Skip to main content

Text-To-Speech V2

POST 
/v2/models/tts

Convert text to speech using the V2 TTS model.

What does this endpoint do?

  • Converts the provided text to natural-sounding speech
  • Allows customization of voice characteristics through description
  • Returns complete audio file in a single response
  • Supported speaker names: "Moussa", "Sekou", "Seydou"

Behavior Notes:

  • Returns complete audio file (non-streaming)
  • May have higher latency than streaming version for long texts

Headers:

  • x-api-key: Your API key for authentication

Parameters:

  • text (str): The text to convert to speech
  • description (str): Description of desired voice characteristics
  • format (str): Output format — mp3 (default), wav, wav_8k, ulaw_8k

Example Request Body:

{
    "text": "Aw ni ce, i ka kene wa?",
    "description": "Moussa speaks with a very clear voice and a friendly tone",
    "format": "mp3"
}

Returns: Response: Complete audio file in the requested format

Request​

Responses​

Successful Response