Create text-to-speech audio

Table of contents

December 23, 2024

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

Please configure at least one www.hailuo.ai account for this endpoint, see Setup MiniMax for details.

This endpoint creates an mp3 audio from the provided text in under 20 seconds.

  • Up to 20 parallel jobs per account are supported.
  • Currently, this service is offered free of charge.

Over 300 pre-built voices provided GET audio/voices supporting the following:

  • Languages: English, Chinese (Mandarin), Spanish, French, Russian, Portuguese, Indonesian, German, Japanese, Korean, Italian, Cantonese
  • Emotions: happy, sad, angry, fearful, disgusted, surprised, neutral
  • Accents: US (General), English, Indian
  • Ages: Young Adult, Adult, Middle-Aged, Senior
  • Genders: Male, Female

https://api.useapi.net/v1/minimax/audio/create-mp3

Request Headers 
Authorization: Bearer {API token}
Content-Type: application/json
# Alternatively you can use multipart/form-data
# Content-Type: multipart/form-data
Request Body 
{
    "account": "Optional MiniMax www.hailuo.ai API account",
    "text": "Required text",
    "voice_id": "Required voice id"
}

  • account is optional when only one www.hailuo.ai account configured. However, if you have multiple accounts configured, this parameter becomes required.

  • text is required. Insert <#0.5#> to add a 0.5s pause between sentences. Adjust the duration as needed.
    Maximum length: 1000 characters.

  • voice_id is required. Use GET audio/voices to get list of all available voices.

  • language_boost is optional. Use tag_name from array voice_tag_language of GET audio/config.
    Default value Auto.

  • emotion is optional. Use value from array t2a_emotion of GET audio/config.
    Default value Auto.

  • vol is optional.
    Default 1.

  • speed is optional.
    Valid range: 0.5…2, default 1.

  • pitch is optional.
    Valid range: -12…12, default 0.

  • deepen_lighten is optional.
    Valid range: -100…100, default 0.

  • stronger_softer is optional.
    Valid range: -100…100, default 0.

  • nasal_crisp is optional.
    Valid range: -100…100, default 0.

  • spacious_echo is optional.
    Supported values: true, false (default).

  • lofi_telephone is optional.
    Supported values: true, false (default).

  • robotic is optional.
    Supported values: true, false (default).

  • auditorium_echo is optional.
    Supported values: true, false (default).

Responses

  • 200 OK

    Use returned audio_url to download generated mp3 audio file.
    Use returned audio_id to retrieve full details using GET audio/audio_id.

    {
    "audio_id": "user:user_id-minimax:account_id-audio:audio_id",
    "audio_length": 0,
    "audio_sample_rate": 32000,
    "audio_size": 1234567,
    "bitrate": 128000,
    "word_count": 0,
    "invisible_character_ratio": 0,
    "usage_characters": 1000,
    "audio_format": "mp3",
    "audio_channel": 1,
    "input_sensitive": false,
    "trace_id": "<trace id>",
    "chunks": 5123,
    "audio_review": 0,
    "user_id": 11223344556677,
    "audio_title": "<autogenerated title>",
    "audio_url": "https://cdn.hailuoai.video/...mp3",
    "update_time": 123456789
}

  • 400 Bad Request

    {
  "error": "<Error message>"
}

  • 401 Unauthorized

    {
  "error": "Unauthorized"
}

  • 429 Too Many Requests

    Wait in a loop for at least 5..10 seconds and retry again. If you receive this message frequently, you may want to consider adding more accounts to spread the load.

Model 
{ // TypeScript, all fields are optional
    audio_id: string
    audio_length: number
    audio_sample_rate: number
    audio_size: number
    bitrate: number
    word_count: number
    invisible_character_ratio: number
    usage_characters: number
    audio_format: string
    audio_channel: number
    input_sensitive: boolean
    trace_id: string
    chunks: number
    audio_review: number
    user_id: number
    audio_title: string
    audio_url: string
    update_time: number
    error: string
}
Examples 
  • curl -H "Accept: application/json" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer …" \
     -X POST "https://api.useapi.net/v1/minimax/audio/create-mp3" \
     -d '{"text": "…", "voice_id": "…"}'

  • const text = "text";      
const voice_id = "voice_id";      
const apiUrl = `https://api.useapi.net/v1/minimax/audio/create-mp3`; 
const token = "API token";
const data = { 
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${token}`,
    'Content-Type': 'application/json' }
};
data.body = JSON.stringify({ 
  text, voice_id
});
const response = await fetch(apiUrl, data);
const result = await response.json();
console.log("response", {response, result});

  • import requests
text = "text"
voice_id = "voice_id"
apiUrl = f"https://api.useapi.net/v1/minimax/audio/create-mp3" 
token = "API token"
headers = {
    "Content-Type": "application/json", 
    "Authorization" : f"Bearer {token}"
}
body = {
    "text": f"{text}",
    "voice_id": f"{voice_id}"
}
response = requests.post(apiUrl, headers=headers, json=body)
print(response, response.json())
Try It