Bodhi Realtime Agent Framework

Appearance

bodhi-realtime-agent / GeminiBatchSTTProvider

Class: GeminiBatchSTTProvider ​

Defined in: transport/gemini-batch-stt-provider.ts:30

STTProvider that uses a separate Gemini model via generateContent() for batch transcription of buffered user audio.

Extracted from GeminiLiveTransport. Audio is buffered via feedAudio(), then transcribed when commit() is called (triggered by model turn start).

Implements ​

Constructors ​

Constructor ​

new GeminiBatchSTTProvider(config): GeminiBatchSTTProvider

Defined in: transport/gemini-batch-stt-provider.ts:41

Parameters ​

config ​

GeminiBatchSTTConfig

Returns ​

GeminiBatchSTTProvider

Properties ​

onPartialTranscript()? ​

optional onPartialTranscript: (text) => void

Defined in: transport/gemini-batch-stt-provider.ts:39

Partial/interim transcription (streaming providers only). Replaces any previous partial for the same turn.

Parameters ​

text ​

string

Returns ​

void

Implementation of ​

STTProvider.onPartialTranscript

onTranscript()? ​

optional onTranscript: (text, turnId) => void

Defined in: transport/gemini-batch-stt-provider.ts:38

Final transcription of user speech.

Parameters ​

text ​

string

The transcribed text.

turnId ​

The turn this transcript belongs to (from commit()). Undefined when a streaming provider's VAD auto-commits before the framework calls commit().

number | undefined

Returns ​

void

Implementation of ​

STTProvider.onTranscript

Methods ​

commit() ​

commit(turnId): void

Defined in: transport/gemini-batch-stt-provider.ts:77

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

Monotonically increasing turn counter for ordering.

Returns ​

void

Implementation of ​

STTProvider.commit

configure() ​

configure(audio): void

Defined in: transport/gemini-batch-stt-provider.ts:46

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 ​

STTAudioConfig

Returns ​

void

Implementation of ​

STTProvider.configure

feedAudio() ​

feedAudio(base64Pcm): void

Defined in: transport/gemini-batch-stt-provider.ts:65

Feed audio data. Format matches the STTAudioConfig from configure().

Parameters ​

base64Pcm ​

string

Base64-encoded PCM audio chunk.

Returns ​

void

Implementation of ​

STTProvider.feedAudio

handleInterrupted() ​

handleInterrupted(): void

Defined in: transport/gemini-batch-stt-provider.ts:123

Signal that the current turn was interrupted by the user. Providers MUST preserve buffered audio for the next commit().

Returns ​

void

Implementation of ​

STTProvider.handleInterrupted

handleTurnComplete() ​

handleTurnComplete(): void

Defined in: transport/gemini-batch-stt-provider.ts:127

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: transport/gemini-batch-stt-provider.ts:56

Start the STT session (e.g. open WebSocket).

Returns ​

Promise<void>

Implementation of ​

STTProvider.start

stop() ​

stop(): Promise<void>

Defined in: transport/gemini-batch-stt-provider.ts:60

Stop the STT session (e.g. close WebSocket).

Returns ​

Promise<void>

Implementation of ​

STTProvider.stop

Built with VitePress