---
title: Chatterbox-TTS-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Chatterbox-TTS-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Chatterbox-TTS-4bit.md"
repository: mlx-community/Chatterbox-TTS-4bit
last_updated: 2025-12-06
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - chatterbox
base_model:
  - ResembleAI/chatterbox
base_model_relation: finetune
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 64
stars: 0
tags:
  - mlx
---

# Chatterbox-TTS-4bit

> Chatterbox-TTS-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Chatterbox-TTS-4bit

mlx-community/Chatterbox-TTS-4bit 是 ModelScope 魔搭社区上的text-to-speech模型，基于 ResembleAI/chatterbox 构建。

- **Repository**: mlx-community/Chatterbox-TTS-4bit
- **Tasks**: text-to-speech
- **Base model**: ResembleAI/chatterbox
- **Tags**: mlx
- **Downloads**: 64
- **Stars**: 0
- **Last updated**: 2025-12-06

Source: https://www.modelscope.cn/models/mlx-community/Chatterbox-TTS-4bit

---

# mlx-community/Chatterbox-TTS-4bit

This model was converted to MLX format from [ResembleAI/chatterbox](https://huggingface.co/ResembleAI/chatterbox) using [mlx-audio-plus](https://github.com/DePasqualeOrg/mlx-audio-plus) version **0.1.0**.

**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-plus

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

### Command line

```bash
mlx_audio.tts --model mlx-community/Chatterbox-TTS-4bit --text "Hello, this is Chatterbox on MLX!" --ref_audio reference.wav --ref_text "."
```

### Python

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

generate_audio(
    text="Hello, this is Chatterbox on MLX!",
    model="mlx-community/Chatterbox-TTS-4bit",
    ref_audio="reference.wav",
    ref_text=".",
    file_prefix="output",
)
```