---
title: "Voice Cloning"
description: "Clone any voice from just a few seconds of audio"
---

## Overview

Voicebox uses **Qwen3-TTS** from Alibaba to achieve near-perfect voice cloning from just a few seconds of audio. The model captures prosody, emotion, and natural cadence.

## How It Works

<Steps>
  <Step title="Upload or Record Sample">
    Provide 10-30 seconds of clear speech from the target voice
  </Step>
  <Step title="Model Analysis">
    Qwen3-TTS analyzes vocal characteristics, tone, and speaking patterns
  </Step>
  <Step title="Voice Profile Created">
    The model generates a voice embedding for synthesis
  </Step>
  <Step title="Generate Speech">
    Use the profile to generate any text in the cloned voice
  </Step>
</Steps>

## Best Practices

### Sample Quality

<CardGroup cols={2}>
  <Card title="Do" icon="check">
    - Use 10-30 seconds of audio
    - Clear, consistent speaking
    - Minimal background noise
    - Natural speaking pace
  </Card>
  <Card title="Don't" icon="xmark">
    - Very short clips (< 5 seconds)
    - Heavy background noise
    - Music or overlapping voices
    - Heavily processed audio
  </Card>
</CardGroup>

### Multiple Samples

Adding multiple samples from the same speaker can improve quality:

- Different speaking styles (casual, formal)
- Different emotions (happy, serious)
- Different recording conditions

<Tip>
  The model will learn a more robust representation from diverse samples.
</Tip>

## Supported Languages

Currently supported:
- English
- Chinese (Mandarin)

More languages coming soon.

## Limitations

<Warning>
  Voice cloning should only be used with consent. Ensure you have permission to clone someone's voice.
</Warning>

- Quality depends on sample clarity
- Works best with consistent speaking tone
- May struggle with extreme accents or speech impediments
- Background noise reduces quality