GenerationConfig
Grouped generation settings for CartesiaTTS. Flat options onCartesiaTTSOptions take precedence over the matching field here.
Constructor
CartesiaTTS
Cartesia text-to-speech provider. Creates a configured Cartesia TTS provider for use in a voice agent.Constructor
Cartesia API key. Falls back to the
CARTESIA_API_KEY env var.Voice as a catalog UUID (string) or a cloning embedding (non-empty number array). Default: a built-in voice UUID.
Alias for
voice; used when voice is not set.Synthesis model. Default:
'sonic-2'.Synthesis language code. Default:
'en'.Output audio sample rate in Hz. Default:
24000. (The effective rate is fixed; other values are ignored.)Speaking speed. Default:
null (or generationConfig.speed).Output volume. Default:
null (or generationConfig.volume).Emotion tag. Default:
null (or generationConfig.emotion).Pronunciation dictionary ID. Default:
null (or generationConfig.pronunciationDictId).Max buffering delay in ms. Default:
null (or generationConfig.maxBufferDelayMs).Emit per-word timestamps. Default:
false (or generationConfig.enableWordTimestamps).Grouped generation settings; flat options above take precedence. Default:
null.close
closeEmitter
emit
getRuntimeConfig
interrupt
listenerCount
off
on
once
onFirstAudioByte
removeAllListeners
synthesize
text on the active session.