Open Source · MIT License

clone-voice

Clone any voice from a short audio clip and generate speech — entirely in the browser.

const clone = require('clone-voice');

const voice = await clone('./my-voice.wav');
const wav = await voice.speak('Hello from my cloned voice!');

npm install clone-voice

🎙️

Record 5 seconds, get a cloned voice. Works in browser and Node/CLI.

const v = await clone.mic(5000);
const wav = await v.speak('Hi!');

🔊

.speak() returns WAV. .stream() fires PCM chunks for real-time playback.

voice.on('chunk', pcm => play(pcm));
await voice.stream('Streaming!');

🌍

English, German, Italian, Portuguese, Spanish. Pass { lang } to clone.

const v = await clone('./s.wav', {
  lang: 'german'
});

🤖

Use pre-trained voices instantly. No audio clip needed.

const v = await clone('alba');
const wav = await v.speak('Hello!');

Try it live