday
You:
ето го и репорт
…
1 reaction, react with +1 emoji
1
Petko Kashinski
DM
Tuesday
Huddle ?
Later
5 in progress
Incomplete • 7 days ago
backend
Nikolay Ivanov
For those using
make cs-fix
and getting annoyed by how long it takes (since it scans the entire project), you can now use
make cs-fix-branch
. It will fix only the files that differ from
master
, and it runs in just a couple of seconds
Incomplete • 7 days ago
Direct Message
Ves
изглежда е нямало QAi postmark и сме използвали този за QA
Incomplete • 3 days ago
Direct Message
Galya Dimitrova
привет, понеже другия спринт ще си продължиш с каквото остана по репортите, можеш ли днес или утре да видиш тези двете неща и да ми кажеш естимейт за тях:
…
Incomplete • 2 days ago
Direct Message
Petko Kashinski
playbackVisited
Due in 3 hours
•
Direct Message
Stefka Stoyanova
здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)
…
Select a notification to view the details.
Processing uploaded file… complete! Message ready to be sent.
Channel...
|
[{"role":"AXPopUpButton","text [{"role":"AXPopUpButton","text":"Switch workspaces… (Jiminny Inc) Has new messages","depth":14,"bounds":{"left":0.5056516,"top":0.058260176,"width":0.011968086,"height":0.028731046},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"Home","depth":14,"bounds":{"left":0.50299203,"top":0.10055866,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Home","depth":16,"bounds":{"left":0.50664896,"top":0.13806863,"width":0.009973404,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"DMs","depth":14,"bounds":{"left":0.50299203,"top":0.15482841,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"DMs","depth":16,"bounds":{"left":0.50764626,"top":0.19233839,"width":0.007978723,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Activity","depth":14,"bounds":{"left":0.50299203,"top":0.20909816,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXStaticText","text":"Activity","depth":16,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.012965426,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.0026595744,"height":0.011173184}},{"char_start":1,"char_count":7,"bounds":{"left":0.50764626,"top":0.24660814,"width":0.010638298,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Files","depth":14,"bounds":{"left":0.50299203,"top":0.26336792,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Files","depth":16,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0076462766,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5099734,"top":0.3008779,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Later","depth":14,"bounds":{"left":0.50299203,"top":0.31763768,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Later","depth":16,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.008643617,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5093085,"top":0.35514766,"width":0.0066489363,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"More…","depth":14,"bounds":{"left":0.50299203,"top":0.3719074,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"More","depth":16,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.008976064,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.0033244682,"height":0.011173184}},{"char_start":1,"char_count":3,"bounds":{"left":0.5106383,"top":0.4094174,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"All, 4 unread","depth":19,"bounds":{"left":0.52892286,"top":0.09497207,"width":0.021609042,"height":0.026336791},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXRadioButton","text":"DMs","depth":19,"bounds":{"left":0.55019945,"top":0.09497207,"width":0.014960106,"height":0.026336791},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"Add new tab","depth":20,"bounds":{"left":0.5674867,"top":0.09497207,"width":0.0056515955,"height":0.026336791},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":22,"bounds":{"left":0.54787236,"top":0.18276137,"width":0.037898935,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.18276137,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.5505319,"top":0.18276137,"width":0.03523936,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.19952115,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as unread","depth":23,"bounds":{"left":0.5880984,"top":0.17797287,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Clear","depth":23,"bounds":{"left":0.5987367,"top":0.17797287,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":23,"bounds":{"left":0.609375,"top":0.17797287,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)","depth":23,"bounds":{"left":0.53324467,"top":0.21787709,"width":0.08643617,"height":0.06703911},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.21787709,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":105,"bounds":{"left":0.53324467,"top":0.21787709,"width":0.08643617,"height":0.049481247}}],"role_description":"text"},{"role":"AXStaticText","text":"…","depth":23,"bounds":{"left":0.55019945,"top":0.27055067,"width":0.0039893617,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":21,"bounds":{"left":0.5671542,"top":0.28890663,"width":0.018949468,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5671542,"top":0.2897047,"width":0.0026595744,"height":0.012769354}},{"char_start":1,"char_count":8,"bounds":{"left":0.5694814,"top":0.2897047,"width":0.01662234,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Mario Georgiev","depth":22,"bounds":{"left":0.54787236,"top":0.33439744,"width":0.034242023,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.33439744,"width":0.004654255,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.5525266,"top":0.33439744,"width":0.02925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.35115722,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.3367917,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.3367917,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.3367917,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"тенк ю вери мъч, махнах му crm seat-a и има достъп, ще го имам напредвид вече че явно бие такава грешка когато фрии акаунта expir-ne или нещо подобно и няма особен workaround","depth":23,"bounds":{"left":0.53324467,"top":0.36951315,"width":0.08610372,"height":0.10215483},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.36951315,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":173,"bounds":{"left":0.53324467,"top":0.36951315,"width":0.08610372,"height":0.10215483}}],"role_description":"text"},{"role":"AXStaticText","text":"Jira Cloud","depth":22,"bounds":{"left":0.54787236,"top":0.43176377,"width":0.021941489,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.43176377,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54986703,"top":0.43176377,"width":0.019946808,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"App","depth":22,"bounds":{"left":0.54787236,"top":0.44852355,"width":0.007978723,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.44852355,"width":0.0029920214,"height":0.012769354}},{"char_start":1,"char_count":2,"bounds":{"left":0.55086434,"top":0.44852355,"width":0.004986702,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.43415803,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.43415803,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.43415803,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"bounds":{"left":0.5405585,"top":0.4668795,"width":0.0013297872,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":23,"bounds":{"left":0.5418883,"top":0.4660814,"width":0.043882977,"height":0.015961692},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":24,"bounds":{"left":0.5425532,"top":0.4668795,"width":0.04255319,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5425532,"top":0.4668795,"width":0.0043218085,"height":0.014365523}},{"char_start":1,"char_count":16,"bounds":{"left":0.5465425,"top":0.4668795,"width":0.03856383,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"assigned a Technical Story from you ⟶ Unassigned","depth":23,"bounds":{"left":0.53324467,"top":0.4668795,"width":0.077792555,"height":0.049481247},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.58577126,"top":0.4668795,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":47,"bounds":{"left":0.53324467,"top":0.4668795,"width":0.077792555,"height":0.049481247}}],"role_description":"text"},{"role":"AXStaticText","text":"…","depth":23,"bounds":{"left":0.5588431,"top":0.5019952,"width":0.0039893617,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":22,"bounds":{"left":0.54787236,"top":0.5291301,"width":0.026595745,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.5291301,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.55086434,"top":0.5291301,"width":0.023271276,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.54588985,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Replied","depth":22,"bounds":{"left":0.58477396,"top":0.53152436,"width":0.012965426,"height":0.011971269},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.58477396,"top":0.5323224,"width":0.0023271276,"height":0.011971269}},{"char_start":1,"char_count":6,"bounds":{"left":0.58710104,"top":0.5323224,"width":0.010638298,"height":0.011971269}}],"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.53152436,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.53152436,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.53152436,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"добреее, значи трябва да има процес, който чете от redis и налива в Elastic Search","depth":23,"bounds":{"left":0.53324467,"top":0.5642458,"width":0.08610372,"height":0.049481247},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.5642458,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":82,"bounds":{"left":0.53324467,"top":0.5642458,"width":0.08610372,"height":0.031923383}}],"role_description":"text"},{"role":"AXStaticText","text":"Review Toast","depth":22,"bounds":{"left":0.54787236,"top":0.62649643,"width":0.028590426,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.62649643,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.55086434,"top":0.62649643,"width":0.025598405,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"App","depth":22,"bounds":{"left":0.54787236,"top":0.6432562,"width":0.007978723,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.6432562,"width":0.0029920214,"height":0.012769354}},{"char_start":1,"char_count":2,"bounds":{"left":0.55086434,"top":0.6432562,"width":0.004986702,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.62889063,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.62889063,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.62889063,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR","depth":23,"bounds":{"left":0.53324467,"top":0.66161215,"width":0.07480053,"height":0.031923383},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.66161215,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":63,"bounds":{"left":0.53324467,"top":0.66161215,"width":0.07480053,"height":0.031923383}}],"role_description":"text"},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":22,"bounds":{"left":0.54787236,"top":0.7238627,"width":0.032247342,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.7238627,"width":0.0039893617,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.5518617,"top":0.7238627,"width":0.027925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.7406225,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.72625697,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.72625697,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.72625697,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"ще станат конфликти","depth":23,"bounds":{"left":0.53324467,"top":0.7589784,"width":0.050199468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.7589784,"width":0.0043218085,"height":0.014365523}},{"char_start":1,"char_count":18,"bounds":{"left":0.5375665,"top":0.7589784,"width":0.045545213,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"James Graham","depth":22,"bounds":{"left":0.54787236,"top":0.8036712,"width":0.031914894,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.8036712,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54986703,"top":0.8036712,"width":0.029920213,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.820431,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.80606544,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.80606544,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.80606544,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"Cheers!","depth":23,"bounds":{"left":0.53324467,"top":0.8387869,"width":0.016954787,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.8387869,"width":0.0033244682,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.5365692,"top":0.8387869,"width":0.013297873,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Tuesday, May 12th","depth":21,"bounds":{"left":0.55851066,"top":0.8922586,"width":0.036236703,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.55851066,"top":0.8930567,"width":0.0023271276,"height":0.012769354}},{"char_start":1,"char_count":16,"bounds":{"left":0.56083775,"top":0.8930567,"width":0.033909574,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Stoyan Tanev","depth":22,"bounds":{"left":0.54787236,"top":0.9377494,"width":0.028922873,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.9377494,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.5505319,"top":0.9377494,"width":0.026263298,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.9545092,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Replied","depth":22,"bounds":{"left":0.58776593,"top":0.94014364,"width":0.012965426,"height":0.011971269},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.58776593,"top":0.94094175,"width":0.0023271276,"height":0.011971269}},{"char_start":1,"char_count":6,"bounds":{"left":0.5900931,"top":0.94094175,"width":0.010638298,"height":0.011971269}}],"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.94014364,"width":0.015292553,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6047208,"top":0.94014364,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":6,"bounds":{"left":0.60671544,"top":0.94014364,"width":0.013630319,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"сега всичко е 6","depth":23,"bounds":{"left":0.53324467,"top":0.9728651,"width":0.034574468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.9728651,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.5355718,"top":0.9728651,"width":0.032247342,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.026595745,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Reacted in","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.019946808,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"platform-inner-team","depth":22,"bounds":{"left":0.56981385,"top":0.9952115,"width":0.027260639,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"You:","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.009640957,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"може ли един approve","depth":23,"bounds":{"left":0.54388297,"top":0.9952115,"width":0.05285904,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"https://github.com/jiminny/app/pull/12024","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.08676862,"height":0.0007980846},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"https://github.com/jiminny/app/pull/12024","depth":24,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.08676862,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"1 reaction, react with white check mark emoji","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.014295213,"height":0.0007980846},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"1","depth":24,"bounds":{"left":0.5425532,"top":0.9952115,"width":0.0023271276,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.03523936,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"И другата седмица имаме презднтации пред борда в Лондон и съм до никъде","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.08610372,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.03523936,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Reacted