ChatTTS Deployment Guide

Windows Pre-packaged Version

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

Linux Source Code Deployment

1. Configure a python3.9+ environment.

2. Create an empty directory /data/chattts and execute 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 required, execute pip3 install torch torchaudio

   If CUDA acceleration is required, execute

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

   You also need to install CUDA11.8 ToolKit. Please search for the installation method yourself.

7. Execute python3 app.py to start. The browser window will open automatically, with the default address http://127.0.0.1:9966.

MacOS Source Code Deployment

1. Configure a python3.9+ environment, install git, and execute the command brew install git [email protected] Continue to execute

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

2. Create an empty directory /data/chattts and execute 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. Execute python3 app.py to start. The browser window will open automatically, with the default address http://127.0.0.1:9966.

Windows Source Code Deployment

1. Download python3.9+, and make sure to check Add Python to environment variables during installation.

2. Download and install git, 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 and enter it. Enter cmd in the address bar and press Enter. In the pop-up cmd window, execute the command git clone https://github.com/jianchang512/chatTTS-ui .

4. Create a virtual environment, execute the command python -m venv venv

5. Activate the virtual environment, execute .\venv\scripts\activate

6. Install dependencies, execute pip install -r requirements.txt

7. If CUDA acceleration is not required, execute pip install torch torchaudio

   If CUDA acceleration is required, execute

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

   You also need to install CUDA11.8 ToolKit. Please search for the installation method yourself.

8. Execute python app.py to start. The browser window will open automatically, with the default address http://127.0.0.1:9966.

Common Issues

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

After changing to downloading the model from modelscope, the following prompt appears when running successfully: 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 solve the problem.

2. If an error occurs under mac, please try

   brew install libomp

3. Prompt not support python3.12+

   Please downgrade to version 3.10