Retrieve text-to-speech audio clip

December 23, 2024 (August 24, 2026)

Table of contents

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

This endpoint will return audio clip generated by

https://api.useapi.net/v1/minimax/speech/audio_id

Request Headers 
Authorization: Bearer {API token}
Content-Type: application/json
Path parameter
  • audio_id is required. Specify audio clip you want to retrieve.

Notes:

  • Accepts an audioId returned by POST speech/create as well as any audio_id listed by GET speech.
  • While a generation from POST speech/create is still running, the response is {"statusLabel": "pending", "statusFinal": false} with no audio_url. Poll until statusFinal is true, or supply a replyUrl and let the callback tell you.
  • A generation that never completed reports statusLabel: "failed" with code and error describing why. Cancelling one with DELETE scheduler/id puts it in the same state.
  • An audioId issued by POST speech/create resolves for 7 days. After that use GET speech to find the recording, which stays on the account.
Responses

  • 200 OK

    {
    "audio_id": "user:user_id-minimax:account_id-audio:audio_id",
    "audio_review": 0,
    "voice_info": {
        "voice_id": "209533299589184",
        "parent_voice_id": "0",
        "voice_name": "Calm Woman",
        "tag_list": [
            "English",
            "Female",
            "Adult",
            "Audiobook",
            "US (General)"
        ],
        "file_id": "",
        "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": "English_CalmWoman",
        "group_id": "0"
    },
    "text": "<Text>",
    "audio_url": "https://cdn.hailuoai.video/...mp3",
    "audio_title": "<Title>",
    "create_time": 1122334455667,
    "emotion": "Auto",
    "language_boost": "Auto",
    "speed": 1,
    "pitch": 0,
    "update_time": 0,
    "effects": {
        "deepen_lighten": 0,
        "stronger_softer": 0,
        "nasal_crisp": 0,
        "spacious_echo": true,
        "lofi_telephone": false,
        "robotic": false,
        "auditorium_echo": false
    },
    "statusLabel": "completed",
    "statusFinal": true
}

    While the generation is still running:

    {
    "audioId": "user:12345-minimax:123456789012345678-audio:178737039436895391",
    "status": 0,
    "statusLabel": "pending",
    "statusFinal": false
}

    And when it failed, or was still unfinished after the 10-minute tracking window:

    {
    "audioId": "user:12345-minimax:123456789012345678-audio:178737039436895391",
    "status": 3,
    "statusLabel": "failed",
    "statusFinal": true,
    "code": 400,
    "error": "More than 10 minutes have passed, the task has expired."
}

    Poll on statusFinal rather than status — statusLabel and statusFinal are added by useapi.net, because every MiniMax history row reports status 0 whether or not it finished.

  • 400 Bad Request

    {
    "error": "<Error message>",
    "code": 400
}

  • 401 Unauthorized

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

  • 404 Not Found

    Returned with an empty body when MiniMax no longer holds the recording, for example once it has been deleted.

  • 596 Account Error

    {
  "error": "Your minimax account has pending error. Please address this issue at https://useapi.net/docs/api-minimax-v1/post-minimax-accounts-account before making any new API calls.",
  "code": 596
}
Model 
{   // TypeScript, all fields are optional
  audio_id: string
  audio_review: 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
  }
  text: string
  audio_url: string
  audio_title: string
  create_time: number
  emotion: string
  language_boost: string
  speed: number
  pitch: number
  volume: number
  update_time: number
  model: string        // The speech model used
  cost_credit: number  // Credits this generation cost
  is_first: boolean
  status: number
  statusLabel: string  // completed once audio_url is set, otherwise processing
  statusFinal: boolean
  async: number
  has_srt: boolean
  has_wav: boolean
  effects: {
      deepen_lighten: number
      stronger_softer: number
      nasal_crisp: number
      spacious_echo: boolean
      lofi_telephone: boolean
      robotic: boolean
      auditorium_echo: boolean
  }
}
Examples 
  • curl "https://api.useapi.net/v1/minimax/speech/audio_id" \
   -H "Accept: application/json" \
   -H "Authorization: Bearer …" 

  • const token = "API token";
const audio_id = "audio_id to retrieve"; 
const apiUrl = `https://api.useapi.net/v1/minimax/speech/${audio_id}`; 
const response = await fetch(apiUrl, {
  headers: {
    "Authorization": `Bearer ${token}`,
  },
});
const result = await response.json();
console.log("response", {response, result});

  • import requests
token = "API token"
audio_id = "audio_id to retrieve"
apiUrl = f"https://api.useapi.net/v1/minimax/speech/{audio_id}"
headers = {
    "Content-Type": "application/json", 
    "Authorization" : f"Bearer {token}"
}
response = requests.get(apiUrl, headers=headers)
print(response, response.json())
Try It