---
title: Kokoro-82M-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Kokoro-82M-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Kokoro-82M-8bit.md"
repository: mlx-community/Kokoro-82M-8bit
last_updated: 2026-01-07
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
base_model:
  - yl4579/StyleTTS2-LJSpeech
base_model_relation: finetune
parameters: 79.4M
tensor_type:
  - F32
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 1513
stars: 0
---

# Kokoro-82M-8bit

> Kokoro-82M-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Kokoro-82M-8bit This model was converted to MLX format from hexagrad/Kokoro-82M using mlx-audio version 0.0.1. Refer to the original model card for more details on the model. Use with mlx

mlx-community/Kokoro-82M-8bit 是 ModelScope 魔搭社区上的 79.4M 参数text-to-speech模型，采用 apache-2.0 许可，基于 yl4579/StyleTTS2-LJSpeech 构建。

- **Repository**: mlx-community/Kokoro-82M-8bit
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 79.4M
- **Base model**: yl4579/StyleTTS2-LJSpeech
- **Downloads**: 1513
- **Stars**: 0
- **Last updated**: 2026-01-07

Source: https://www.modelscope.cn/models/mlx-community/Kokoro-82M-8bit

---

# mlx-community/Kokoro-82M-8bit
This model was converted to MLX format from [`hexagrad/Kokoro-82M`]() using mlx-audio version **0.0.1**.
Refer to the [original model card](https://huggingface.co/hexagrad/Kokoro-82M) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_audio.tts.generate --model mlx-community/Kokoro-82M-8bit --text "Hello world"
```