Voice Cloning Quota

August 24, 2026

Table of contents

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

Returns how many cloned voice slots the MiniMax account holds and how many are in use.

Worth calling before POST speech/clone-voice, which spends around twenty seconds building a voice. Without this the only signal that an account is out of slots arrives after that work is done.

https://api.useapi.net/v1/minimax/speech/equity?account={account}

Request Headers
Authorization: Bearer {API token}
Query Parameters
  • account is optional when only one account is configured. If you have several MiniMax accounts configured, this parameter becomes required.
Responses
  • 200 OK

    {
      "used": 3,
      "total": 3,
      "voice_clone_preview_free_quota": "inf",
      "srt_download": false,
      "base_resp": {}
    }
    
  • 401 Unauthorized

    {
      "error": "Unauthorized",
      "code": 401
    }
    
  • 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
  used: number,                            // Cloned voices currently stored
  total: number,                           // Slots the plan grants
  voice_clone_preview_free_quota: string,  // Free clone previews left, "inf" when unlimited
  srt_download: boolean                    // Whether the plan includes SRT download on minimax.io
}
  • used is allowed to exceed total. An account observed with three slots reported four in use, so treat these figures as advisory rather than as a hard gate — the authoritative refusal is the error returned by POST speech/clone-voice itself.
  • Slots are freed by POST speech/delete-voice.
  • srt_download reflects whether the MiniMax plan includes subtitle downloads on their own site. It does not gate this API — word timings come back on POST speech/create-mp3 and the streaming done event whatever it says, see Word timings.
Examples
  • curl "https://api.useapi.net/v1/minimax/speech/equity?account=123456789012345678" \
      -H "Authorization: Bearer …"
    
  • const response = await fetch("https://api.useapi.net/v1/minimax/speech/equity?account=123456789012345678", {
      headers: { "Authorization": "Bearer …" }
    });
    
    const { used, total } = await response.json();
    
    console.log(`${used} of ${total} voice slots in use`);
    
  • import requests
    
    response = requests.get(
        "https://api.useapi.net/v1/minimax/speech/equity",
        headers={"Authorization": "Bearer …"},
        params={"account": "123456789012345678"}
    )
    
    equity = response.json()
    
    print(equity["used"], "of", equity["total"], "voice slots in use")
    
Try It