Sign in

v52

OpenAPI 3.1.0raw.githubusercontent.com2026-07-311,1941,9384.1 MB
Voice Designs

Create or add a version to a voice design

Creates a new voice design (version 1) when voice_design_id is omitted. When voice_design_id is provided, adds a new version to the existing design instead. A design can have at most 50 versions.

post/voice_designs

Request body

languagestring

Language for synthesis. Supported values: Auto, Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian. Defaults to Auto.

max_new_tokensinteger

Maximum number of tokens to generate. Default: 2048.

namestring

Name for the voice design. Required when creating a new design (voice_design_id is not provided); ignored when adding a version. Cannot be a UUID.

promptstring required

Natural language description of the voice style, e.g. 'Speak in a warm, friendly tone with a slight British accent'.

provider'telnyx' | 'minimax' | 'Telnyx' | 'Minimax'

Voice synthesis provider. telnyx uses the Qwen3TTS model; minimax uses the Minimax speech models. Case-insensitive. Defaults to telnyx.

repetition_penaltynumber float

Repetition penalty to reduce repeated patterns in generated audio. Default: 1.05.

temperaturenumber float

Sampling temperature controlling randomness. Higher values produce more varied output. Default: 0.9.

textstring required

Sample text to synthesize for this voice design.

top_kinteger

Top-k sampling parameter — limits the token vocabulary considered at each step. Default: 50.

top_pnumber float

Top-p (nucleus) sampling parameter — cumulative probability cutoff for token selection. Default: 1.0.

voice_design_idstring uuid

ID of an existing voice design to add a new version to. When provided, a new version is created instead of a new design.

Example request

{
  "language": "Auto",
  "name": "friendly-narrator",
  "prompt": "Speak in a warm, friendly tone",
  "provider": "telnyx",
  "text": "Hello, welcome to our service."
}

Response

Voice design created or new version added successfully.

Example response

{
  "data": {
    "created_at": "2024-01-01T00:00:00Z",
    "id": "550e8400-e29b-41d4-a716-446655440000",
    "name": "friendly-narrator",
    "prompt": "Speak in a warm tone",
    "provider": "Telnyx",
    "provider_supported_models": [
      "Qwen3TTS"
    ],
    "provider_voice_id": "550e8400-e29b-41d4-a716-446655440000",
    "record_type": "voice_design",
    "text": "Hello, welcome.",
    "updated_at": "2024-01-01T00:00:00Z",
    "version": 1,
    "version_created_at": "2024-01-01T00:00:00Z",
    "voice_sample_size": 48000
  }
}