Configure ExtraBrain Audio Settings
Open Settings → Audio to configure capture and transcription. The analysis model is selected separately in AI Providers.
Main Controls
Section titled “Main Controls”| Control | Purpose |
|---|---|
| Transcription Provider | Local Parakeet, on-device Apple Speech where supported, or cloud Deepgram. |
| Microphone / Audio Source | Select the microphone device or System Default. |
| System Audio Capture | Check access for sound from calls, videos, and other apps. |
| Voice Trigger | Start analysis from a configured spoken phrase during live transcription. |
| Transcript Cleanup | Remove built-in and custom filler terms before transcript cards and analysis. |
Compare transcription providers for setup and data flow. Apple Speech has its own language and asset status; changing the interface language does not change the speech language.
Advanced Audio
Section titled “Advanced Audio”Open Show advanced audio controls to inspect:
- Reduce speaker audio picked up by the mic to limit duplicate speaker audio in microphone transcription.
- Use stronger speaker-audio reduction for more aggressive suppression. It may reduce your voice when people speak at the same time.
- Automatic microphone gain control to balance microphone volume. Leave it off if your voice fades while computer audio plays.
Follow the displayed restart requirement for echo-reduction changes. Device and provider changes should be tested in a new session.
Test Capture
Section titled “Test Capture”- Grant macOS permissions.
- Select the intended microphone and provider.
- Start a short session and test your speech.
- Play computer audio and verify it separately.
- Inspect warnings such as unavailable device, mic stopped, or system audio stopped.
If the selected device disappears, ExtraBrain can fall back to the default. Check the actual device status before a call. Muting an audio source does not end the session.
See Voice Trigger and Transcript Cleanup.