Interface AudioTranscriptionStreamCapability<TInput, TOutput>

Provider-agnostic streaming audio transcription capability.

Streams incremental transcription deltas and emits a final transcript output.

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

Type Parameters

TInput = unknown
TOutput = NormalizedChatMessage[]

Hierarchy (View Summary)

ProviderCapability
- AudioTranscriptionStreamCapability

Implemented by

Index

Methods

transcribeAudioStream

Methods

transcribeAudioStream

transcribeAudioStream(
    request: AIRequest<TInput>,
    ctx: MultiModalExecutionContext,
    signal?: AbortSignal,
): AsyncGenerator<AIResponseChunk<TOutput>>
Stream transcription deltas for input audio.
Parameters
- request: AIRequest<TInput>
  Unified AI request containing transcription input.
- ctx: MultiModalExecutionContext
  Execution context.
- Optionalsignal: AbortSignal
  Optional abort signal.
Returns AsyncGenerator<AIResponseChunk<TOutput>>
Async generator yielding transcript deltas and final output.
- Defined in src/core/provider/capabilities/AudioCapability.ts:57