in","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.019946808,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.56848407,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"You:","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.009640957,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ако трябва да се пипне и в кода ще си направя тикет","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.08510638,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"1 reaction, react with +1 emoji","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.014295213,"height":0.0007980846},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"1","depth":24,"bounds":{"left":0.5425532,"top":0.9952115,"width":0.0023271276,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.038231384,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ще го видя","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.025265958,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.038231384,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Reacted in","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.019946808,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.56848407,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"You:","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.009640957,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ето го и репорт","depth":23,"bounds":{"left":0.54388297,"top":0.9952115,"width":0.03557181,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"…","depth":23,"bounds":{"left":0.5794548,"top":0.9952115,"width":0.0039893617,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"1 reaction, react with +1 emoji","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.014295213,"height":0.0007980846},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"1","depth":24,"bounds":{"left":0.5425532,"top":0.9952115,"width":0.0023271276,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Petko Kashinski","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.034574468,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Huddle ?","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.019614361,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Later","depth":20,"bounds":{"left":0.5275931,"top":0.29289705,"width":0.011968086,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5275931,"top":0.29289705,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":4,"bounds":{"left":0.53025264,"top":0.29289705,"width":0.008976064,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"5 in progress","depth":20,"bounds":{"left":0.5418883,"top":0.29449323,"width":0.024601065,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5418883,"top":0.29449323,"width":0.0026595744,"height":0.012769354}},{"char_start":1,"char_count":12,"bounds":{"left":0.54454786,"top":0.29449323,"width":0.021941489,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Incomplete • 7 days ago","depth":23,"bounds":{"left":0.52958775,"top":0.32881084,"width":0.04654255,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.52958775,"top":0.32881084,"width":0.0013297872,"height":0.012769354}},{"char_start":1,"char_count":22,"bounds":{"left":0.5309175,"top":0.32881084,"width":0.045212764,"height":0.012769354}}],"role_description":"text"},{"role":"AXButton","text":"backend","depth":23,"bounds":{"left":0.58211434,"top":0.3272147,"width":0.020944148,"height":0.015961692},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":23,"bounds":{"left":0.54089093,"top":0.34796488,"width":0.032912236,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54089093,"top":0.34796488,"width":0.0039893617,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.54488033,"top":0.34796488,"width":0.028590426,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"For those using","depth":23,"bounds":{"left":0.54089093,"top":0.36552274,"width":0.034906916,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54089093,"top":0.36552274,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.54355055,"top":0.36552274,"width":0.030917553,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"make cs-fix","depth":24,"bounds":{"left":0.5767952,"top":0.367917,"width":0.026595745,"height":0.011971269},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5767952,"top":0.367917,"width":0.0026595744,"height":0.011971269}},{"char_start":1,"char_count":10,"bounds":{"left":0.57912236,"top":0.367917,"width":0.024268618,"height":0.011971269}}],"role_description":"text"},{"role":"AXStaticText","text":"and getting annoyed by how long it takes (since it scans the entire project), you can now use","depth":23,"bounds":{"left":0.54089093,"top":0.36552274,"width":0.096409574,"height":0.049481247},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6047208,"top":0.36552274,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":92,"bounds":{"left":0.54089093,"top":0.36552274,"width":0.09607713,"height":0.031923383}}],"role_description":"text"},{"role":"AXStaticText","text":"make cs-fix-branch","depth":24,"bounds":{"left":0.54089093,"top":0.40303272,"width":0.09275266,"height":0.02952913},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":". It will fix only the files that differ from","depth":23,"bounds":{"left":0.54089093,"top":0.41819632,"width":0.09375,"height":0.031923383},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"master","depth":24,"bounds":{"left":0.5668218,"top":0.43814844,"width":0.014295213,"height":0.011971269},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":", and it runs in just a couple of seconds","depth":23,"bounds":{"left":0.54089093,"top":0.43575418,"width":0.08676862,"height":0.031923383},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Incomplete • 7 days ago","depth":23,"bounds":{"left":0.52958775,"top":0.42218676,"width":0.04654255,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Direct Message","depth":23,"bounds":{"left":0.58211434,"top":0.42059058,"width":0.02925532,"height":0.015961692},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Ves","depth":23,"bounds":{"left":0.54089093,"top":0.44134077,"width":0.007978723,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"изглежда е нямало QAi postmark и сме използвали този за QA","depth":23,"bounds":{"left":0.54089093,"top":0.45889863,"width":0.091090426,"height":0.031923383},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Incomplete • 3 days ago","depth":23,"bounds":{"left":0.52958775,"top":0.51556265,"width":0.04654255,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Direct Message","depth":23,"bounds":{"left":0.58211434,"top":0.5139665,"width":0.02925532,"height":0.015961692},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Galya Dimitrova","depth":23,"bounds":{"left":0.54089093,"top":0.53471667,"width":0.035904255,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"привет, понеже другия спринт ще си продължиш с каквото остана по репортите, можеш ли днес или утре да видиш тези двете неща и да ми кажеш естимейт за тях:","depth":23,"bounds":{"left":0.54089093,"top":0.5522745,"width":0.09275266,"height":0.08459697},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"…","depth":23,"bounds":{"left":0.5787899,"top":0.62250596,"width":0.003656915,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Incomplete • 2 days ago","depth":23,"bounds":{"left":0.52958775,"top":0.6089386,"width":0.04654255,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Direct Message","depth":23,"bounds":{"left":0.58211434,"top":0.60734236,"width":0.02925532,"height":0.015961692},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Petko Kashinski","depth":23,"bounds":{"left":0.54089093,"top":0.6280926,"width":0.03523936,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"playbackVisited","depth":23,"bounds":{"left":0.54089093,"top":0.64565045,"width":0.034242023,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Due in 3 hours","depth":23,"bounds":{"left":0.5262633,"top":0.6839585,"width":0.02825798,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"•","depth":24,"bounds":{"left":0.5568484,"top":0.6839585,"width":0.0026595744,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Direct Message","depth":23,"bounds":{"left":0.5621675,"top":0.6831604,"width":0.029587766,"height":0.014365523},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":23,"bounds":{"left":0.54089093,"top":0.70231444,"width":0.03856383,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)","depth":23,"bounds":{"left":0.54089093,"top":0.7198723,"width":0.09607713,"height":0.049481247},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"…","depth":23,"bounds":{"left":0.61901593,"top":0.754988,"width":0.003656915,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Select a notification to view the details.","depth":17,"bounds":{"left":0.7712766,"top":0.5171588,"width":0.08577128,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Processing uploaded file… complete! Message ready to be sent.","depth":11,"bounds":{"left":0.5,"top":0.9992019,"width":0.022938829,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Channel","depth":11,"bounds":{"left":0.5,"top":0.9992019,"width":0.01761968,"height":0.0007980846},"on_screen":true,"role_description":"text"}]...
|
-7915702098255327959
|
-4770723107705118713
|
visual_change
|
hybrid
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
All, 4 unread
DMs
Add new tab
Stefka Stoyanova
DM
Mark as unread
Clear
More actions
здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)
…
Yesterday
Mario Georgiev
DM
Yesterday
тенк ю вери мъч, махнах му crm seat-a и има достъп, ще го имам напредвид вече че явно бие такава грешка когато фрии акаунта expir-ne или нещо подобно и няма особен workaround
Jira Cloud
App
Yesterday
@Stefka Stoyanova
@Stefka Stoyanova
assigned a Technical Story from you ⟶ Unassigned
…
Vasil Vasilev
DM
Replied
Yesterday
добреее, значи трябва да има процес, който чете от redis и налива в Elastic Search
Review Toast
App
Yesterday
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
Nikolay Ivanov
DM
Yesterday
ще станат конфликти
James Graham
DM
Yesterday
Cheers!
Tuesday, May 12th
Stoyan Tanev
DM
Replied
Tuesday
сега всичко е 6
Vasil Vasilev
Reacted in
platform-inner-team
Tuesday
You:
може ли един approve
https://github.com/jiminny/app/pull/12024
https://github.com/jiminny/app/pull/12024
1 reaction, react with white check mark emoji
1
Galya Dimitrova
DM
Tuesday
И другата седмица имаме презднтации пред борда в Лондон и съм до никъде
Galya Dimitrova
Reacted in
DM
Tuesday
You:
ако трябва да се пипне и в кода ще си направя тикет
1 reaction, react with +1 emoji
1
Steliyan Georgiev
DM
Tuesday
ще го видя
Steliyan Georgiev
Reacted in
DM
Tuesday
You:
ето го и репорт
…
1 reaction, react with +1 emoji
1
Petko Kashinski
DM
Tuesday
Huddle ?
Later
5 in progress
Incomplete • 7 days ago
backend
Nikolay Ivanov
For those using
make cs-fix
and getting annoyed by how long it takes (since it scans the entire project), you can now use
make cs-fix-branch
. It will fix only the files that differ from
master
, and it runs in just a couple of seconds
Incomplete • 7 days ago
Direct Message
Ves
изглежда е нямало QAi postmark и сме използвали този за QA
Incomplete • 3 days ago
Direct Message
Galya Dimitrova
привет, понеже другия спринт ще си продължиш с каквото остана по репортите, можеш ли днес или утре да видиш тези двете неща и да ми кажеш естимейт за тях:
…
Incomplete • 2 days ago
Direct Message
Petko Kashinski
playbackVisited
Due in 3 hours
•
Direct Message
Stefka Stoyanova
здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)
…
Select a notification to view the details.
Processing uploaded file… complete! Message ready to be sent.
Channel
SlackScreenpipe - ArchiveAll docs • AFFiNE) DXP4800PLUS-B5F8©Screenpipe - Archive(*SQLite Web: archive.db( SQLite Web: db.salite• Claude% Manage extra usage for paicG 2 TB in 25 MB/s - Gooale Se- New TabVIewmistoryWindowHelpdop.screenolpe.lakylak.xyz• Goocle GeminiGeminiGShow thinkingThat is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even thesecondarv ssu-onlv beelink Nas It vou ena uo oulloino iu will keeo vour local ssu lean whilekeepina vour database searchableAs for setting up languages for transcription, yes, you can configure it, but it helps tounderstand how ScreenPipe handles language natively first.How the Transcription Engine Handles Languageby derault, screenripe uses a multilingual whisper model and sets the language contigurationTO AuTO-DerectWhen a new audio chunk comes in, the model listens to the first few seconds of audio, quessesthe language, and transcribes the rest of that chunk using that assumption.• The Advantage: If vou are watchina a tutorial in Enalish. and then an hour later vou are in aZoom call speakina Bulaarian. ScreenPipe will automatically switch gears without vouhaving to touch the settinas.• The Drawback: Auto-detect can sometimes guess wrong, especially it there is heavybackground noise, it someone starts a sentence with a foreign loanword, or it you arerapidly code-switching between Slovak and English in the same conversation. When itguesses wrong, it might try to torce Slovak words into English spelling, resulting incloberishHow to Force a Soecific LanquadeIf vou want to ensure maximum accuracy and vou know vou will primarily be recordina in onelanquage for a specific period, vou can explicitly set the lanquage. This also sliahtly speeds upthe processina because the model skips the detection phase.If vou are usina the Deskton Aoo UI:1. Open the ScreenPipe settinasAck CeminiS0 hhlDaily - Platform • in 19 m100% CInu 14 May 9-20.14@ Describe what you are looking forScreenpipe (archive.db • 2071.1MBXeaVneVSearchWork Repor09 : 45HomeDMSActivits12 Mav 10:15 . iTerm2Petko KashinskilAC.MIVAll4DMsStefka Stoyanovaзлаости / укаш. ше направиш листори ла ъпгрейлнем Pidedrive SDK....Later 5 in progressIncomplete • 7 days ago # backendNikolav IvanovFor those using make cs-fix and gettingannoyed by how long it takes (since it scan…Incomolete • 7 davs ago Direct Messageизглежла е нямало •Ai nostmark и сме.използвали този за одIncomolete • 3 davs agoDirect MessageGalva Dimitrovaпривет. понеже доугия споинт ше сиIncomplete • 2 days ago Direct MessageDotka KochinckilplaybackVisitedDue in 2 hourc Direct MeccaodStetka Stovanovaзлаости Лукаш, ще напоавиш ли сторила злглеилнем Pinedrive SDK ако може...Select a notification to view the detailsPro VGemini is Aland can make mictakes includina about neonle Your nrivacv and GeminSummarize pageB +•* 30sierm? FirefoCtavan Thnowdo oMcors oeuuvA ALReplied Tuesdav...
|
38668
|
NULL
|
NULL
|
NULL
|
|
38670
|
1439
|
3
|
2026-05-14T06:26:18.069546+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739978069_m2.jpg...
|
Slack
|
Activity - Jiminny Inc - 4 new items - Slack
|
1
|
NULL
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
All, 4 unread
DMs
Add new tab
Stefka Stoyanova
DM
Mark as unread
Clear
More actions
здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)
…
Yesterday
Mario Georgiev
DM
Yesterday
тенк ю вери мъч, махнах му crm seat-a и има достъп, ще го имам напредвид вече че явно бие такава грешка когато фрии акаунта expir-ne или нещо подобно и няма особен workaround
Jira Cloud
App
Yesterday
@Stefka Stoyanova
@Stefka Stoyanova
assigned a Technical Story from you ⟶ Unassigned
…
Vasil Vasilev
DM
Replied
Yesterday
добреее, значи трябва да има процес, който чете от redis и налива в Elastic Search
Review Toast
App
Yesterday
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
Nikolay Ivanov
DM
Yesterday
ще станат конфликти
James Graham
DM
Yesterday
Cheers!
Tuesday, May 12th
Stoyan Tanev
DM
Replied
Tuesday
сега всичко е 6
Vasil Vasilev
Reacted in
platform-inner-team
Tuesday
You:
може ли един approve
https://github.com/jiminny/app/pull/12024
https://github.com/jiminny/app/pull/12024
1 reaction, react with white check mark emoji
1
Galya Dimitrova
DM
Tuesday
И другата седмица имаме презднтации пред борда в Лондон и съм до никъде
Galya Dimitrova
Reacted in
DM
Tuesday
You:
ако трябва да се пипне и в кода ще си направя тикет
1 reaction, react with +1 emoji
1
Steliyan Georgiev
DM
Tuesday
ще го видя
Steliyan Georgiev
Reacted in
DM
Tuesday
You:
ето го и репорт
…
1 reaction, react with +1 emoji
1
Petko Kashinski
DM
Tuesday
Huddle ?
