Realtime Voice Changer is a web-based application for real-time voice modification. This project consists of a React frontend, a Node.js backend server, and a Python-based voice processing server.
- Real-time voice input and modification
- Support for various voice modification models (RVC, ONNX)
- Easy control through web interface
- Server status monitoring
- Frontend: React
- Backend: Node.js, Express
- Voice Processing Server: Python, FastAPI
- Real-time Communication: WebSocket
- Voice Processing: ONNX Runtime, PyTorch
-
Clone the repository:
git clone https://github.com/sioaeko/OpenVoiceChanger.git cd OpenVoiceChanger -
Install dependencies:
chmod x install_dependencies.sh ./install_dependencies.shThis script installs all dependencies for the client, server, and Python environment.
-
Start the Node.js server:
cd server npm start -
Start the Python server:
cd python_server source venv/bin/activate # On Windows: venv\Scripts\activate python python_server.py -
Start the client:
cd client npm start -
Access the web interface at
http://localhost:3000
- Click the "start" button in the "Server Control" section of the web interface to start the server.
- Select the desired model and settings in the "Model Setting" section.
- Choose audio input and output devices in the "Device Setting" section.
- Click the "Record" button to start voice input.
- The modified voice will be output in real-time.
OpenVoiceChanger/
│
├── client/ # React frontend
│ ├── src/
│ │ ├── components/
│ │ │ └── VoiceChangerDesktop.js
│ │ ├── App.js
│ │ └── index.js
│ └── package.json
│
├── server/ # Node.js backend
│ ├── models/
│ ├── rvc-model.js
│ ├── onnx-model.js
│ ├── index.js
│ └── package.json
│
├── python_server/ # Python voice processing server
│ ├── python_server.py
│ └── requirements.txt
│
├── install_dependencies.sh
└── README.md
This project is licensed under the MIT License. For more details, refer to the LICENSE file.