POST
/
text-to-speech
TypeScript
import { Livepeer } from "@livepeer/ai";

const livepeer = new Livepeer({
  httpBearer: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await livepeer.generate.textToSpeech({
    modelId: "",
    text: "",
    description: "A male speaker delivers a slightly expressive and animated speech with a moderate speed and pitch.",
  });

  // Handle the result
  console.log(result);
}

run();
{
  "audio": {
    "url": "<string>"
  }
}
The default Gateway used in this guide is the public Livepeer.cloud Gateway. It is free to use but not intended for production-ready applications. For production-ready applications, consider using the Livepeer Studio Gateway, which requires an API token. Alternatively, you can set up your own Gateway node or partner with one via the ai-video channel on Discord.
Please note that the exact parameters, default values, and responses may vary between models. For more information on model-specific parameters, please refer to the respective model documentation available in the text-to-speech pipeline. Not all parameters might be available for a given model.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model_id
string
default:""
required

Hugging Face model ID used for text to speech generation.

​
text
string
default:""

Text input for speech generation.

​
description
string
default:A male speaker delivers a slightly expressive and animated speech with a moderate speed and pitch.

Description of speaker to steer text to speech generation.

Response

Successful Response

Response model for audio generation.

​
audio
object
required

The generated audio. A URL from which media can be accessed.