talk: add configurable silence timeout

This commit is contained in:
dano does design
2026-03-08 17:58:15 +11:00
committed by Peter Steinberger
parent 097c588a6b
commit 6ff7e8f42e
18 changed files with 162 additions and 9 deletions

View File

@@ -1659,6 +1659,7 @@ Defaults for Talk mode (macOS/iOS/Android).
modelId: "eleven_v3",
outputFormat: "mp3_44100_128",
apiKey: "elevenlabs_api_key",
silenceTimeoutMs: 1500,
interruptOnSpeech: true,
},
}
@@ -1668,6 +1669,7 @@ Defaults for Talk mode (macOS/iOS/Android).
- `apiKey` and `providers.*.apiKey` accept plaintext strings or SecretRef objects.
- `ELEVENLABS_API_KEY` fallback applies only when no Talk API key is configured.
- `voiceAliases` lets Talk directives use friendly names.
- `silenceTimeoutMs` controls how long Talk mode waits after user silence before it sends the transcript. Unset keeps the platform default pause window (`700` ms on macOS and Android, `900` ms on iOS).
---

View File

@@ -56,6 +56,7 @@ Supported keys:
modelId: "eleven_v3",
outputFormat: "mp3_44100_128",
apiKey: "elevenlabs_api_key",
silenceTimeoutMs: 1500,
interruptOnSpeech: true,
},
}
@@ -64,6 +65,7 @@ Supported keys:
Defaults:
- `interruptOnSpeech`: true
- `silenceTimeoutMs`: when unset, Talk keeps the platform default pause window before sending the transcript (`700` ms on macOS and Android, `900` ms on iOS)
- `voiceId`: falls back to `ELEVENLABS_VOICE_ID` / `SAG_VOICE_ID` (or first ElevenLabs voice when API key is available)
- `modelId`: defaults to `eleven_v3` when unset
- `apiKey`: falls back to `ELEVENLABS_API_KEY` (or gateway shell profile if available)