Select a notification to view the details.
Processing uploaded file… complete! Message ready to be sent.
Channel...
|
[{"role":"AXPopUpButton","text [{"role":"AXPopUpButton","text":"Switch workspaces… (Jiminny Inc) Has new messages","depth":14,"bounds":{"left":0.5056516,"top":0.058260176,"width":0.011968086,"height":0.028731046},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXRadioButton","text":"Home","depth":14,"bounds":{"left":0.50299203,"top":0.10055866,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Home","depth":16,"bounds":{"left":0.50664896,"top":0.13806863,"width":0.009973404,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"DMs","depth":14,"bounds":{"left":0.50299203,"top":0.15482841,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"DMs","depth":16,"bounds":{"left":0.50764626,"top":0.19233839,"width":0.007978723,"height":0.0103751},"on_screen":true,"role_description":"text"},{"role":"AXRadioButton","text":"Activity","depth":14,"bounds":{"left":0.50299203,"top":0.20909816,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXStaticText","text":"Activity","depth":16,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.012965426,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5053192,"top":0.24660814,"width":0.0026595744,"height":0.011173184}},{"char_start":1,"char_count":7,"bounds":{"left":0.50764626,"top":0.24660814,"width":0.010638298,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Files","depth":14,"bounds":{"left":0.50299203,"top":0.26336792,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Files","depth":16,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0076462766,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50797874,"top":0.3008779,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5099734,"top":0.3008779,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"Later","depth":14,"bounds":{"left":0.50299203,"top":0.31763768,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Later","depth":16,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.008643617,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.35514766,"width":0.0019946808,"height":0.011173184}},{"char_start":1,"char_count":4,"bounds":{"left":0.5093085,"top":0.35514766,"width":0.0066489363,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"More…","depth":14,"bounds":{"left":0.50299203,"top":0.3719074,"width":0.017287234,"height":0.054269753},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"More","depth":16,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.008976064,"height":0.0103751},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.50731385,"top":0.4094174,"width":0.0033244682,"height":0.011173184}},{"char_start":1,"char_count":3,"bounds":{"left":0.5106383,"top":0.4094174,"width":0.0056515955,"height":0.011173184}}],"role_description":"text"},{"role":"AXRadioButton","text":"All, 4 unread","depth":19,"bounds":{"left":0.52892286,"top":0.09497207,"width":0.021609042,"height":0.026336791},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true,"is_expanded":false},{"role":"AXRadioButton","text":"DMs","depth":19,"bounds":{"left":0.55019945,"top":0.09497207,"width":0.014960106,"height":0.026336791},"on_screen":true,"role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"Add new tab","depth":20,"bounds":{"left":0.5674867,"top":0.09497207,"width":0.0056515955,"height":0.026336791},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Stefka Stoyanova","depth":22,"bounds":{"left":0.54787236,"top":0.18276137,"width":0.037898935,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.18276137,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":15,"bounds":{"left":0.5505319,"top":0.18276137,"width":0.03523936,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.19952115,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXButton","text":"Mark as unread","depth":23,"bounds":{"left":0.5880984,"top":0.17797287,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Clear","depth":23,"bounds":{"left":0.5987367,"top":0.17797287,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXPopUpButton","text":"More actions","depth":23,"bounds":{"left":0.609375,"top":0.17797287,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"pop-up button","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)","depth":23,"bounds":{"left":0.53324467,"top":0.21787709,"width":0.08643617,"height":0.06703911},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.21787709,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":105,"bounds":{"left":0.53324467,"top":0.21787709,"width":0.08643617,"height":0.049481247}}],"role_description":"text"},{"role":"AXStaticText","text":"…","depth":23,"bounds":{"left":0.55019945,"top":0.27055067,"width":0.0039893617,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":21,"bounds":{"left":0.5671542,"top":0.28890663,"width":0.018949468,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5671542,"top":0.2897047,"width":0.0026595744,"height":0.012769354}},{"char_start":1,"char_count":8,"bounds":{"left":0.5694814,"top":0.2897047,"width":0.01662234,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Mario Georgiev","depth":22,"bounds":{"left":0.54787236,"top":0.33439744,"width":0.034242023,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.33439744,"width":0.004654255,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.5525266,"top":0.33439744,"width":0.02925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.35115722,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.3367917,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.3367917,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.3367917,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"тенк ю вери мъч, махнах му crm seat-a и има достъп, ще го имам напредвид вече че явно бие такава грешка когато фрии акаунта expir-ne или нещо подобно и няма особен workaround","depth":23,"bounds":{"left":0.53324467,"top":0.36951315,"width":0.08610372,"height":0.10215483},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.36951315,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":173,"bounds":{"left":0.53324467,"top":0.36951315,"width":0.08610372,"height":0.10215483}}],"role_description":"text"},{"role":"AXStaticText","text":"Jira Cloud","depth":22,"bounds":{"left":0.54787236,"top":0.43176377,"width":0.021941489,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.43176377,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":9,"bounds":{"left":0.54986703,"top":0.43176377,"width":0.019946808,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"App","depth":22,"bounds":{"left":0.54787236,"top":0.44852355,"width":0.007978723,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.44852355,"width":0.0029920214,"height":0.012769354}},{"char_start":1,"char_count":2,"bounds":{"left":0.55086434,"top":0.44852355,"width":0.004986702,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.43415803,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.43415803,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.43415803,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"","depth":23,"bounds":{"left":0.5405585,"top":0.4668795,"width":0.0013297872,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"@Stefka Stoyanova","depth":23,"bounds":{"left":0.5418883,"top":0.4660814,"width":0.043882977,"height":0.015961692},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"@Stefka Stoyanova","depth":24,"bounds":{"left":0.5425532,"top":0.4668795,"width":0.04255319,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.5425532,"top":0.4668795,"width":0.0043218085,"height":0.014365523}},{"char_start":1,"char_count":16,"bounds":{"left":0.5465425,"top":0.4668795,"width":0.03856383,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"assigned a Technical Story from you ⟶ Unassigned","depth":23,"bounds":{"left":0.53324467,"top":0.4668795,"width":0.077792555,"height":0.049481247},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.58577126,"top":0.4668795,"width":0.0013297872,"height":0.014365523}},{"char_start":1,"char_count":47,"bounds":{"left":0.53324467,"top":0.4668795,"width":0.077792555,"height":0.049481247}}],"role_description":"text"},{"role":"AXStaticText","text":"…","depth":23,"bounds":{"left":0.5588431,"top":0.5019952,"width":0.0039893617,"height":0.014365523},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":22,"bounds":{"left":0.54787236,"top":0.5291301,"width":0.026595745,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.5291301,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":12,"bounds":{"left":0.55086434,"top":0.5291301,"width":0.023271276,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.54588985,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Replied","depth":22,"bounds":{"left":0.58477396,"top":0.53152436,"width":0.012965426,"height":0.011971269},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.58477396,"top":0.5323224,"width":0.0023271276,"height":0.011971269}},{"char_start":1,"char_count":6,"bounds":{"left":0.58710104,"top":0.5323224,"width":0.010638298,"height":0.011971269}}],"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.53152436,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.53152436,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.53152436,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"добреее, значи трябва да има процес, който чете от redis и налива в Elastic Search","depth":23,"bounds":{"left":0.53324467,"top":0.5642458,"width":0.08610372,"height":0.049481247},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.5642458,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":82,"bounds":{"left":0.53324467,"top":0.5642458,"width":0.08610372,"height":0.031923383}}],"role_description":"text"},{"role":"AXStaticText","text":"Review Toast","depth":22,"bounds":{"left":0.54787236,"top":0.62649643,"width":0.028590426,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.62649643,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.55086434,"top":0.62649643,"width":0.025598405,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"App","depth":22,"bounds":{"left":0.54787236,"top":0.6432562,"width":0.007978723,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.6432562,"width":0.0029920214,"height":0.012769354}},{"char_start":1,"char_count":2,"bounds":{"left":0.55086434,"top":0.6432562,"width":0.004986702,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.62889063,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.62889063,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.62889063,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR","depth":23,"bounds":{"left":0.53324467,"top":0.66161215,"width":0.07480053,"height":0.031923383},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.66161215,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":63,"bounds":{"left":0.53324467,"top":0.66161215,"width":0.07480053,"height":0.031923383}}],"role_description":"text"},{"role":"AXStaticText","text":"Nikolay Ivanov","depth":22,"bounds":{"left":0.54787236,"top":0.7238627,"width":0.032247342,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.7238627,"width":0.0039893617,"height":0.014365523}},{"char_start":1,"char_count":13,"bounds":{"left":0.5518617,"top":0.7238627,"width":0.027925532,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.7406225,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.72625697,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.72625697,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.72625697,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"ще станат конфликти","depth":23,"bounds":{"left":0.53324467,"top":0.7589784,"width":0.050199468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.7589784,"width":0.0043218085,"height":0.014365523}},{"char_start":1,"char_count":18,"bounds":{"left":0.5375665,"top":0.7589784,"width":0.045545213,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"James Graham","depth":22,"bounds":{"left":0.54787236,"top":0.8036712,"width":0.031914894,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.8036712,"width":0.0019946808,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.54986703,"top":0.8036712,"width":0.029920213,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.820431,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Yesterday","depth":22,"bounds":{"left":0.60172874,"top":0.80606544,"width":0.018284574,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.60172874,"top":0.80606544,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":8,"bounds":{"left":0.6037234,"top":0.80606544,"width":0.01662234,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"Cheers!","depth":23,"bounds":{"left":0.53324467,"top":0.8387869,"width":0.016954787,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.8387869,"width":0.0033244682,"height":0.014365523}},{"char_start":1,"char_count":6,"bounds":{"left":0.5365692,"top":0.8387869,"width":0.013297873,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Tuesday, May 12th","depth":21,"bounds":{"left":0.55851066,"top":0.8922586,"width":0.036236703,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.55851066,"top":0.8930567,"width":0.0023271276,"height":0.012769354}},{"char_start":1,"char_count":16,"bounds":{"left":0.56083775,"top":0.8930567,"width":0.033909574,"height":0.012769354}}],"role_description":"text"},{"role":"AXStaticText","text":"Stoyan Tanev","depth":22,"bounds":{"left":0.54787236,"top":0.9377494,"width":0.028922873,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.54787236,"top":0.9377494,"width":0.0026595744,"height":0.014365523}},{"char_start":1,"char_count":11,"bounds":{"left":0.5505319,"top":0.9377494,"width":0.026263298,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.9545092,"width":0.00731383,"height":0.012769354},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Replied","depth":22,"bounds":{"left":0.58776593,"top":0.94014364,"width":0.012965426,"height":0.011971269},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.58776593,"top":0.94094175,"width":0.0023271276,"height":0.011971269}},{"char_start":1,"char_count":6,"bounds":{"left":0.5900931,"top":0.94094175,"width":0.010638298,"height":0.011971269}}],"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.94014364,"width":0.015292553,"height":0.012769354},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.6047208,"top":0.94014364,"width":0.0023271276,"height":0.013567438}},{"char_start":1,"char_count":6,"bounds":{"left":0.60671544,"top":0.94014364,"width":0.013630319,"height":0.013567438}}],"role_description":"text"},{"role":"AXStaticText","text":"сега всичко е 6","depth":23,"bounds":{"left":0.53324467,"top":0.9728651,"width":0.034574468,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.53324467,"top":0.9728651,"width":0.0023271276,"height":0.014365523}},{"char_start":1,"char_count":14,"bounds":{"left":0.5355718,"top":0.9728651,"width":0.032247342,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Vasil Vasilev","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.026595745,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Reacted in","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.019946808,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"platform-inner-team","depth":22,"bounds":{"left":0.56981385,"top":0.9952115,"width":0.027260639,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"You:","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.009640957,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"може ли един approve","depth":23,"bounds":{"left":0.54388297,"top":0.9952115,"width":0.05285904,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXLink","text":"https://github.com/jiminny/app/pull/12024","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.08676862,"height":0.0007980846},"on_screen":true,"role_description":"link","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"https://github.com/jiminny/app/pull/12024","depth":24,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.08676862,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"1 reaction, react with white check mark emoji","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.014295213,"height":0.0007980846},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"1","depth":24,"bounds":{"left":0.5425532,"top":0.9952115,"width":0.0023271276,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.03523936,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"И другата седмица имаме презднтации пред борда в Лондон и съм до никъде","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.08610372,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Galya Dimitrova","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.03523936,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Reacted in","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.019946808,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.56848407,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"You:","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.009640957,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ако трябва да се пипне и в кода ще си направя тикет","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.08510638,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"1 reaction, react with +1 emoji","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.014295213,"height":0.0007980846},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"1","depth":24,"bounds":{"left":0.5425532,"top":0.9952115,"width":0.0023271276,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.038231384,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ще го видя","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.025265958,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Steliyan Georgiev","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.038231384,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Reacted in","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.019946808,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.56848407,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"You:","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.009640957,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"ето го и репорт","depth":23,"bounds":{"left":0.54388297,"top":0.9952115,"width":0.03557181,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"…","depth":23,"bounds":{"left":0.5794548,"top":0.9952115,"width":0.0039893617,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXCheckBox","text":"1 reaction, react with +1 emoji","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.014295213,"height":0.0007980846},"on_screen":true,"role_description":"toggle button","subrole":"AXToggleButton","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"1","depth":24,"bounds":{"left":0.5425532,"top":0.9952115,"width":0.0023271276,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Petko Kashinski","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.034574468,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"DM","depth":22,"bounds":{"left":0.54787236,"top":0.9952115,"width":0.00731383,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Tuesday","depth":22,"bounds":{"left":0.6047208,"top":0.9952115,"width":0.015292553,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Huddle ?","depth":23,"bounds":{"left":0.53324467,"top":0.9952115,"width":0.019614361,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Select a notification to view the details.","depth":17,"bounds":{"left":0.7712766,"top":0.5171588,"width":0.08577128,"height":0.014365523},"on_screen":true,"lines":[{"char_start":0,"char_count":1,"bounds":{"left":0.7712766,"top":0.5171588,"width":0.0029920214,"height":0.014365523}},{"char_start":1,"char_count":41,"bounds":{"left":0.77393615,"top":0.5171588,"width":0.08344415,"height":0.014365523}}],"role_description":"text"},{"role":"AXStaticText","text":"Processing uploaded file… complete! Message ready to be sent.","depth":11,"bounds":{"left":0.5,"top":0.9992019,"width":0.022938829,"height":0.0007980846},"on_screen":true,"role_description":"text"},{"role":"AXStaticText","text":"Channel","depth":11,"bounds":{"left":0.5,"top":0.9992019,"width":0.01761968,"height":0.0007980846},"on_screen":true,"role_description":"text"}]...
