Skip to content

cartesia_tts

cartesia_tts

Cartesia text-to-speech backend.

Uses the Cartesia REST API for high-quality, low-latency voice synthesis. Requires CARTESIA_API_KEY environment variable or config.

Classes

CartesiaTTSBackend 

CartesiaTTSBackend(
    *,
    api_key: str = "",
    model: str = "sonic",
    language: str = "en",
)

Bases: TTSBackend

Cartesia TTS backend — fast, high-quality synthesis.

Source code in src/diapason/speech/cartesia_tts.py 
60
61
62
63
64
65
def __init__(
    self, *, api_key: str = "", model: str = "sonic", language: str = "en"
) -> None:
    self._api_key = api_key or os.environ.get("CARTESIA_API_KEY", "")
    self._model = model
    self._language = language or os.environ.get("CARTESIA_LANGUAGE", "en")