Skip to content

elevenlabs_tts

elevenlabs_tts

ElevenLabs text-to-speech backend.

Uses the ElevenLabs REST API for high-quality multilingual voice synthesis. Requires ELEVENLABS_API_KEY environment variable or config.

Classes

ElevenLabsTTSBackend 

ElevenLabsTTSBackend(*, api_key: str = '', model: str = '', voice_id: str = '')

Bases: TTSBackend

ElevenLabs TTS backend — premium multilingual synthesis.

Source code in src/openjarvis/speech/elevenlabs_tts.py 
136
137
138
139
140
141
142
143
144
145
def __init__(
    self, *, api_key: str = "", model: str = "", voice_id: str = ""
) -> None:
    self._api_key = _normalize_api_key(
        api_key or os.environ.get("ELEVENLABS_API_KEY", "")
    )
    self._model = model or os.environ.get(
        "ELEVENLABS_MODEL", "eleven_multilingual_v2"
    )
    self._voice_id = voice_id or os.environ.get("ELEVENLABS_VOICE_ID", "")