Starting a recording
PressCmd+Shift+Space (Ctrl+Shift+Space on Windows) or click record on the overlay pill.
While recording, the pill shows a live indicator. The tray tooltip switches to “Raven (Recording)”. On Windows 11 a new tray icon may start in the ^ overflow.
What gets captured
Live capture uses the OS default mic and playback devices. The Settings mic picker is only for the in-app mic test.
You can turn off system-audio capture in Settings (
captureSystemAudio). Then only the mic stream runs.
Echo cancellation
Without AEC, speaker audio leaks into the mic and shows up as You.- System PCM is the GStreamer reference (
webrtcechoprobe). - Mic PCM goes through
webrtcdsp(WebRTC AEC3). ResidualEchoGatecompares raw mic to recent system audio and drops leftover speaker bleed before STT.
Live transcription
Two STT connections run in parallel (mic → You, system → Them).- Interim text is italic while someone is still speaking
- Final text replaces interims on pause
- Labels stay You / Them (or your display name for You)
Engine pick
SettingssttProvider: auto (default), assemblyai, or deepgram. You need at least one STT key or recording will not start.
multi / auto-detect language uses Deepgram. AssemblyAI failures can fall back to Deepgram.
Languages
Set transcription language in Settings → Language. Deepgramnova-3 covers a wide set including multilingual auto-detect. AssemblyAI Universal-3 Pro realtime covers the six languages above.
Stopping
PressCmd/Ctrl+Shift+Space again or click stop. Raven:
- Stops capture
- Saves transcript and overlay chat (unless incognito)
- Generates a title and summary with a cheap/fast model on your LLM key
Permissions
macOS
Grant them in System Settings → Privacy & Security if the first prompt was denied.