List text-to-speech voices

June 25, 2026 (November 16, 2026)

Table of contents

  1. Request Headers
  2. Query Parameters
  3. Responses
  4. Model
  5. Examples
  6. Try It

List the voices available for POST speech/create, filtered by model and language. Each POST speech/create request needs a voice_id from here — the paired provider_voice_id is derived from it automatically. The MiniMax catalog carries 300+ voices, ElevenLabs ~20.

The provider is derived from the model, so you only pass model (and optionally language).

https://api.useapi.net/v2/pixverse/speech/voices?…

Request Headers
Authorization: Bearer {API token}
Content-Type: application/json
Query Parameters
  • email is optional when only one account configured. However, if you have multiple accounts configured, this parameter becomes required.

  • model is optional, default speech-2.8-hd. One of the models — the provider is derived from it. An unknown model is rejected with 400.

  • language is optional, default auto. An ISO language code (en, es, ja, …) to filter the catalog to voices recommended for that language.

Responses
  • 200 OK

    {
        "voices": [
            {
                "voice_id": "minimax_english_radiant_girl",
                "provider_voice_id": "English_radiant_girl",
                "display_name": "Radiant Girl",
                "provider": "minimax",
                "gender": "female",
                "age": "young",
                "accent": "",
                "style_tags": ["bright", "warm"],
                "recommended_languages": ["en"],
                "preview_url": "https://media.pixverse.ai/pixverse/audio/voice/preview/English_radiant_girl.mp3",
                "compatible_models": ["speech-2.8-hd", "speech-2.8-turbo"]
            }
        ],
        "pagination": { "total": 332, "has_more": false }
    }
    
  • 400 Bad Request

    Returned for an unknown model.

    {
        "error": "Invalid model '<model>'. Valid values: speech-2.8-hd,speech-2.8-turbo,eleven-multilingual-v2,eleven-v3,eleven-turbo-v2.5",
        "code": 400
    }
    
  • 401 Unauthorized

    {
      "error": "Unauthorized",
      "code": 401
    }
    
Model

The voices in voices, each with its voice_id, name, gender, accent, preview_url and the models it works with, plus pagination.

The list of voices, field by field
{   // TypeScript, all fields are optional
  voices: {
    voice_id: string
    provider_voice_id: string
    display_name: string
    provider: string
    gender: string
    age: string
    accent: string
    style_tags: string[]
    recommended_languages: string[]
    preview_url: string
    compatible_models: string[]
  }[]
  pagination: {
    total: number
    has_more: boolean
  }
}
Examples
  • curl "https://api.useapi.net/v2/pixverse/speech/voices?model=speech-2.8-hd&language=en" \
       -H "Accept: application/json" \
       -H "Authorization: Bearer …"
    
  • const token = "API token";
    const apiUrl = `https://api.useapi.net/v2/pixverse/speech/voices?model=speech-2.8-hd&language=en`;
    const response = await fetch(apiUrl, {
      headers: {
        "Authorization": `Bearer ${token}`,
      },
    });
    const result = await response.json();
    console.log("response", {response, result});
    
  • import requests
    token = "API token"
    apiUrl = f"https://api.useapi.net/v2/pixverse/speech/voices?model=speech-2.8-hd&language=en"
    headers = {
        "Content-Type": "application/json",
        "Authorization" : f"Bearer {token}"
    }
    response = requests.get(apiUrl, headers=headers)
    print(response, response.json())
    
Try It