Class OpenAIAudioTranslationCapabilityImpl

OpenAI audio translation capability implementation.

Uses OpenAI's dedicated audio translations endpoint, which always returns English output.

Implements

AudioTranslationCapability<ClientAudioTranslationRequest>

Index

Constructors

Methods

Constructors

constructor

new OpenAIAudioTranslationCapabilityImpl(
provider: BaseProvider,
client: OpenAI,
): OpenAIAudioTranslationCapabilityImpl
Creates a new OpenAI audio translation capability adapter.
Parameters
- provider: BaseProvider
  Owning provider instance used for initialization checks and merged config access.
- client: OpenAI
  Initialized OpenAI SDK client.
Returns OpenAIAudioTranslationCapabilityImpl
- Defined in src/providers/openai/capabilities/OpenAIAudioTranslationCapabilityImpl.ts:37

Methods

translateAudio

translateAudio(
    request: AIRequest<ClientAudioTranslationRequest>,
    _ctx: MultiModalExecutionContext,
    signal?: AbortSignal,
): Promise<AIResponse<NormalizedChatMessage[]>>
Translates spoken audio into English text.
Parameters
- request: AIRequest<ClientAudioTranslationRequest>
  Unified translation request envelope.
- _ctx: MultiModalExecutionContext
  Optional multimodal execution context. Unused directly in this adapter.
- Optionalsignal: AbortSignal
  Optional cancellation signal.
Returns Promise<AIResponse<NormalizedChatMessage[]>>
Provider-normalized translated chat message artifacts.

Throws
If input file is missing, request is aborted, or target language is unsupported.
Implementation of AudioTranslationCapability.translateAudio
- Defined in src/providers/openai/capabilities/OpenAIAudioTranslationCapabilityImpl.ts:51