Clone a voice using uploaded audio samples

Table of contents

December 27, 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.

Make sure that you have no manually cloned voices and all slots are available. To check, please navigate to https://www.hailuo.ai/audio/voices and select “My Voices” as shown below. If you see any voices in that list, please delete them. Using the API, you will be able to clone as many voices as you want, but you will need to remove all manually cloned voices for that feature to work properly.

Screenshot www.hailuo.ai/audio/voices

Please be patient, voice cloning can take up to 60 seconds. This endpoint can only support one or two parallel tasks maximum, so organize internal queuing if you need to clone many voices in bulk.

https://api.useapi.net/v1/minimax/audio/clone-voice

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",
    "voice_name": "Doctor Who",
    "language_tag": "English",
    "files": "user:user_id-minimax:account-file:file_id1,user:user_id-minimax:account-file:file_id2",
}

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

  • voice_name is required.
    Maximum length: 30 characters.

  • language_tag is required. Use tag_name from array voice_tag_language of GET audio/config.

  • files is required. Provide up to 10 comma-separated fileID values of audio samples uploaded via POST audio/upload-sample. Each audio sample should be between 10 to 60 seconds long.

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

Responses

  • 200 OK

    {
    "input_sensitive": false,
    "input_sensitive_type": 0,
    "voice_info": {
        "voice_id": "1122334455667788",
        "parent_voice_id": "0",
        "voice_name": "Doctor Who",
        "tag_list": [
            "English"
        ],
        "file_id": "1234567890",
        "cover_url": "https://cdn.hailuoai.video/...png",
        "create_time": 1122334455667,
        "update_time": 1122334455668,
        "collected": false,
        "voice_status": 2,
        "sample_audio": "https://cdn.hailuoai.video/...mp3",
        "uniq_id": "<uniq_id>",
        "group_id": "<group_id>"
    },
    "base_resp": {}
}

  • 400 Bad Request

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

  • 401 Unauthorized

    {
  "error": "Unauthorized"
}
Model 
{ // TypeScript, all fields are optional
    input_sensitive: boolean
    input_sensitive_type: number
    voice_info: {
        voice_id: string
        parent_voice_id: string
        voice_name: string
        tag_list: string[]
        file_id: string
        cover_url: string
        create_time: number
        update_time: number
        collected: boolean
        voice_status: number
        sample_audio: string
        uniq_id: string
        group_id: string
        managed_by_api?: boolean
    }
    base_resp: {
        status_code: number 
        status_msg: string
    }
}
Examples 
  • curl -H "Accept: application/json" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer …" \
     -X POST https://api.useapi.net/v1/minimax/audio/clone-voice \
     -d '{"account": "…", "voice_name": "…", "language_tag": "…", "files": …}'

  • const account = "Previously configured audio account";      
const voice_name = "Voice Name";      
const language_tag = "Voice Language";      
const files = "fileID1,fileID2";      
const apiUrl = `https://api.useapi.net/v1/minimax/audio/clone-voice`; 
const api_token = "API token";
const data = { 
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${api_token}`,
    'Content-Type': 'application/json' }
};
data.body = JSON.stringify({ 
  account, voice_name, language_tag, files
});
const response = await fetch(apiUrl, data);
const result = await response.json();
console.log("response", {response, result});

  • import requests
account = "Previously configured audio account"
voice_name = "Voice Name"
language_tag = "Voice Language"
files = "fileID1,fileID2" 
apiUrl = f"https://api.useapi.net/v1/minimax/audio/clone-voice" 
api_token = "API token"
maxJobs = 1
headers = {
    "Content-Type": "application/json", 
    "Authorization" : f"Bearer {api_token}"
}
body = {
    "account": f"{account}",
    "voice_name": f"{voice_name}", 
    "language_tag": f"{language_tag}", 
    "files": files
}
response = requests.post(apiUrl, headers=headers, json=body)
print(response, response.json())
Try It