provider::elevenlabs::on_router_ready
Internal: re-declare with llm-router after it restarts (bound to the router::ready trigger).
- okbooleanrequired
ElevenLabs speech provider worker; implements provider::elevenlabs::transcribe and provider::elevenlabs::speak behind llm-router's router::transcribe and router::speak.
iii trigger compose::add worker=provider-elevenlabsRun in your project with the iii engine running. Exact versions are immutable and digest-pinned.
Internal: re-declare with llm-router after it restarts (bound to the router::ready trigger).
Refresh the ElevenLabs catalog slice from GET /v1/models (text-to-speech models with their languages) plus the Scribe speech-to-text models, through router::models::reconcile.
Text to speech on the ElevenLabs voices behind router::speak: text and a voice id or name in, base64 audio out (mp3, wav, pcm16, opus).
`mp3` (default), `wav`, `pcm16`, `opus`.
ISO 639-1 language to enforce; ignored by models that pick it from the text.
Text-to-speech model id; `eleven_multilingual_v2` when omitted.
Speaking-rate multiplier, 0.7 to 1.2; 1.0 is the voice's own pace.
Text to speak.
Voice id, or the name of a voice on the account; George when omitted.
The voice id used.
Speech to text on ElevenLabs Scribe behind router::transcribe: base64 audio in, text with timed segments and the detected language out.
The audio, base64. Any common container; `mime` names it.
ISO 639-1 or 639-3 language code; detected when omitted.
MIME type of the audio; `audio/wav` when omitted.
Speech-to-text model id; `scribe_v1` when omitted.
Accepted for the shared contract; Scribe takes no prompt.
Language Scribe detected (ISO 639-3, e.g. `eng`).
Sentences, cut at punctuation or a pause, with word timings.
Find workers, kits and executables, or jump to a page.