Interface OpenAITextToSpeechProviderConfig

Configuration for the OpenAITextToSpeechProvider.

See

interface OpenAITextToSpeechProviderConfig {
    apiKey: string;
    baseUrl?: string;
    model?: string;
    voice?: string;
    fetchImpl?: {
        (input, init?): Promise<Response>;
        (input, init?): Promise<Response>;
    };
}

Properties

apiKey baseUrl? model? voice? fetchImpl?

Properties

apiKey

apiKey: string

OpenAI API key used for authentication. Sent as Authorization: Bearer <apiKey>.

Optional baseUrl

baseUrl?: string

Base URL for the OpenAI API. Override for proxies, Azure OpenAI, or compatible third-party endpoints.

Default

'https://api.openai.com/v1'

Optional model

model?: string

Default TTS model. tts-1 is optimized for real-time, tts-1-hd for quality.

OpenAI removes tts-1, tts-1-hd and the gpt-4o-mini-tts snapshots on 2027-01-06. The replacement it names, gpt-realtime-2.1-mini, runs only on the Realtime API and is not accepted by /v1/audio/speech, which this provider calls.

Default

'tts-1'

Optional voice

voice?: string

Default voice identifier. See OPENAI_VOICES for available options.

Default

'nova'

Optional fetchImpl

fetchImpl?: {
    (input, init?): Promise<Response>;
    (input, init?): Promise<Response>;
}

Custom fetch implementation for dependency injection in tests.

Type declaration

    • (input, init?): Promise<Response>

    • Parameters

      • input: RequestInfo | URL
      • Optional init: RequestInit

      Returns Promise<Response>

    • (input, init?): Promise<Response>

    • Parameters

      • input: string | Request | URL
      • Optional init: RequestInit

      Returns Promise<Response>

Default

globalThis.fetch

Settings

Member Visibility

Theme

On This Page

apiKeybaseUrlmodelvoicefetchImpl