Class GeminiAudioTextToSpeechCapabilityImpl

Description

Provider capability implementation for GeminiAudioTextToSpeechCapabilityImpl.

Implements

Index

Constructors

Methods

textToSpeech textToSpeechStream

Constructors

constructor

new GeminiAudioTextToSpeechCapabilityImpl(
_provider: BaseProvider,
_client: GoogleGenAI,
): GeminiAudioTextToSpeechCapabilityImpl
Parameters
- _provider: BaseProvider
- _client: GoogleGenAI
Returns GeminiAudioTextToSpeechCapabilityImpl
- Defined in src/providers/gemini/capabilities/GeminiAudioTextToSpeechCapabilityImpl.ts:39

Methods

textToSpeech

textToSpeech(
    request: AIRequest<ClientTextToSpeechRequest>,
    _ctx?: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedAudio[]>>
Synthesizes speech in a single non-streaming call.
Parameters
- request: AIRequest<ClientTextToSpeechRequest>
  Unified AI request containing TTS input/options/context
- Optional_ctx: MultiModalExecutionContext
  Optional multimodal execution context (unused by this capability)
- Optionalsignal: AbortSignal
  Optional abort signal
Returns Promise<AIResponse<NormalizedAudio[]>>
Provider-normalized TTS audio artifact response

Throws
If input text is empty, request is aborted, or provider returns no audio data
Implementation of TextToSpeechCapability.textToSpeech
- Defined in src/providers/gemini/capabilities/GeminiAudioTextToSpeechCapabilityImpl.ts:53

textToSpeechStream

textToSpeechStream(
    request: AIRequest<ClientTextToSpeechRequest>,
    _ctx?: MultiModalExecutionContext,
    signal?: AbortSignal,
): AsyncGenerator<AIResponseChunk<NormalizedAudio[]>>
Streams synthesized speech as incremental audio chunks and emits a final artifact.
Parameters
- request: AIRequest<ClientTextToSpeechRequest>
  Unified AI request containing TTS input/options/context
- Optional_ctx: MultiModalExecutionContext
  Optional multimodal execution context (unused by this capability)
- Optionalsignal: AbortSignal
  Optional abort signal
Returns AsyncGenerator<AIResponseChunk<NormalizedAudio[]>>
Async generator of TTS audio chunks and a terminal completion chunk

Throws
If input text is empty before stream setup
Implementation of TextToSpeechStreamCapability.textToSpeechStream
- Defined in src/providers/gemini/capabilities/GeminiAudioTextToSpeechCapabilityImpl.ts:140