|
8367143638802948576
|
-5949560164595188541
|
visual_change
|
hybrid
|
NULL
|
Switch workspaces… (Jiminny Inc) Has new messages
Switch workspaces… (Jiminny Inc) Has new messages
Home
Home
DMs
DMs
Activity
Activity
Files
Files
Later
Later
More…
More
All, 4 unread
DMs
Add new tab
Stefka Stoyanova
DM
Mark as unread
Clear
More actions
здарсти Лукаш, ще направиш ли стори да ъпгрейднем Pipedrive SDK (ако може да напишеш от коя на коя версия)
…
Yesterday
Mario Georgiev
DM
Yesterday
тенк ю вери мъч, махнах му crm seat-a и има достъп, ще го имам напредвид вече че явно бие такава грешка когато фрии акаунта expir-ne или нещо подобно и няма особен workaround
Jira Cloud
App
Yesterday
@Stefka Stoyanova
@Stefka Stoyanova
assigned a Technical Story from you ⟶ Unassigned
…
Vasil Vasilev
DM
Replied
Yesterday
добреее, значи трябва да има процес, който чете от redis и налива в Elastic Search
Review Toast
App
Yesterday
PR review requested by @stefka-jiminny on @nikolaybiaivanov's PR
Nikolay Ivanov
DM
Yesterday
ще станат конфликти
James Graham
DM
Yesterday
Cheers!
Tuesday, May 12th
Stoyan Tanev
DM
Replied
Tuesday
сега всичко е 6
Vasil Vasilev
Reacted in
platform-inner-team
Tuesday
You:
може ли един approve
https://github.com/jiminny/app/pull/12024
https://github.com/jiminny/app/pull/12024
1 reaction, react with white check mark emoji
1
Galya Dimitrova
DM
Tuesday
И другата седмица имаме презднтации пред борда в Лондон и съм до никъде
Galya Dimitrova
Reacted in
DM
Tuesday
You:
ако трябва да се пипне и в кода ще си направя тикет
1 reaction, react with +1 emoji
1
Steliyan Georgiev
DM
Tuesday
ще го видя
Steliyan Georgiev
Reacted in
DM
Tuesday
You:
ето го и репорт
…
1 reaction, react with +1 emoji
1
Petko Kashinski
DM
Tuesday
Huddle ?
Select a notification to view the details.
Processing uploaded file… complete! Message ready to be sent.
Channel
SlackScreenpipe - ArchiveAll docs • AFFiNE)) DXP4800PLUS-B5F8©Screenpipe - Archive(*SQLite Web: archive.db( SQLite Web: db.salite→ Claude% Manage extra usage for paicG 2 TB in 25 MB/s - Gooale Se- New TabVIewmistoryWindowHelpdop.screenolpe.lakylak.xyz• Goocle GeminiGeminiGShow thinkingThat is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even thesecondarv ssu-onlv beelink Nas It vou ena uo oulloino iu will keeo vour local ssu lean whilekeepina vour database searchableAs for setting up languages for transcription, yes, you can configure it, but it helps tounderstand how ScreenPipe handles language natively first.How the Transcription Engine Handles Languageby derault, screenripe uses a multilingual whisper model and sets the language contigurationTO AuTO-DerectWhen a new audio chunk comes in, the model listens to the first few seconds of audio, quessesthe language, and transcribes the rest of that chunk using that assumption.• The Advantage: If vou are watchina a tutorial in Enalish. and then an hour later vou are in aZoom call speakina Bulaarian. ScreenPipe will automatically switch gears without vouhaving to touch the settinas.• The Drawback: Auto-detect can sometimes guess wrong, especially it there is heavybackground noise, it someone starts a sentence with a foreign loanword, or it you arerapidly code-switching between Slovak and English in the same conversation. When itguesses wrong, it might try to torce Slovak words into English spelling, resulting inaloberish.How to Force a Soecific LanquadeIf vou want to ensure maximum accuracy and vou know vou will primarily be recordina in onelanquage for a specific period, vou can explicitly set the lanquage. This also sliahtly speeds upthe processina because the model skips the detection phase.If vou are usina the Deskton Aon Ul:1. Open the ScreenPipe settinasAck CeminiS0 hhlDaily - Platform • in 19 m100% CThu 14 May 9:26:17@ Describe what you are looking forScreenpipe (archive.db • 2071.1MBXeaVneVSearchWork Repor09 : 45HomeDMSActivits12 Mav 10:15. Finder /Petko KashinskiPro VGemini is Aland can make mictakes includina about neonle Your nrivacv and GeminSummarize pageB +•* 30sierm? FirefoAC.MIVAll 4DMsStefka Stoyanovaзлаости / укаш. ше направиш листори ла ъпгрейлнем Pidedrive SDK.IYesterdayMario GeorgievYesterday2 DMтенк ю вери мъч, махнах му crm seat-аиима достьл, ще го имам ...Jira CloudYesterday@Stefka Stoyanova assigned aTechnical Story from you →HO DMVasil VasilevReplied Yesterdayлоблеве значи тпябва ла има.ппошес който чете от redis и налив .Review ToastiYesterdayPR review requested by @stefka-liminnv on @nikolavhiaivanov's PRNikolav IvanovVecterdavще станат коноликти.S omeames GrahamVoctordavCheerçiTuesdav. Mav 12thCtavan Thnayao oMcors oeuuvA ALReplied TuesdaySelect a notification to view the details...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38671
|
1439
|
4
|
2026-05-14T06:26:21.124015+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739981124_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · Finder / .screenpipe
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.056664005,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.09417398,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.0981644,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.0981644,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.13407822,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"bounds":{"left":0.5021609,"top":0.13407822,"width":0.005319149,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"bounds":{"left":0.5147939,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.5206117,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"bounds":{"left":0.52393615,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"bounds":{"left":0.5440492,"top":0.1300878,"width":0.027593086,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"bounds":{"left":0.5749667,"top":0.1300878,"width":0.016788565,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"bounds":{"left":0.45761302,"top":0.1895451,"width":0.10571808,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"bounds":{"left":0.813996,"top":0.18515563,"width":0.009807181,"height":0.018754989},"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"bounds":{"left":0.82795876,"top":0.18914606,"width":0.004155585,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"bounds":{"left":0.83643615,"top":0.18515563,"width":0.009640957,"height":0.018754989},"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"bounds":{"left":0.8494016,"top":0.18914606,"width":0.004654255,"height":0.011173184},"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"bounds":{"left":0.85538566,"top":0.18914606,"width":0.011136968,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"bounds":{"left":0.45910904,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"bounds":{"left":0.47573137,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"bounds":{"left":0.4921875,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"bounds":{"left":0.50880986,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"bounds":{"left":0.52526593,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"bounds":{"left":0.5415558,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"bounds":{"left":0.55801195,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"bounds":{"left":0.57430184,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"bounds":{"left":0.59075797,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"bounds":{"left":0.6072141,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"bounds":{"left":0.6236702,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"bounds":{"left":0.64012635,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"bounds":{"left":0.6565825,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"bounds":{"left":0.67303854,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"bounds":{"left":0.68949467,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"bounds":{"left":0.7059508,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"bounds":{"left":0.7224069,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"bounds":{"left":0.7386968,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"bounds":{"left":0.75515294,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"bounds":{"left":0.77160907,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"bounds":{"left":0.78806514,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"bounds":{"left":0.804355,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"bounds":{"left":0.82081115,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"bounds":{"left":0.8374335,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"bounds":{"left":0.85388964,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · Finder / .screenpipe","depth":10,"bounds":{"left":0.45628324,"top":0.31883478,"width":0.06482713,"height":0.011971269},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.45694813,"top":0.94094175,"width":0.023936171,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.48354387,"top":0.9413408,"width":0.02244016,"height":0.023942538},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.5086436,"top":0.94094175,"width":0.027925532,"height":0.02434158},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.53922874,"top":0.9413408,"width":0.022273935,"height":0.023942538},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.56416225,"top":0.94094175,"width":0.024102394,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.61486036,"top":0.943336,"width":0.04870346,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:15","depth":10,"bounds":{"left":0.8580452,"top":0.9477255,"width":0.009142287,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.45761302,"top":0.98324025,"width":0.011801862,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.47772607,"top":0.98324025,"width":0.011801862,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.4978391,"top":0.98324025,"width":0.009474734,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.515625,"top":0.98324025,"width":0.02144282,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.545379,"top":0.98324025,"width":0.017287234,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.5709774,"top":0.98324025,"width":0.010970744,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.5902593,"top":0.98324025,"width":0.03025266,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.62882316,"top":0.98324025,"width":0.010472074,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.6476064,"top":0.98324025,"width":0.017453458,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.673371,"top":0.98324025,"width":0.013630319,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.6953125,"top":0.98324025,"width":0.025598405,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.72922206,"top":0.98324025,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":0.7496675,"top":0.98324025,"width":0.00930851,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":0.76728725,"top":0.98324025,"width":0.027426861,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"bounds":{"left":0.80302525,"top":0.98324025,"width":0.015791224,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"bounds":{"left":0.82712764,"top":0.98324025,"width":0.012965426,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"bounds":{"left":0.8484042,"top":0.98324025,"width":0.0068151597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"bounds":{"left":0.8635306,"top":0.98324025,"width":0.0071476065,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
3720194340268485401
|
8637114893386525653
|
visual_change
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · Finder / .screenpipe
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38673
|
1439
|
5
|
2026-05-14T06:26:30.218544+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739990218_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false}]...
|
5799034816774620835
|
8632611152042027997
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini...
|
38671
|
NULL
|
NULL
|
NULL
|
|
38672
|
1437
|
2
|
2026-05-14T06:26:30.230344+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739990230_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-4742960000478597602
|
8632611152016845789
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38674
|
1437
|
3
|
2026-05-14T06:26:31.357070+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739991357_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
4863947415272186562
|
8632611152025234397
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor...
|
38672
|
NULL
|
NULL
|
NULL
|
|
38675
|
1439
|
6
|
2026-05-14T06:26:31.359426+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739991359_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
2104907568730886079
|
8632611152025234397
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38676
|
1437
|
4
|
2026-05-14T06:26:32.019725+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739992019_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
3911498094355917053
|
8632611152025234397
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38677
|
1439
|
7
|
2026-05-14T06:26:32.022014+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739992022_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.056664005,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.09417398,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.0981644,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.0981644,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.13407822,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-3637532402420667954
|
8632611152025234397
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45...
