Voicechanger.co
Developer API

Voice Transformation at Scale

Integrate real-time voice cloning and transformation into your application with simple REST endpoints.

Get API KeyExplore Endpoints

API Endpoints

Simple, powerful, and well-documented

POST
/v1/synthesize
Generate speech from text with a specified voice

Parameters

text, voice_id, language, speed, format
POST
/v1/clone
Clone a voice from a reference audio sample

Parameters

audio_file, reference_text (optional)
POST
/v1/transform
Transform audio from one voice to another in real-time

Parameters

audio_stream, target_voice_id, language
GET
/v1/voices
List all available and custom voices

Parameters

language, page, limit

Quick Start

Get up and running in minutes

import requests

response = requests.post(
    "https://api.voicechanger.co/v1/synthesize",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "text": "Hello, this is a voice test!",
        "voice_id": "voice_sarah_en",
        "language": "en",
        "speed": 1.0,
        "format": "mp3",
    },
)

with open("output.mp3", "wb") as f:
    f.write(response.content)

Built for Production

<100ms

API Latency

P95 response time

99.9%

Uptime

SLA guaranteed

10K+

Concurrent

requests per second

600+

Languages

supported languages