Clone voice for speech

August 18, 2025

Table of contents

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

This endpoint creates a custom voice clone by uploading an audio sample. The cloned voice can then be used for speech generation via POST /speech. Upload clear, high-quality audio MP3 samples (10-60 seconds) for best results. Voice cloning typically takes 60-90 seconds to process.

https://api.useapi.net/v1/mureka/speech/voice?…

Request Headers 
Authorization: Bearer {API token}
Content-Type: audio/mpeg
Query Parameters

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

  • title is required. Voice title.
    Length: 1-50 characters.

  • desc is required. Voice description.
    Length: 1-500 characters.

  • lang is required. Language code for the voice.
    Supported values: en (English), zh-Hans (Simplified Chinese), zh-Hant (Traditional Chinese), ja (Japanese), ko (Korean), es (Spanish), pt (Portuguese), de (German), fr (French), it (Italian), ru (Russian).

Request Body

Binary audio file content.
Supported format: MP3 only (audio/mpeg content type).
Recommended: 10-60 seconds of clear speech for optimal cloning quality.

Responses

  • 200 OK

    {
    "id": 12345678901234,
    "user_id": 23456789012345,
    "title": "Custom Voice",
    "cover": "https://static-cos.mureka.ai/cos-prod/res/cover/….png",
    "mp3_url": "https://static-cos.mureka.ai/cos-prod/tts-v2/….mp3",
    "language": "en",
    "created_at": 1755483687,
    "description": "Custom cloned voice description",
    "duration_milliseconds": 12520,
    "machine_audit_state": 1
}

  • 400 Bad Request

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

  • 401 Unauthorized

    {
  "error": "Unauthorized",
  "code": 401
}
Model 
{ // TypeScript, all fields are optional
    id: number
    user_id: number
    title: string
    cover: string
    mp3_url: string
    language: string
    created_at: number
    description: string
    duration_milliseconds: number
    machine_audit_state: number
}
Examples 
  • curl "https://api.useapi.net/v1/mureka/speech/voice?title=CustomVoice&desc=MyVoiceDescription&lang=en" \
   -H "Accept: application/json" \
   -H "Authorization: Bearer …" \
   -H "Content-Type: audio/mpeg" \
   --data-binary @voice_sample.mp3

  • const token = "API token";
const title = "Custom Voice";
const desc = "My voice description";
const lang = "en";
const fileInput = document.querySelector('input[type="file"]');
const file = fileInput.files[0];

const apiUrl = `https://api.useapi.net/v1/mureka/speech/voice?title=${title}&desc=${desc}&lang=${lang}`;
const response = await fetch(apiUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${token}`,
    "Content-Type": file.type,
  },
  body: file,
});
const result = await response.json();
console.log("response", {response, result});

  • import requests
token = "API token"
title = "Custom Voice"
desc = "My voice description"
lang = "en"

apiUrl = f"https://api.useapi.net/v1/mureka/speech/voice?title={title}&desc={desc}&lang={lang}"
headers = {
    "Authorization" : f"Bearer {token}",
    "Content-Type": "audio/mpeg"
}

with open('voice_sample.mp3', 'rb') as audio_file:
    response = requests.post(apiUrl, headers=headers, data=audio_file.read())
    print(response, response.json())
Try It