An extension for the text-generation-webui by oobabooga that uses Piper for fast voice generation.
This project is a Web user interface (WebUI) for text generation using Gradio and a Piper text-to-speech (TTS) model. The main objective is to provide a user-friendly experience for text generation with audio.
outputs
folder.Selected settings are saved in a JSON file settings.json
so that the user can retrieve his preferences each time he uses the device.
Make sure you install all necessary dependencies and configure your environment according to the project instructions.
git clone https://github.com/tijo95/piper_tts.git
For windows, download https://github.com/rhasspy/piper/releases/download/2023.11.14-2/piper_windows_amd64.zip
Unzip all contents into piper_tts
For linux:
cd piper_tts/
wget https://github.com/rhasspy/piper/releases/download/2023.11.14-2/piper_linux_x86_64.tar.gz
tar -xvf piper_linux_x86_64.tar.gz
rm piper_linux_x86_64.tar.gz
Download the .onnx model and their .json files and place them in the piper_tts/model
directory.
The models are available at this address: https://huggingface.co/rhasspy/piper-voices/tree/v1.0.0
Run the main script and have fun surprising your AI.
Contributions are welcome! Feel free to open an issue or propose an extraction request to improve this project.
Github : https://github.com/rhasspy/piper#running-in-python
Listen to voice samples : https://rhasspy.github.io/piper-samples