Interface TextToSpeechStreamCapability<TInput, TOutput>

Provider-agnostic streaming text-to-speech capability.

Streams generated audio chunks and emits the final synthesized artifact.

interface TextToSpeechStreamCapability<
    TInput = unknown,
    TOutput = NormalizedAudio[],
> {
    textToSpeechStream(
        request: AIRequest<TInput>,
        ctx: MultiModalExecutionContext,
        signal?: AbortSignal,
    ): AsyncGenerator<AIResponseChunk<TOutput>>;
}

Type Parameters

TInput = unknown
TOutput = NormalizedAudio[]

Hierarchy (View Summary)

ProviderCapability
- TextToSpeechStreamCapability

Implemented by

Index

Methods

textToSpeechStream

Methods

textToSpeechStream

textToSpeechStream(
    request: AIRequest<TInput>,
    ctx: MultiModalExecutionContext,
    signal?: AbortSignal,
): AsyncGenerator<AIResponseChunk<TOutput>>
Stream speech synthesis output from text.
Parameters
- request: AIRequest<TInput>
  Unified AI request containing TTS input.
- ctx: MultiModalExecutionContext
  Execution context.
- Optionalsignal: AbortSignal
  Optional abort signal.
Returns AsyncGenerator<AIResponseChunk<TOutput>>
Async generator yielding partial and final audio output.
- Defined in src/core/provider/capabilities/AudioCapability.ts:126