This is a simple UI that utilize's Coqui's XTTSv2 paired with RVC functionality to improve output quality.
Clone this repository:
git clone https://github.com/Vali-98/XTTS-RVC-UI.git
It is recommended to create a venv.
Then, install the requirements:
pip install -r requirements.txt
If you have a CUDA device available, it is also recommended to install PyTorch with CUDA for faster conversions.
pip install torch==2.1.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118
Then run start.bat
, start.sh
or simply python app.py
This will create the following folders within the project:
\models\xtts
\rvcs
\voices
\models
. This will be approximately ~2.27GB.\models\xtts
.\rvcs
. Rename them as needed. If an identically named .index file exists in \rvcs
, it will also be used.\voices