---
title: chatterbox-multilingual-v3
canonical_url: "https://www.modelscope.cn/models/mlx-community/chatterbox-multilingual-v3"
md_url: "https://www.modelscope.cn/models/mlx-community/chatterbox-multilingual-v3.md"
repository: mlx-community/chatterbox-multilingual-v3
last_updated: 2026-08-01
license: mit
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - chatterbox
base_model:
  - ResembleAI/chatterbox
base_model_relation: finetune
parameters: 677.7M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ar
  - da
  - de
  - el
  - en
  - es
  - fi
  - fr
  - he
  - hi
  - it
  - ja
  - ko
  - ms
  - nl
  - no
  - pl
  - pt
  - ru
  - sv
  - sw
  - tr
  - zh
downloads: 2348
stars: 0
tags:
  - mlx
  - text-to-speech
  - voice-cloning
---

# chatterbox-multilingual-v3

> chatterbox-multilingual-v3 - mlx-community 在 ModelScope 开源的模型。mlx-community/chatterbox-multilingual-v3

mlx-community/chatterbox-multilingual-v3 是 ModelScope 魔搭社区上的 677.7M 参数text-to-speech模型，采用 mit 许可，基于 ResembleAI/chatterbox 构建。

- **Repository**: mlx-community/chatterbox-multilingual-v3
- **License**: mit
- **Tasks**: text-to-speech
- **Parameters**: 677.7M
- **Base model**: ResembleAI/chatterbox
- **Tags**: mlx, text-to-speech, voice-cloning
- **Downloads**: 2348
- **Stars**: 0
- **Last updated**: 2026-08-01

Source: https://www.modelscope.cn/models/mlx-community/chatterbox-multilingual-v3

---

# 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",
)
```