README.md

---
library_name: mlx-audio
license: mit
base_model:
- ResembleAI/chatterbox
language:
  - ar
  - da
  - de
  - el
  - en
  - es
  - fi
  - fr
  - he
  - hi
  - it
  - ja
  - ko
  - ms
  - nl
  - no
  - pl
  - pt
  - ru
  - sv
  - sw
  - tr
  - zh
pipeline_tag: text-to-speech
tags:
- mlx
- text-to-speech
- voice-cloning
---

# mlx-community/chatterbox-multilingual-v3

This is Chatterbox Multilingual V3, converted to MLX format from [ResembleAI/chatterbox](https://huggingface.co/ResembleAI/chatterbox) using [mlx-audio](https://github.com/Blaizzy/mlx-audio) version **0.4.7**.

**Note:** This model requires the S3Tokenizer weights from [mlx-community/S3TokenizerV2](https://huggingface.co/mlx-community/S3TokenizerV2), which will be downloaded automatically.

## Use with mlx-audio

```bash
pip install -U mlx-audio
```

### Command line

```bash
mlx_audio.tts.generate --model mlx-community/chatterbox-multilingual-v3 --text "Bonjour, voici Chatterbox sur MLX !" --ref_audio reference.wav --lang_code fr
```

### Python

```python
from mlx_audio.tts.generate import generate_audio

generate_audio(
    text="Bonjour, voici Chatterbox sur MLX !",
    model="mlx-community/chatterbox-multilingual-v3",
    ref_audio="reference.wav",
    lang_code="fr",
    file_prefix="output",
)
```