CartesiaSTT
Cartesia speech-to-text provider.
Creates a configured Cartesia STT provider for use in a voice agent.
Constructor
Cartesia API key. Falls back to the CARTESIA_API_KEY env var, then null.
model
CartesiaSTTModel | string
Transcription model. Default: 'ink-whisper'.
Transcription language code. Default: 'en'.
Audio sample rate in Hz. Default: 48000.
close
Release any resources held by the provider.
closeEmitter
Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds
for in-flight async handlers to settle before returning.
emit
getRuntimeConfig
listenerCount
off
once
onSttTranscript
Register a callback to receive transcripts as they are produced.
callback
SttTranscriptCallback
required
processAudio
Process a buffer of audio frames. Override in a custom provider.
removeAllListeners
streamTranscribe
Transcribe a streaming audio source, yielding STTResponses. Override in a custom provider.
returns
AsyncIterator<STTResponse>
CartesiaSTTModel
Supported Cartesia speech-to-text model names.