|
38675
|
NULL
|
NULL
|
NULL
|
|
38678
|
1437
|
5
|
2026-05-14T06:26:32.535432+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739992535_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · PhpStorm","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.38993055,"top":0.0,"width":0.05,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.4454861,"top":0.0,"width":0.046875,"height":0.033333335},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.49791667,"top":0.0,"width":0.058333334,"height":0.033888888},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.56180555,"top":0.0,"width":0.046527777,"height":0.033333335},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":true,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.61388886,"top":0.0,"width":0.050347224,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.71979165,"top":0.0,"width":0.10173611,"height":0.027222222},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:15","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.39131945,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.43333334,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.47534722,"top":0.0,"width":0.019791666,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.5125,"top":0.0,"width":0.044791665,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.5746528,"top":0.0,"width":0.036111113,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.628125,"top":0.0,"width":0.022916667,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.6684028,"top":0.0,"width":0.063194446,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.74895835,"top":0.0,"width":0.021875,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.7881944,"top":0.0,"width":0.036458332,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.8420139,"top":0.0,"width":0.028472222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.88784724,"top":0.0,"width":0.05347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.95868057,"top":0.0,"width":0.025347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.0013889074,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.038194418,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
1032570310279506603
|
8637114889091558357
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
38676
|
NULL
|
NULL
|
NULL
|
|
38679
|
1439
|
8
|
2026-05-14T06:26:32.711955+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739992711_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.056664005,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.09417398,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.0981644,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.0981644,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.13407822,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"bounds":{"left":0.5021609,"top":0.13407822,"width":0.005319149,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"bounds":{"left":0.5147939,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.5206117,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"bounds":{"left":0.52393615,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"bounds":{"left":0.5440492,"top":0.1300878,"width":0.027593086,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"bounds":{"left":0.5749667,"top":0.1300878,"width":0.016788565,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"bounds":{"left":0.45761302,"top":0.1895451,"width":0.10571808,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"bounds":{"left":0.813996,"top":0.18515563,"width":0.009807181,"height":0.018754989},"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"bounds":{"left":0.82795876,"top":0.18914606,"width":0.004155585,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"bounds":{"left":0.83643615,"top":0.18515563,"width":0.009640957,"height":0.018754989},"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"bounds":{"left":0.8494016,"top":0.18914606,"width":0.004654255,"height":0.011173184},"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"bounds":{"left":0.85538566,"top":0.18914606,"width":0.011136968,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"bounds":{"left":0.45910904,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"bounds":{"left":0.47573137,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"bounds":{"left":0.4921875,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"bounds":{"left":0.50880986,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"bounds":{"left":0.52526593,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"bounds":{"left":0.5415558,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"bounds":{"left":0.55801195,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"bounds":{"left":0.57430184,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"bounds":{"left":0.59075797,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"bounds":{"left":0.6072141,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"bounds":{"left":0.6236702,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"bounds":{"left":0.64012635,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"bounds":{"left":0.6565825,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"bounds":{"left":0.67303854,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"bounds":{"left":0.68949467,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"bounds":{"left":0.7059508,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"bounds":{"left":0.7224069,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"bounds":{"left":0.7386968,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"bounds":{"left":0.75515294,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"bounds":{"left":0.77160907,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"bounds":{"left":0.78806514,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"bounds":{"left":0.804355,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"bounds":{"left":0.82081115,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"bounds":{"left":0.8374335,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"bounds":{"left":0.85388964,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · PhpStorm","depth":10,"bounds":{"left":0.45628324,"top":0.31883478,"width":0.046210106,"height":0.011971269},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.45694813,"top":0.94094175,"width":0.023936171,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.48354387,"top":0.9413408,"width":0.02244016,"height":0.023942538},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.5086436,"top":0.94094175,"width":0.027925532,"height":0.02434158},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.53922874,"top":0.9413408,"width":0.022273935,"height":0.023942538},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":true,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.56416225,"top":0.94094175,"width":0.024102394,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.61486036,"top":0.943336,"width":0.04870346,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:15","depth":10,"bounds":{"left":0.8580452,"top":0.9477255,"width":0.009142287,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.45761302,"top":0.98324025,"width":0.011801862,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.47772607,"top":0.98324025,"width":0.011801862,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.4978391,"top":0.98324025,"width":0.009474734,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.515625,"top":0.98324025,"width":0.02144282,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.545379,"top":0.98324025,"width":0.017287234,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.5709774,"top":0.98324025,"width":0.010970744,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.5902593,"top":0.98324025,"width":0.03025266,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.62882316,"top":0.98324025,"width":0.010472074,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.6476064,"top":0.98324025,"width":0.017453458,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.673371,"top":0.98324025,"width":0.013630319,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.6953125,"top":0.98324025,"width":0.025598405,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.72922206,"top":0.98324025,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":0.7496675,"top":0.98324025,"width":0.00930851,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":0.76728725,"top":0.98324025,"width":0.027426861,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"bounds":{"left":0.80302525,"top":0.98324025,"width":0.015791224,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"bounds":{"left":0.82712764,"top":0.98324025,"width":0.012965426,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"bounds":{"left":0.8484042,"top":0.98324025,"width":0.0068151597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"bounds":{"left":0.8635306,"top":0.98324025,"width":0.0071476065,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
1032570310279506603
|
8637114889091558357
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38680
|
1437
|
6
|
2026-05-14T06:26:33.093809+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739993093_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-4742960000478597602
|
8632611152016845789
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38681
|
1439
|
9
|
2026-05-14T06:26:33.274945+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739993274_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.056664005,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.09417398,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.0981644,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.0981644,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.13407822,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"bounds":{"left":0.5021609,"top":0.13407822,"width":0.005319149,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"bounds":{"left":0.5147939,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.5206117,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"bounds":{"left":0.52393615,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"bounds":{"left":0.5440492,"top":0.1300878,"width":0.027593086,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"bounds":{"left":0.5749667,"top":0.1300878,"width":0.016788565,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"bounds":{"left":0.45761302,"top":0.1895451,"width":0.10571808,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"bounds":{"left":0.813996,"top":0.18515563,"width":0.009807181,"height":0.018754989},"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"bounds":{"left":0.82795876,"top":0.18914606,"width":0.004155585,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"bounds":{"left":0.83643615,"top":0.18515563,"width":0.009640957,"height":0.018754989},"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"bounds":{"left":0.8494016,"top":0.18914606,"width":0.004654255,"height":0.011173184},"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"bounds":{"left":0.85538566,"top":0.18914606,"width":0.011136968,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"bounds":{"left":0.45910904,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"bounds":{"left":0.47573137,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"bounds":{"left":0.4921875,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"bounds":{"left":0.50880986,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"bounds":{"left":0.52526593,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"bounds":{"left":0.5415558,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"bounds":{"left":0.55801195,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"bounds":{"left":0.57430184,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"bounds":{"left":0.59075797,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"bounds":{"left":0.6072141,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"bounds":{"left":0.6236702,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"bounds":{"left":0.64012635,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"bounds":{"left":0.6565825,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"bounds":{"left":0.67303854,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"bounds":{"left":0.68949467,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"bounds":{"left":0.7059508,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"bounds":{"left":0.7224069,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"bounds":{"left":0.7386968,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"bounds":{"left":0.75515294,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"bounds":{"left":0.77160907,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"bounds":{"left":0.78806514,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"bounds":{"left":0.804355,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"bounds":{"left":0.82081115,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"bounds":{"left":0.8374335,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"bounds":{"left":0.85388964,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · PhpStorm","depth":10,"bounds":{"left":0.45628324,"top":0.31883478,"width":0.046210106,"height":0.011971269},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.45694813,"top":0.94094175,"width":0.023936171,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.48354387,"top":0.9413408,"width":0.02244016,"height":0.023942538},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.5086436,"top":0.94094175,"width":0.027925532,"height":0.02434158},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.53922874,"top":0.9413408,"width":0.022273935,"height":0.023942538},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":true,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.56416225,"top":0.94094175,"width":0.024102394,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.61486036,"top":0.943336,"width":0.04870346,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:15","depth":10,"bounds":{"left":0.8580452,"top":0.9477255,"width":0.009142287,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
4379175045512496875
|
8632611289464187869
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15...
|
38679
|
NULL
|
NULL
|
NULL
|
|
38682
|
1437
|
7
|
2026-05-14T06:26:33.713279+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739993713_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · PhpStorm","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.38993055,"top":0.0,"width":0.05,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.4454861,"top":0.0,"width":0.046875,"height":0.033333335},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.49791667,"top":0.0,"width":0.058333334,"height":0.033888888},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.56180555,"top":0.0,"width":0.046527777,"height":0.033333335},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":true,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.61388886,"top":0.0,"width":0.050347224,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.71979165,"top":0.0,"width":0.10173611,"height":0.027222222},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:15","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.39131945,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.43333334,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.47534722,"top":0.0,"width":0.019791666,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.5125,"top":0.0,"width":0.044791665,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.5746528,"top":0.0,"width":0.036111113,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.628125,"top":0.0,"width":0.022916667,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.6684028,"top":0.0,"width":0.063194446,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.74895835,"top":0.0,"width":0.021875,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.7881944,"top":0.0,"width":0.036458332,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.8420139,"top":0.0,"width":0.028472222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.88784724,"top":0.0,"width":0.05347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.95868057,"top":0.0,"width":0.025347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.0013889074,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.038194418,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
1032570310279506603
|
8637114889091558357
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
38680
|
NULL
|
NULL
|
NULL
|
|
38683
|
1439
|
10
|
2026-05-14T06:26:33.839608+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739993839_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.056664005,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.09417398,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.0981644,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.0981644,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.13407822,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"bounds":{"left":0.5021609,"top":0.13407822,"width":0.005319149,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"bounds":{"left":0.5147939,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.5206117,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"bounds":{"left":0.52393615,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"bounds":{"left":0.5440492,"top":0.1300878,"width":0.027593086,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"bounds":{"left":0.5749667,"top":0.1300878,"width":0.016788565,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"bounds":{"left":0.45761302,"top":0.1895451,"width":0.10571808,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"bounds":{"left":0.813996,"top":0.18515563,"width":0.009807181,"height":0.018754989},"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"bounds":{"left":0.82795876,"top":0.18914606,"width":0.004155585,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"bounds":{"left":0.83643615,"top":0.18515563,"width":0.009640957,"height":0.018754989},"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"bounds":{"left":0.8494016,"top":0.18914606,"width":0.004654255,"height":0.011173184},"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"bounds":{"left":0.85538566,"top":0.18914606,"width":0.011136968,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"bounds":{"left":0.45910904,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"bounds":{"left":0.47573137,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"bounds":{"left":0.4921875,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"bounds":{"left":0.50880986,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"bounds":{"left":0.52526593,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"bounds":{"left":0.5415558,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"bounds":{"left":0.55801195,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"bounds":{"left":0.57430184,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"bounds":{"left":0.59075797,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"bounds":{"left":0.6072141,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"bounds":{"left":0.6236702,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"bounds":{"left":0.64012635,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"bounds":{"left":0.6565825,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"bounds":{"left":0.67303854,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"bounds":{"left":0.68949467,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"bounds":{"left":0.7059508,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"bounds":{"left":0.7224069,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"bounds":{"left":0.7386968,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"bounds":{"left":0.75515294,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"bounds":{"left":0.77160907,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"bounds":{"left":0.78806514,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"bounds":{"left":0.804355,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"bounds":{"left":0.82081115,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"bounds":{"left":0.8374335,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"bounds":{"left":0.85388964,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · PhpStorm","depth":10,"bounds":{"left":0.45628324,"top":0.31883478,"width":0.046210106,"height":0.011971269},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.45694813,"top":0.94094175,"width":0.023936171,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.48354387,"top":0.9413408,"width":0.02244016,"height":0.023942538},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.5086436,"top":0.94094175,"width":0.027925532,"height":0.02434158},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.53922874,"top":0.9413408,"width":0.022273935,"height":0.023942538},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":true,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.56416225,"top":0.94094175,"width":0.024102394,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false}]...
|
-7967358063450908527
|
8637114889091558365
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38684
|
1437
|
8
|
2026-05-14T06:26:34.385260+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739994385_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-4742960000478597602
|
8632611152016845789
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38685
|
1439
|
11
|
2026-05-14T06:26:34.392556+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739994392_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false}]...
|
-818381692646404447
|
8632611152025234397
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search...
