Passer au contenu principal
POST
/
text-to-speech
Text To Speech
curl --request POST \
  --url https://dream-gateway.livepeer.cloud/text-to-speech \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model_id": "",
  "text": "",
  "description": "A male speaker delivers a slightly expressive and animated speech with a moderate speed and pitch."
}
'
{
  "audio": {
    "url": "<string>"
  }
}

Autorisations

Authorization
string
header
requis

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

Corps

application/json
model_id
string
défaut:""

Hugging Face model ID used for text to speech generation.

text
string
défaut:""

Text input for speech generation.

description
string
défaut: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.

Réponse

Successful Response

Response model for audio generation.

audio
MediaURL · object
requis

The generated audio.

Last modified on March 1, 2026