ChatTTS Deployment Guide

Windows Pre-packaged Version

1. Download the compressed package from Releases, extract it, and double-click app.exe to use.

Source Code Deployment on Linux

1. Set up a Python 3.9+ environment.

2. Create an empty directory /data/chattts and run the command: cd /data/chattts && git clone https://github.com/jianchang512/chatTTS-ui .

3. Create a virtual environment: python3 -m venv venv

4. Activate the virtual environment: source ./venv/bin/activate

5. Install dependencies: pip3 install -r requirements.txt

6. If CUDA acceleration is not needed, run: pip3 install torch torchaudio

   If CUDA acceleration is required, run:

   pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu118
   pip install nvidia-cublas-cu11 nvidia-cudnn-cu11

   Additionally, install the CUDA 11.8 Toolkit. Please search for the installation method.

7. Run python3 app.py to start. It will automatically open a browser window at the default address http://127.0.0.1:9966.

Source Code Deployment on MacOS

1. Set up a Python 3.9+ environment and install Git by running: brew install git [email protected] Then continue with:

   export PATH="/usr/local/opt/[email protected]/bin:$PATH"
   source ~/.bash_profile
   source ~/.zshrc

2. Create an empty directory /data/chattts and run the command: cd /data/chattts && git clone https://github.com/jianchang512/chatTTS-ui .

3. Create a virtual environment: python3 -m venv venv

4. Activate the virtual environment: source ./venv/bin/activate

5. Install dependencies: pip3 install -r requirements.txt

6. Install torch: pip3 install torch torchaudio

7. Run python3 app.py to start. It will automatically open a browser window at the default address http://127.0.0.1:9966.

Source Code Deployment on Windows

1. Download Python 3.9+ and ensure to check Add Python to environment variables during installation.

2. Download and install Git from: https://github.com/git-for-windows/git/releases/download/v2.45.1.windows.1/Git-2.45.1-64-bit.exe

3. Create an empty folder D:/chattts, navigate to it, type cmd in the address bar and press Enter, then run: git clone https://github.com/jianchang512/chatTTS-ui .

4. Create a virtual environment: python -m venv venv

5. Activate the virtual environment: .\venv\scripts\activate

6. Install dependencies: pip install -r requirements.txt

7. If CUDA acceleration is not needed, run: pip install torch torchaudio

   If CUDA acceleration is required, run:

   pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu118

   Additionally, install the CUDA 11.8 Toolkit. Please search for the installation method.

8. Run python app.py to start. It will automatically open a browser window at the default address http://127.0.0.1:9966.

Common Issues

1. Missing spk_stat.pt after downloading the model from modelscope

   After switching to download the model from modelscope, you may encounter the error: AssertionError: Missing spk_stat.pt: **/pzc163/chatTTS/asset/spk_stat.pt

   Download spk_stat.pt from https://huggingface.co/2Noise/ChatTTS/blob/main/asset/spk_stat.pt and copy it to the asset directory to resolve the issue.

2. If errors occur on Mac, try:

   brew install libomp

3. If prompted that Python 3.12+ is not supported, downgrade to version 3.10.