|
38683
|
NULL
|
NULL
|
NULL
|
|
38686
|
1437
|
9
|
2026-05-14T06:26:34.891735+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739994891_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · PhpStorm","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.38993055,"top":0.0,"width":0.05,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.4454861,"top":0.0,"width":0.046875,"height":0.033333335},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.49791667,"top":0.0,"width":0.058333334,"height":0.033888888},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.56180555,"top":0.0,"width":0.046527777,"height":0.033333335},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":true,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.61388886,"top":0.0,"width":0.050347224,"height":0.033888888},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.71979165,"top":0.0,"width":0.10173611,"height":0.027222222},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:15","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.39131945,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.43333334,"top":0.0,"width":0.024652777,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.47534722,"top":0.0,"width":0.019791666,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.5125,"top":0.0,"width":0.044791665,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.5746528,"top":0.0,"width":0.036111113,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.628125,"top":0.0,"width":0.022916667,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.6684028,"top":0.0,"width":0.063194446,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.74895835,"top":0.0,"width":0.021875,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.7881944,"top":0.0,"width":0.036458332,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.8420139,"top":0.0,"width":0.028472222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.88784724,"top":0.0,"width":0.05347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.95868057,"top":0.0,"width":0.025347222,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.0013889074,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":1.0,"top":0.0,"width":-0.038194418,"height":0.015},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
1032570310279506603
|
8637114889091558357
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
38684
|
NULL
|
NULL
|
NULL
|
|
38687
|
1439
|
12
|
2026-05-14T06:26:35.106730+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739995106_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"bounds":{"left":0.97390294,"top":0.06464485,"width":0.009474734,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"bounds":{"left":0.9847075,"top":0.0650439,"width":0.0051529254,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"bounds":{"left":0.45262632,"top":0.060654428,"width":0.013464096,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"bounds":{"left":0.8111702,"top":0.060654428,"width":0.01412899,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.8312833,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"bounds":{"left":0.83710104,"top":0.060255386,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"bounds":{"left":0.84042555,"top":0.060255386,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"bounds":{"left":0.85920876,"top":0.056664005,"width":0.012300532,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"bounds":{"left":0.45561835,"top":0.09417398,"width":0.41289893,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"bounds":{"left":0.642121,"top":0.0981644,"width":0.036070477,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"bounds":{"left":0.67918885,"top":0.0981644,"width":0.0028257978,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"bounds":{"left":0.45561835,"top":0.13407822,"width":0.009973404,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"bounds":{"left":0.47290558,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.4787234,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"bounds":{"left":0.4820479,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"bounds":{"left":0.5021609,"top":0.13407822,"width":0.005319149,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"bounds":{"left":0.5147939,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"bounds":{"left":0.5206117,"top":0.13367917,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"bounds":{"left":0.52393615,"top":0.13367917,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"bounds":{"left":0.5440492,"top":0.1300878,"width":0.027593086,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"bounds":{"left":0.5749667,"top":0.1300878,"width":0.016788565,"height":0.018754989},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"bounds":{"left":0.45761302,"top":0.1895451,"width":0.10571808,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"bounds":{"left":0.813996,"top":0.18515563,"width":0.009807181,"height":0.018754989},"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"bounds":{"left":0.82795876,"top":0.18914606,"width":0.004155585,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"bounds":{"left":0.83643615,"top":0.18515563,"width":0.009640957,"height":0.018754989},"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"bounds":{"left":0.8494016,"top":0.18914606,"width":0.004654255,"height":0.011173184},"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"bounds":{"left":0.85538566,"top":0.18914606,"width":0.011136968,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09:30","depth":13,"bounds":{"left":0.45910904,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:00","depth":13,"bounds":{"left":0.47573137,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10:30","depth":13,"bounds":{"left":0.4921875,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:00","depth":13,"bounds":{"left":0.50880986,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"11:30","depth":13,"bounds":{"left":0.52526593,"top":0.2753392,"width":0.0078125,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:00","depth":13,"bounds":{"left":0.5415558,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12:30","depth":13,"bounds":{"left":0.55801195,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:00","depth":13,"bounds":{"left":0.57430184,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"13:30","depth":13,"bounds":{"left":0.59075797,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:00","depth":13,"bounds":{"left":0.6072141,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"14:30","depth":13,"bounds":{"left":0.6236702,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:00","depth":13,"bounds":{"left":0.64012635,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"15:30","depth":13,"bounds":{"left":0.6565825,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:00","depth":13,"bounds":{"left":0.67303854,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"16:30","depth":13,"bounds":{"left":0.68949467,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:00","depth":13,"bounds":{"left":0.7059508,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"17:30","depth":13,"bounds":{"left":0.7224069,"top":0.2753392,"width":0.007978723,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:00","depth":13,"bounds":{"left":0.7386968,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"18:30","depth":13,"bounds":{"left":0.75515294,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:00","depth":13,"bounds":{"left":0.77160907,"top":0.2753392,"width":0.00831117,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"19:30","depth":13,"bounds":{"left":0.78806514,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:00","depth":13,"bounds":{"left":0.804355,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"20:30","depth":13,"bounds":{"left":0.82081115,"top":0.2753392,"width":0.008643617,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:00","depth":13,"bounds":{"left":0.8374335,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"21:30","depth":13,"bounds":{"left":0.85388964,"top":0.2753392,"width":0.008144947,"height":0.008778931},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12 May 10:15 · PhpStorm","depth":10,"bounds":{"left":0.45628324,"top":0.31883478,"width":0.046210106,"height":0.011971269},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"⏮ 30s","depth":9,"bounds":{"left":0.45694813,"top":0.94094175,"width":0.023936171,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"◀ 10s","depth":9,"bounds":{"left":0.48354387,"top":0.9413408,"width":0.02244016,"height":0.023942538},"on_screen":true,"help_text":"←","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"⏸ Pause","depth":9,"bounds":{"left":0.5086436,"top":0.94094175,"width":0.027925532,"height":0.02434158},"on_screen":true,"help_text":"Space","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"10s ▶","depth":9,"bounds":{"left":0.53922874,"top":0.9413408,"width":0.022273935,"height":0.023942538},"on_screen":true,"help_text":"→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":true,"is_selected":false},{"role":"AXButton","text":"30s ⏭","depth":9,"bounds":{"left":0.56416225,"top":0.94094175,"width":0.024102394,"height":0.02434158},"on_screen":true,"help_text":"Ctrl+→","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"🔊 Auto-Play Audio: ON","depth":9,"bounds":{"left":0.61486036,"top":0.943336,"width":0.04870346,"height":0.019553073},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"10:15","depth":10,"bounds":{"left":0.8580452,"top":0.9477255,"width":0.009142287,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"iTerm2","depth":9,"bounds":{"left":0.45761302,"top":0.98324025,"width":0.011801862,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Firefox","depth":9,"bounds":{"left":0.47772607,"top":0.98324025,"width":0.011801862,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Slack","depth":9,"bounds":{"left":0.4978391,"top":0.98324025,"width":0.009474734,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"CleanShot X","depth":9,"bounds":{"left":0.515625,"top":0.98324025,"width":0.02144282,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"PhpStorm","depth":9,"bounds":{"left":0.545379,"top":0.98324025,"width":0.017287234,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finder","depth":9,"bounds":{"left":0.5709774,"top":0.98324025,"width":0.010970744,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"QuickTime Player","depth":9,"bounds":{"left":0.5902593,"top":0.98324025,"width":0.03025266,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Alfred","depth":9,"bounds":{"left":0.62882316,"top":0.98324025,"width":0.010472074,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"coreautha","depth":9,"bounds":{"left":0.6476064,"top":0.98324025,"width":0.017453458,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Raycast","depth":9,"bounds":{"left":0.673371,"top":0.98324025,"width":0.013630319,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Control Centre","depth":9,"bounds":{"left":0.6953125,"top":0.98324025,"width":0.025598405,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Claude","depth":9,"bounds":{"left":0.72922206,"top":0.98324025,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Code","depth":9,"bounds":{"left":0.7496675,"top":0.98324025,"width":0.00930851,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Activity Monitor","depth":9,"bounds":{"left":0.76728725,"top":0.98324025,"width":0.027426861,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Windsurf","depth":9,"bounds":{"left":0.80302525,"top":0.98324025,"width":0.015791224,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Anybox","depth":9,"bounds":{"left":0.82712764,"top":0.98324025,"width":0.012965426,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"MIC","depth":9,"bounds":{"left":0.8484042,"top":0.98324025,"width":0.0068151597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SYS","depth":9,"bounds":{"left":0.8635306,"top":0.98324025,"width":0.0071476065,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
1032570310279506603
|
8637114889091558357
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow
09:30
10:00
10:30
11:00
11:30
12:00
12:30
13:00
13:30
14:00
14:30
15:00
15:30
16:00
16:30
17:00
17:30
18:00
18:30
19:00
19:30
20:00
20:30
21:00
21:30
12 May 10:15 · PhpStorm
⏮ 30s
◀ 10s
⏸ Pause
10s ▶
30s ⏭
🔊 Auto-Play Audio: ON
10:15
iTerm2
Firefox
Slack
CleanShot X
PhpStorm
Finder
QuickTime Player
Alfred
coreautha
Raycast
Control Centre
Claude
Code
Activity Monitor
Windsurf
Anybox
MIC
SYS...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38688
|
1437
|
10
|
2026-05-14T06:26:35.481322+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739995481_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2026","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Calendar","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXStaticText","text":"Monitor","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Jump to","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"--","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Go","depth":8,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"📅 Time Range Filter ▼","depth":9,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"📅 Time Range Filter","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"▼","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"From:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"09","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"45","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"To:","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"10","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":":","depth":11,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"30","depth":12,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Apply Filter","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Clear","depth":10,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"−","depth":9,"on_screen":true,"help_text":"Zoom out","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"1×","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"+","depth":9,"on_screen":true,"help_text":"Zoom in","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"checkbox","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Follow","depth":10,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
1967162247208383570
|
8632611289464187869
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/
2026
Calendar
Monitor
Jump to
--
:
--
Go
📅 Time Range Filter ▼
📅 Time Range Filter
▼
From:
09
:
45
To:
10
:
30
Apply Filter
Clear
APP TIMELINE · CLICK TO PLAY · DRAG SCROLLBAR TO PAN
−
1×
+
Follow
Follow...
|
NULL
|
NULL
|
NULL
|
NULL
|
|
38689
|
1437
|
11
|
2026-05-14T06:26:36.450667+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739996450_m1.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_1
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.0,"top":0.0,"width":0.134375,"height":0.020555556},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false}]...
|
-2527110329049053212
|
8632612251536862173
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary...
|
38688
|
NULL
|
NULL
|
NULL
|
|
38690
|
1439
|
13
|
2026-05-14T06:26:36.455353+00:00
|
/Users/lukas/.screenpipe/data/data/2026-05-14/1778 /Users/lukas/.screenpipe/data/data/2026-05-14/1778739996455_m2.jpg...
|
Firefox
|
Screenpipe — Archive — Personal
|
1
|
app.screenpipe.lakylak.xyz
|
monitor_2
|
NULL
|
NULL
|
NULL
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/...
