bodhi-realtime-agent / GeminiLiveTranscribeSTTProvider
Class: GeminiLiveTranscribeSTTProvider
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:214
Provider-agnostic interface for pluggable speech-to-text providers.
VoiceSession creates the provider, calls configure() with the transport's audio format, then start(). Audio flows via feedAudio(); turn signals via commit()/handleInterrupted()/handleTurnComplete(). Results arrive via the onTranscript/onPartialTranscript callbacks.
Implements
Constructors
Constructor
new GeminiLiveTranscribeSTTProvider(
config):GeminiLiveTranscribeSTTProvider
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:259
Parameters
config
GeminiLiveTranscribeSTTConfig | GeminiLiveTranscribeSTTProviderConfig
Returns
GeminiLiveTranscribeSTTProvider
Properties
onConnectionLifecycle?
optionalonConnectionLifecycle?: (event) =>void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:218
See GeminiLiveTranscribeSTTOptions.onConnectionLifecycle.
Parameters
event
GeminiLiveTranscribeLifecycleEvent
Returns
void
onFatal?
optionalonFatal?: (error) =>void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:220
See GeminiLiveTranscribeSTTOptions.onFatal.
Parameters
error
Error
Returns
void
onPartialTranscript?
optionalonPartialTranscript?: (text) =>void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:216
Partial/interim transcription (streaming providers only). Replaces any previous partial for the same turn.
Parameters
text
string
Returns
void
Implementation of
STTProvider.onPartialTranscript
onTranscript?
optionalonTranscript?: (text,turnId) =>void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:215
Final transcription of user speech.
Parameters
text
string
The transcribed text.
turnId
number | undefined
The turn this transcript belongs to (from commit()). Undefined when a streaming provider's VAD auto-commits before the framework calls commit().
Returns
void
Implementation of
Methods
commit()
commit(
_turnId):void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:362
Signal that the user's turn has ended (model started responding). For batch providers, this triggers transcription. For streaming providers, this may trigger a manual commit.
Parameters
_turnId
number
Returns
void
Implementation of
configure()
configure(
audio):void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:306
Configure the audio format that feedAudio() will deliver. Called once before start(). The provider MUST resample or reject if it cannot handle the given format.
Parameters
audio
Returns
void
Implementation of
feedAudio()
feedAudio(
base64Pcm):void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:344
Feed audio data. Format matches the STTAudioConfig from configure().
Parameters
base64Pcm
string
Base64-encoded PCM audio chunk.
Returns
void
Implementation of
handleInterrupted()
handleInterrupted():
void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:363
Signal that the current turn was interrupted by the user. Providers MUST preserve buffered audio for the next commit().
Returns
void
Implementation of
handleTurnComplete()
handleTurnComplete():
void
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:364
Signal a natural turn completion (model finished, no interruption). Batch providers SHOULD clear buffers. Streaming providers may no-op.
Returns
void
Implementation of
STTProvider.handleTurnComplete
start()
start():
Promise<void>
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:316
Resolves once the first session is set up; rejects (and resets) if setup fails or times out.
Returns
Promise<void>
Implementation of
stop()
stop():
Promise<void>
Defined in: src/transport/gemini-live-transcribe-stt-provider.ts:339
Stop the STT session (e.g. close WebSocket).
Returns
Promise<void>