# Mimic: clone your voice in your browser

By Lucas Espindola · https://lucasespindola.com/mimic · in the site's terminal: `app mimic`

Mimic records about ten seconds of you reading a passage aloud, then says whatever you type in that voice, with Resemble AI’s Chatterbox Turbo (350M, MIT) or the original Chatterbox, which sounds less like you but has an expressiveness control. The model runs on your GPU through WebGPU; the recording and the text never leave the page.

## How it works

1. Record yourself reading a passage aloud: about ten seconds is enough, and four is the minimum.
2. The model learns your voice in your browser. The first time, it downloads while you read.
3. Type something and press Speak. Long texts are said a sentence or so at a time, and each take can be played again or saved as a .wav.

## Privacy and limits

- Only copy a voice you have the right to use: Mimic records from the microphone only, never from a file.
- Your recording and your text never leave your device.
- Needs WebGPU: Chrome or Edge on a computer, or Safari 26. English only.
- Requires WebGPU and a microphone.

## Models

- [Chatterbox Turbo](https://huggingface.co/ResembleAI/chatterbox-turbo-ONNX)
- [Chatterbox](https://huggingface.co/onnx-community/chatterbox-ONNX)