|
[{"role":"AXRadioButton","text [{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.0518755,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.06304868,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"All docs · AFFiNE","depth":4,"bounds":{"left":0.0,"top":0.08459697,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"All docs · AFFiNE","depth":5,"bounds":{"left":0.013297873,"top":0.09577015,"width":0.029587766,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"DXP4800PLUS-B5F8","depth":4,"bounds":{"left":0.0,"top":0.11731844,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"DXP4800PLUS-B5F8","depth":5,"bounds":{"left":0.013297873,"top":0.12849163,"width":0.036901597,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Screenpipe — Archive","depth":4,"bounds":{"left":0.0,"top":0.15003991,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":true},{"role":"AXStaticText","text":"Screenpipe — Archive","depth":5,"bounds":{"left":0.013297873,"top":0.16121309,"width":0.037898935,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Close tab","depth":5,"bounds":{"left":0.05651596,"top":0.15722266,"width":0.007978723,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXRadioButton","text":"SQLite Web: archive.db","depth":4,"bounds":{"left":0.0,"top":0.18276137,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: archive.db","depth":5,"bounds":{"left":0.013297873,"top":0.19393456,"width":0.040724736,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"SQLite Web: db.sqlite","depth":4,"bounds":{"left":0.0,"top":0.21548285,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"SQLite Web: db.sqlite","depth":5,"bounds":{"left":0.013297873,"top":0.22665602,"width":0.03756649,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Claude","depth":4,"bounds":{"left":0.0,"top":0.2482043,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Claude","depth":5,"bounds":{"left":0.013297873,"top":0.25937748,"width":0.012134309,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":4,"bounds":{"left":0.0,"top":0.28092578,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Manage extra usage for paid Claude plans | Claude Help Center","depth":5,"bounds":{"left":0.013297873,"top":0.29209897,"width":0.1100399,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXRadioButton","text":"2 TB in 25 MB/s - Google Search","depth":4,"bounds":{"left":0.0,"top":0.31364724,"width":0.06881649,"height":0.032721467},"on_screen":true,"help_text":"","role_description":"tab","subrole":"AXTabButton","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"2 TB in 25 MB/s - Google Search","depth":5,"bounds":{"left":0.013297873,"top":0.32482043,"width":0.05668218,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New Tab","depth":4,"bounds":{"left":0.0028257978,"top":0.34796488,"width":0.06333112,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Customize sidebar","depth":6,"bounds":{"left":0.0028257978,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Close Google Gemini (⌃X)","depth":6,"bounds":{"left":0.013796543,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open history (⇧⌘H)","depth":6,"bounds":{"left":0.024933511,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Open bookmarks (⌘B)","depth":6,"bounds":{"left":0.036070477,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bitwarden","depth":6,"bounds":{"left":0.04720745,"top":0.97007185,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Chat settings","depth":7,"bounds":{"left":0.29321808,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Close","depth":7,"bounds":{"left":0.30518618,"top":0.055067837,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Google Account: Lukáš Koválik (kovaliklukas@gmail.com)","depth":12,"bounds":{"left":0.3025266,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Main menu","depth":12,"bounds":{"left":0.07280585,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.08610372,"top":0.10454908,"width":0.028590426,"height":0.030327214},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini","depth":15,"bounds":{"left":0.0887633,"top":0.10973663,"width":0.021941489,"height":0.020351157},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"New chat","depth":12,"bounds":{"left":0.2613032,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share conversation","depth":11,"bounds":{"left":0.27460107,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Open menu for conversation actions.","depth":12,"bounds":{"left":0.28789893,"top":0.103751,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXHeading","text":"Conversation with Gemini","depth":15,"bounds":{"left":0.068484046,"top":0.14764565,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Conversation with Gemini","depth":16,"bounds":{"left":0.068484046,"top":0.15003991,"width":0.1200133,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe is fundamentally designed to be a","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"100% local, privacy-first","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":27,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"1. Where It Starts: The Capture Layer","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. Where It Starts: The Capture Layer","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"System Audio:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Microphone Input:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Everything you say into your mic.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. How It Gets Transferred and Transcribed","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. How It Gets Transferred and Transcribed","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe prioritizes local processing, the \"transfer\" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is the transcription pipeline:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Engine:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The raw audio chunks are fed into a local speech-to-text model.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"OpenAI Whisper","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Diarization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As it transcribes the text, the engine also performs \"diarization\"—a technical term for speaker identification.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"View source details. Opens side panel.","depth":29,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Storage:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The final transcribed text is then indexed into a local","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"SQLite database","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":". This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The \"Work in Progress\" (WIP) Stage","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The \"Work in Progress\" (WIP) Stage","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"There is a slight bottleneck between","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"hearing","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the audio and","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"saving","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"the text, which acts as the WIP stage:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Buffering:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Processing Queue:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Finalization:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"4. Understanding the Folder Structure","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"4. Understanding the Folder Structure","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The SQLite Database (","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"):","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is \"done.\"","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folders:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Temp Files:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you see rapidly changing files, temporary","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"chunks, or locked database journals (like","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Sources","depth":26,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Sources","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":21,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?","depth":23,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Expand","depth":21,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Listen","depth":24,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Yes, those","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Here is exactly what those files are doing sitting in your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"directory and how they interact with the rest of the system.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"1. The \"Time Machine\" Playback","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"1. The \"Time Machine\" Playback","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"database along with","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"precise timestamps and file path references","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"2. Re-processing and Model Upgrades","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"2. Re-processing and Model Upgrades","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"3. The Source of Truth for Hallucinations","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"3. The Source of Truth for Hallucinations","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"file is your fallback source of truth to verify what was actually said.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Database Views Them","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Database Views Them","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you were to open up your","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"db.sqlite","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and query the tables (e.g.,","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"audio_transcriptions","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"), you would see that the database treats the","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/data/","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"soundcore AeroClip (input)_2026-05-12_07-40-48.mp4","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"What happens if you delete them?","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you manually","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"rm","depth":28,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a \"file not found\" error in the background logs.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Managing the Storage Footprint","depth":26,"on_screen":false,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Managing the Storage Footprint","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Because ScreenPipe records continuously, this folder will inevitably grow over time.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Built-in Garbage Collection:","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).","depth":29,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Archiving:","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.02642952,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you prefer to keep a permanent, searchable \"life log\" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22041224,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"older","depth":29,"bounds":{"left":0.18035239,"top":0.0,"width":0.015292553,"height":0.016360734},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.","depth":29,"bounds":{"left":0.09142287,"top":0.0,"width":0.22174202,"height":0.057861134},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":24,"bounds":{"left":0.075465426,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":24,"bounds":{"left":0.08610372,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Share and export","depth":23,"bounds":{"left":0.09674202,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":24,"bounds":{"left":0.107380316,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":23,"bounds":{"left":0.11801862,"top":0.029928172,"width":0.010638298,"height":0.025538707},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy prompt","depth":21,"bounds":{"left":0.12566489,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Edit","depth":21,"bounds":{"left":0.14029256,"top":0.0905826,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXHeading","text":"You said yes I will do that. Is there a way to setup languages to transcription?","depth":21,"bounds":{"left":0.16023937,"top":0.100159615,"width":0.15026596,"height":0.03830806},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You said","depth":23,"bounds":{"left":0.068484046,"top":0.1009577,"width":0.019946808,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes I will do that. Is there a way to setup languages to transcription?","depth":23,"bounds":{"left":0.16023937,"top":0.10175578,"width":0.12849069,"height":0.035514764},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Listen","depth":24,"bounds":{"left":0.3025266,"top":0.17039107,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Show thinking","depth":28,"bounds":{"left":0.09208777,"top":0.17278531,"width":0.030917553,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Gemini said","depth":23,"bounds":{"left":0.08976064,"top":0.21428572,"width":0.0003324468,"height":0.0007980846},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Gemini said","depth":24,"bounds":{"left":0.08976064,"top":0.21628092,"width":0.04105718,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.","depth":27,"bounds":{"left":0.0787899,"top":0.21747805,"width":0.23088431,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"As for setting up languages for transcription,","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.10920878,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"yes, you can configure it","depth":27,"bounds":{"left":0.18799867,"top":0.28850758,"width":0.06333112,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":", but it helps to understand how ScreenPipe handles language natively first.","depth":27,"bounds":{"left":0.0787899,"top":0.28850758,"width":0.20994017,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How the Transcription Engine Handles Language","depth":26,"bounds":{"left":0.0787899,"top":0.3499601,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How the Transcription Engine Handles Language","depth":27,"bounds":{"left":0.0787899,"top":0.35155627,"width":0.12549867,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"By default, ScreenPipe uses a","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.072972074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"multilingual Whisper model","depth":27,"bounds":{"left":0.15176196,"top":0.37789306,"width":0.07047872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"and sets the language configuration to","depth":27,"bounds":{"left":0.0787899,"top":0.37789306,"width":0.23321144,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-Detect","depth":27,"bounds":{"left":0.08510638,"top":0.39864326,"width":0.032247342,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":".","depth":27,"bounds":{"left":0.11735372,"top":0.39864326,"width":0.0013297872,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.","depth":27,"bounds":{"left":0.0787899,"top":0.42817238,"width":0.23038563,"height":0.037110932},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Advantage:","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.040724736,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.","depth":29,"bounds":{"left":0.09142287,"top":0.47845173,"width":0.22174202,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"The Drawback:","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.038896278,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.","depth":29,"bounds":{"left":0.09142287,"top":0.5494813,"width":0.20744681,"height":0.09936153},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"How to Force a Specific Language","depth":26,"bounds":{"left":0.0787899,"top":0.67318434,"width":0.234375,"height":0.01915403},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"How to Force a Specific Language","depth":27,"bounds":{"left":0.0787899,"top":0.67478055,"width":0.08759973,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.","depth":27,"bounds":{"left":0.0787899,"top":0.70111734,"width":0.2278923,"height":0.057861134},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are using the Desktop App UI:","depth":27,"bounds":{"left":0.0787899,"top":0.7721468,"width":0.09275266,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Open the ScreenPipe settings.","depth":29,"bounds":{"left":0.09142287,"top":0.801676,"width":0.07347074,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Navigate to the","depth":29,"bounds":{"left":0.09142287,"top":0.8312051,"width":0.038231384,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Audio","depth":29,"bounds":{"left":0.12965426,"top":0.8312051,"width":0.014960106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.14461437,"top":0.8312051,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"AI/Transcription","depth":29,"bounds":{"left":0.15242687,"top":0.8312051,"width":0.041888297,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"section.","depth":29,"bounds":{"left":0.19431517,"top":0.8312051,"width":0.02044548,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Look for the","depth":29,"bounds":{"left":0.09142287,"top":0.8607342,"width":0.030585106,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Whisper Language","depth":29,"bounds":{"left":0.12200798,"top":0.8607342,"width":0.04837101,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or","depth":29,"bounds":{"left":0.17037898,"top":0.8607342,"width":0.0078125,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Transcription Language","depth":29,"bounds":{"left":0.17819148,"top":0.8607342,"width":0.061502658,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"dropdown.","depth":29,"bounds":{"left":0.23969415,"top":0.8607342,"width":0.027260639,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Change it from \"Auto\" to your specific language (e.g., English, Bulgarian, or Slovak).","depth":29,"bounds":{"left":0.09142287,"top":0.8902634,"width":0.20079787,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you are running ScreenPipe via CLI/Config:","depth":27,"bounds":{"left":0.0787899,"top":0.92378294,"width":0.116023935,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"You can modify your underlying configuration (usually found in","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.15159574,"height":0.016360734},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"~/.screenpipe/pipe.json","depth":28,"bounds":{"left":0.23238032,"top":0.94573027,"width":0.064328454,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:","depth":27,"bounds":{"left":0.0787899,"top":0.9445331,"width":0.234375,"height":0.05546689},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Slovak)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.020777926,"height":-0.015562654},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(Bulgarian)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.027925532,"height":-0.04509175},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"(English)","depth":29,"bounds":{"left":0.14012633,"top":1.0,"width":0.02244016,"height":-0.07462096},"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.","depth":27,"on_screen":false,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Good response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXCheckBox","text":"Bad response","depth":23,"on_screen":false,"help_text":"","role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Redo","depth":23,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Share and export","depth":22,"on_screen":false,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Copy","depth":23,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Show more options","depth":22,"on_screen":false,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXTextArea","text":"Ask Gemini","depth":20,"bounds":{"left":0.08211436,"top":0.83439744,"width":0.22573139,"height":0.01915403},"on_screen":true,"value":"Ask Gemini","help_text":"","role_description":"text entry area","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Ask Gemini","depth":21,"bounds":{"left":0.08211436,"top":0.8347965,"width":0.030086435,"height":0.018355945},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Open upload file menu","depth":20,"bounds":{"left":0.078125,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Tools","depth":18,"bounds":{"left":0.094082445,"top":0.87031126,"width":0.013297873,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false,"is_expanded":false},{"role":"AXButton","text":"Open mode picker","depth":20,"bounds":{"left":0.27044547,"top":0.867917,"width":0.026097074,"height":0.031923383},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Pro","depth":23,"bounds":{"left":0.2757646,"top":0.87669593,"width":0.007480053,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXCheckBox","text":"Microphone","depth":19,"bounds":{"left":0.29853722,"top":0.867917,"width":0.013297873,"height":0.031923383},"on_screen":true,"role_description":"toggle button","subrole":"AXToggle","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Send message","depth":19,"bounds":{"left":0.30485374,"top":0.8671189,"width":0.013962766,"height":0.033519555},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":false,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Gemini is AI and can make mistakes, including about people.","depth":17,"bounds":{"left":0.11702128,"top":0.92178774,"width":0.11170213,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXLink","text":"Your privacy and Gemini Opens in a new window","depth":17,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"link","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Your privacy and Gemini","depth":18,"bounds":{"left":0.2287234,"top":0.92178774,"width":0.044215426,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Opens in a new window","depth":19,"bounds":{"left":0.068484046,"top":0.92098963,"width":0.043218084,"height":0.012370312},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Summarize page","depth":7,"bounds":{"left":0.07413564,"top":0.95730245,"width":0.053523935,"height":0.025538707},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Summarize page","depth":9,"bounds":{"left":0.07978723,"top":0.96249,"width":0.042220745,"height":0.015163607},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXHeading","text":"Screenpipe [archive.db · 2071.1MB]","depth":7,"bounds":{"left":0.33061835,"top":0.061452515,"width":0.064328454,"height":0.017956903},"on_screen":true,"help_text":"","role_description":"heading","subrole":"AXUnknown"},{"role":"AXStaticText","text":"Screenpipe","depth":8,"bounds":{"left":0.33061835,"top":0.06304868,"width":0.027759308,"height":0.014764565},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"[archive.db · 2071.1MB]","depth":9,"bounds":{"left":0.35970744,"top":0.06703911,"width":0.03523936,"height":0.009976057},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXButton","text":"Activity","depth":7,"bounds":{"left":0.39960107,"top":0.059856344,"width":0.024767287,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Search","depth":7,"bounds":{"left":0.42503324,"top":0.059856344,"width":0.023603724,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Audio","depth":7,"bounds":{"left":0.44930187,"top":0.059856344,"width":0.021110373,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Work Report","depth":7,"bounds":{"left":0.4710771,"top":0.059856344,"width":0.03507314,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"Timetable","depth":7,"bounds":{"left":0.50681514,"top":0.059856344,"width":0.029587766,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXButton","text":"AI Summary","depth":7,"bounds":{"left":0.53706783,"top":0.059856344,"width":0.034242023,"height":0.0207502},"on_screen":true,"help_text":"","role_description":"button","subrole":"AXUnknown","is_enabled":true,"is_focused":false,"is_selected":false},{"role":"AXStaticText","text":"Date","depth":8,"bounds":{"left":0.93866354,"top":0.0650439,"width":0.008144947,"height":0.010774142},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"12","depth":9,"bounds":{"left":0.95545214,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.96127,"top":0.06464485,"width":0.0023271276,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"05","depth":9,"bounds":{"left":0.9645944,"top":0.06464485,"width":0.0048204786,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"},{"role":"AXStaticText","text":"/","depth":8,"bounds":{"left":0.97041225,"top":0.06464485,"width":0.002493351,"height":0.011572227},"on_screen":true,"help_text":"","role_description":"text","subrole":"AXUnknown"}]...
