Skip to content
Registry

provider-elevenlabs

v0.1.1

ElevenLabs speech provider worker; implements provider::elevenlabs::transcribe and provider::elevenlabs::speak behind llm-router's router::transcribe and router::speak.

license: Apache-2.0elevenlabsproviderspeechstttts

Install

bash
iii trigger compose::add worker=provider-elevenlabs

Run in your project with the iii engine running. Exact versions are immutable and digest-pinned.

Functions4

provider::elevenlabs::on_router_ready

Function

Internal: re-declare with llm-router after it restarts (bound to the router::ready trigger).

Request
Empty object
Response
  • okbooleanrequired

provider::elevenlabs::refresh_models

Function

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.

Request
Empty object
Response
  • countinteger· uintrequiredmin 0
  • okbooleanrequired

provider::elevenlabs::speak

Function

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).

Request
  • formatstring

    `mp3` (default), `wav`, `pcm16`, `opus`.

  • languagestring

    ISO 639-1 language to enforce; ignored by models that pick it from the text.

  • modelstring

    Text-to-speech model id; `eleven_multilingual_v2` when omitted.

  • speednumber· double

    Speaking-rate multiplier, 0.7 to 1.2; 1.0 is the voice's own pace.

  • textstringrequired

    Text to speak.

  • voicestring

    Voice id, or the name of a voice on the account; George when omitted.

Response
  • audio_base64stringrequired
  • mimestringrequired
  • modelstringrequired
  • voicestringrequired

    The voice id used.

provider::elevenlabs::transcribe

Function

Speech to text on ElevenLabs Scribe behind router::transcribe: base64 audio in, text with timed segments and the detected language out.

Request
  • audio_base64stringrequired

    The audio, base64. Any common container; `mime` names it.

  • languagestring

    ISO 639-1 or 639-3 language code; detected when omitted.

  • mimestring

    MIME type of the audio; `audio/wav` when omitted.

  • modelstring

    Speech-to-text model id; `scribe_v1` when omitted.

  • promptstring

    Accepted for the shared contract; Scribe takes no prompt.

Response
  • duration_secsnumber· double
  • languagestring

    Language Scribe detected (ISO 639-3, e.g. `eng`).

  • modelstringrequired
  • segmentsobject[]

    Sentences, cut at punctuation or a pause, with word timings.

    • end_secsnumber· double
    • start_secsnumber· double
    • textstringrequired
  • textstringrequired

Triggers0

No triggers registered

Search the registry

Find workers, kits and executables, or jump to a page.