https://github.com/billwuhao/ComfyUI_MegaTTS3

Lightweight and Efficient, 🎧Ultra High-Quality Voice Cloning, Chinese and English.
https://github.com/billwuhao/ComfyUI_MegaTTS3

Last synced: 8 days ago
JSON representation

Lightweight and Efficient, 🎧Ultra High-Quality Voice Cloning, Chinese and English.

• Host: GitHub
• URL: https://github.com/billwuhao/ComfyUI_MegaTTS3
• Owner: billwuhao
• License: apache-2.0
• Created: 2025-04-06T05:37:57.000Z (12 days ago)
• Default Branch: main
• Last Pushed: 2025-04-06T07:14:01.000Z (12 days ago)
• Last Synced: 2025-04-06T07:32:09.244Z (12 days ago)
• Language: Python
• Homepage:
• Size: 5.86 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README-CN.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-comfyui - **MW-ComfyUI_MegaTTS3** - Quality Voice Cloning, Chinese and English. (All Workflows Sorted by GitHub Stars)

README

        
[中文](README-CN.md) | [English](README.md) 

# ComfyUI 的 MegaTTS3 声音克隆节点

声音克隆质量非常高, 支持中英文, 并可跨语言克隆.

![image](https://github.com/billwuhao/ComfyUI_MegaTTS3/blob/main/images/2025-04-06_13-52-57.png)

## 📣 更新

[2025-04-06]⚒️: 发布 v1.0.0.

## 安装

```

cd ComfyUI/custom_nodes

git clone https://github.com/billwuhao/ComfyUI_MegaTTS3.git

cd ComfyUI_MegaTTS3

pip install -r requirements.txt

# python_embeded

./python_embeded/python.exe -m pip install -r requirements.txt

```

## 模型下载

- 模型和音色需要手动下载放到 `ComfyUI\models\TTS` 路径下:

[MegaTTS3](https://huggingface.co/ByteDance/MegaTTS3/tree/main)  整个文件夹全部下载放到 `TTS` 文件夹下.

`MegaTTS3` 文件夹中新建 `speakers` 文件夹, 从 [Google drive](https://drive.google.com/drive/folders/1QhcHWcy20JfqWjgqZX1YM3I6i9u4oNlr) 下载所有 `.wav` 和 `.npy` 文件, 放到 `speakers` 文件夹下.

![image](https://github.com/billwuhao/ComfyUI_MegaTTS3/blob/main/images/2025-04-06_14-49-12.png)

## 鸣谢

- [MegaTTS3](https://github.com/bytedance/MegaTTS3)