|
-3436662734314472178
|
8632612251536862173
|
click
|
accessibility
|
NULL
|
Screenpipe — Archive
Screenpipe — Archive
All docs Screenpipe — Archive
Screenpipe — Archive
All docs · AFFiNE
All docs · AFFiNE
DXP4800PLUS-B5F8
DXP4800PLUS-B5F8
Screenpipe — Archive
Screenpipe — Archive
Close tab
SQLite Web: archive.db
SQLite Web: archive.db
SQLite Web: db.sqlite
SQLite Web: db.sqlite
Claude
Claude
Manage extra usage for paid Claude plans | Claude Help Center
Manage extra usage for paid Claude plans | Claude Help Center
2 TB in 25 MB/s - Google Search
2 TB in 25 MB/s - Google Search
New Tab
Customize sidebar
Close Google Gemini (⌃X)
Open history (⇧⌘H)
Open bookmarks (⌘B)
Bitwarden
AI Chat settings
Close
Google Account: Lukáš Koválik ([EMAIL])
Main menu
New chat
Gemini
New chat
Share conversation
Open menu for conversation actions.
Conversation with Gemini
Conversation with Gemini
Copy prompt
You said Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
You said
Exaplin me: how does the ScreenPipe audio recording work? Where did it start? How is it getting transferred and transcribed? Is there some work in progress stage? How can I see from the folder structure what has been done and what hasn't been done?
Listen
Show thinking
Gemini said
Gemini said
Here is a breakdown of how ScreenPipe handles audio recording, from the moment it captures sound to how it organizes the data on your machine.
ScreenPipe is fundamentally designed to be a
100% local, privacy-first
application, meaning the vast majority of its processing happens directly on your hardware without relying on the cloud.
View source details. Opens side panel.
1. Where It Starts: The Capture Layer
1. Where It Starts: The Capture Layer
The process begins locally by tapping directly into your operating system’s audio routing. ScreenPipe simultaneously captures two separate audio streams:
System Audio:
Everything your computer outputs (e.g., the voices of other people in a Zoom or Teams meeting, a YouTube video, or Spotify).
Microphone Input:
Everything you say into your mic.
View source details. Opens side panel.
Because ScreenPipe acts as a 24/7 background process, it continuously listens to these streams and breaks the continuous audio into manageable chunks to prepare them for the next stage.
2. How It Gets Transferred and Transcribed
2. How It Gets Transferred and Transcribed
Because ScreenPipe prioritizes local processing, the "transfer" step is incredibly short. The audio data never leaves your machine unless you explicitly set up a cloud plugin.
Here is the transcription pipeline:
The Engine:
The raw audio chunks are fed into a local speech-to-text model.
By default, ScreenPipe uses
OpenAI Whisper
running locally on your hardware. (Users can also configure it to use cloud providers like Deepgram if they need faster processing, but local Whisper is the standard).
View source details. Opens side panel.
Diarization:
As it transcribes the text, the engine also performs "diarization"—a technical term for speaker identification.
It analyzes the audio to distinguish between your voice and the voices of others, labeling who said what.
View source details. Opens side panel.
Storage:
The final transcribed text is then indexed into a local
SQLite database
. This database uses Full-Text Search (FTS5), which is what allows you to instantly search for a phrase you heard in a meeting three weeks ago.
3. The "Work in Progress" (WIP) Stage
3. The "Work in Progress" (WIP) Stage
There is a slight bottleneck between
hearing
the audio and
saving
the text, which acts as the WIP stage:
Buffering:
Audio is recorded into a temporary buffer in your system's RAM or written as temporary chunk files on your disk.
Processing Queue:
Whisper requires CPU/GPU resources to transcribe. If you are having a rapid, multi-person conversation, the raw audio chunks line up in a processing queue.
Finalization:
Once the AI finishes transcribing a chunk, the text is committed to the SQLite database alongside a timestamp, and the raw audio is compressed and saved so you can play it back later.
4. Understanding the Folder Structure
4. Understanding the Folder Structure
All of ScreenPipe's data lives locally on your machine (usually in a hidden directory like
~/.screenpipe
on Mac/Linux or in your AppData folder on Windows). You can determine what has been processed by looking at a few key areas in this directory:
The SQLite Database (
):
This is the master ledger. If text exists inside this database, it means the audio has been fully transcribed, diarized, and is "done."
The
or
folders:
This is where the compressed, raw audio files and JPEG screenshots are stored permanently. Think of this as the raw archive.
Temp Files:
If you see rapidly changing files, temporary
chunks, or locked database journals (like
), this indicates the system is actively processing a backlog of audio (the WIP stage). Once the engine catches up, these temporary chunk files are usually cleared out or moved to permanent storage, and the database updates.
Are you setting up ScreenPipe for a specific workflow (like summarizing meetings or tracking your daily tasks), or just exploring how the architecture works under the hood?
Sources
Sources
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
You said I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
You said
I see the files in ~/.screenpipe/data/ as LakyLak bose qc35 II (input)_2026-05-12_06-49-17.mp4 or MacBook Pro Microphone (input)_2026-05-12_12-17-23.mp4 or soundcore AeroClip (input)_2026-05-12_07-40-48.mp4 or System Audio (output)_2026-05-11_06-17-14.mp4. Are these used for anything after transcribing and storing in sqlite db?
Expand
Listen
Show thinking
Gemini said
Gemini said
Yes, those
.mp4
files are absolutely still used after the transcription process is complete. They are not temporary processing chunks; they act as your permanent media archive.
Here is exactly what those files are doing sitting in your
~/.screenpipe/data/
directory and how they interact with the rest of the system.
1. The "Time Machine" Playback
1. The "Time Machine" Playback
The primary reason ScreenPipe keeps these files is for audio playback. When Whisper transcribes your meetings or ambient audio, it writes the text into the
db.sqlite
database along with
precise timestamps and file path references
.
When you search your ScreenPipe history for a specific conversation, the UI doesn't just show you the text—it uses the file path stored in the database to pull up that specific
.mp4
file and starts playing it at the exact second the keyword was spoken. Without these files, you get the transcript, but you lose the ability to actually listen to the context, tone, or nuance of the original conversation.
2. Re-processing and Model Upgrades
2. Re-processing and Model Upgrades
Local LLMs and transcription models are improving rapidly. Right now, your system might be using a quantized Whisper model to balance CPU load with accuracy. If you later decide to run a heavier, more accurate model—or if a radically better speaker diarization algorithm is released—having the raw
.mp4
files allows you to re-process historical audio. Without the raw input files, your data is permanently locked to the quality of the transcription model you were running on May 12th.
3. The Source of Truth for Hallucinations
3. The Source of Truth for Hallucinations
Speech-to-text engines, even great ones, occasionally hallucinate or misinterpret technical jargon, overlapping voices, or background noise. If a database query returns a completely nonsensical sentence, that
.mp4
file is your fallback source of truth to verify what was actually said.
How the Database Views Them
How the Database Views Them
If you were to open up your
db.sqlite
and query the tables (e.g.,
audio_transcriptions
), you would see that the database treats the
~/.screenpipe/data/
folder essentially as a blob storage backend. The tables contain columns acting as soft foreign keys pointing to filenames like
soundcore AeroClip (input)_2026-05-12_07-40-48.mp4
.
What happens if you delete them?
If you manually
rm
those files to free up space on your Mac's SSD, ScreenPipe won't crash. The SQLite database will still hold all your searchable text. However, any attempt to play back the audio for those older transcripts will silently fail or throw a "file not found" error in the background logs.
Managing the Storage Footprint
Managing the Storage Footprint
Because ScreenPipe records continuously, this folder will inevitably grow over time.
Built-in Garbage Collection:
ScreenPipe usually handles this automatically based on retention settings (e.g., deleting media older than 30 days or when the folder hits a specific GB limit).
Archiving:
If you prefer to keep a permanent, searchable "life log" without eating up your local SSD space, you don't necessarily have to let ScreenPipe delete them. You could script a simple cron job to regularly
older
files to your massive 4-drive RAID 5 array, replacing the local files with symlinks. This would keep the database references intact while offloading the heavy media storage to your NAS.
Good response
Bad response
Share and export
Copy
Show more options
Copy prompt
Edit
You said yes I will do that. Is there a way to setup languages to transcription?
You said
yes I will do that. Is there a way to setup languages to transcription?
Listen
Show thinking
Gemini said
Gemini said
That is a solid plan. Offloading those older media files to your 4-drive RAID 5 setup (or even the secondary SSD-only Beelink NAS if you end up building it) will keep your local SSD lean while keeping your database searchable.
As for setting up languages for transcription,
yes, you can configure it
, but it helps to understand how ScreenPipe handles language natively first.
How the Transcription Engine Handles Language
How the Transcription Engine Handles Language
By default, ScreenPipe uses a
multilingual Whisper model
and sets the language configuration to
Auto-Detect
.
When a new audio chunk comes in, the model listens to the first few seconds of audio, guesses the language, and transcribes the rest of that chunk using that assumption.
The Advantage:
If you are watching a tutorial in English, and then an hour later you are in a Zoom call speaking Bulgarian, ScreenPipe will automatically switch gears without you having to touch the settings.
The Drawback:
Auto-detect can sometimes guess wrong, especially if there is heavy background noise, if someone starts a sentence with a foreign loanword, or if you are rapidly code-switching between Slovak and English in the same conversation. When it guesses wrong, it might try to force Slovak words into English spelling, resulting in gibberish.
How to Force a Specific Language
How to Force a Specific Language
If you want to ensure maximum accuracy and you know you will primarily be recording in one language for a specific period, you can explicitly set the language. This also slightly speeds up the processing because the model skips the detection phase.
If you are using the Desktop App UI:
Open the ScreenPipe settings.
Navigate to the
Audio
or
AI/Transcription
section.
Look for the
Whisper Language
or
Transcription Language
dropdown.
Change it from "Auto" to your specific language (e.g., English, Bulgarian, or Slovak).
If you are running ScreenPipe via CLI/Config:
You can modify your underlying configuration (usually found in
~/.screenpipe/pipe.json
or by passing a flag when starting the daemon) to force a specific language code. You would use the standard ISO language codes:
(Slovak)
(Bulgarian)
(English)
If you find yourself frequently jumping between those three languages, your best bet is to leave it on Auto-Detect and perhaps run a slightly larger, more accurate Whisper model (like Whisper 'Small' or 'Base' instead of 'Tiny') if your hardware has the headroom for it.
Good response
Bad response
Redo
Share and export
Copy
Show more options
Ask Gemini
Ask Gemini
Open upload file menu
Tools
Open mode picker
Pro
Microphone
Send message
Gemini is AI and can make mistakes, including about people.
Your privacy and Gemini Opens in a new window
Your privacy and Gemini
Opens in a new window
Summarize page
Summarize page
Screenpipe [archive.db · 2071.1MB]
Screenpipe
[archive.db · 2071.1MB]
Activity
Search
Audio
Work Report
Timetable
AI Summary
Date
12
/
05
/...
|
38687
|
NULL
|
NULL
|
NULL
|