Agent OS · Component · foreground-voice-capture
Foreground voice recording and submission
What it does
Records mono PCM WAV in a microphone foreground service, supports notification stop/cancel and submits the completed clip to the streaming turn API.
Core pattern
User-initiated recording + completed-clip conversation intake
- Input
- Microphone audio
- Output
- WAV clip, transcription and response events
Key parameters
| Name | Type | Default | Values |
|---|---|---|---|
| operation | string | start | start · stop · cancel · submit |
| context | — | — | — |
| sample_rate_hz | integer | 16000 | 8000–96000 |
| channels | integer | 1 | 1–2 |
| duration_seconds | integer | 60 | 1–86400 |
Maturity and limits
Recording lifecycle, WAV header, notification actions and cleanup are implemented; recording is uploaded after stopping. Phase 2: source paths and implementation inspected statically; tests and external integrations were not executed. Maturity rates repository implementation, not a verified production deployment.
Voice privacy; not realtime ASR; background behavior needs device testing.
1 sentence citing source paths or vendor names omitted for publication.
Used in pipelines
Industry tags
- Business & general servicesTransferable use
For office assistants taking meeting requests with consent, use user-initiated recording followed by completed-clip conversation intake.
Skills pack
Contract scaffold and deterministic mock
Download · 11KBSHA-256 01f0f48c368b3356929c79de0fa601487ca48f3f64a0f70b7142a5e684e2dcc6
Related components
-
Browser-assisted desktop authentication
Browser challenge verification + device session renewal
Working 1 pipeline -
Cross-platform desktop agent workspace
Project and conversation navigation + artifact workbench
Working 2 pipelines -
Calendar, notification and device context
Authorized calendar and device state + bounded context
Working 1 pipeline -
Android assistant and creation studio
Multimodal intake + conversation and artifact views
Working 1 pipeline