Skip to main content

Overview

Text-to-speech endpoints

Available Operations

createSpeech

Synthesizes audio from the input text. Returns a raw audio bytestream in the requested format (e.g. mp3, pcm, wav).

Example Usage

Standalone function

The standalone function version of this method:

Parameters

Response

Promise<ReadableStream<Uint8Array>>

Errors

listModels

Lists every text-to-speech model with the inputs it accepts and its speech output parameters, merged across its endpoints, plus each endpoint with its own.

Example Usage

Standalone function

The standalone function version of this method:

Parameters

Response

Promise<models.SpeechModelsListResponse>

Errors

getModel

Returns a text-to-speech model with each endpoint’s own inputs and speech output parameters.

Example Usage

Standalone function

The standalone function version of this method:

Parameters

Response

Promise<models.SpeechModelResponse>

Errors