Clone your voice and simple text to speech with xtts v2 using a gradio UI
3.0K
Based on: https://github.com/daswer123/xtts-webui
Tutorial (german): https://youtu.be/QCI22uxmsXY
Running the image with docker run command:
docker run --name xtts --gpus all -v C:\Playground\XTTS\models:/venv/xtts/models -v C:\Playground\XTTS\output:/venv/xtts/output -v C:\Playground\XTTS\cache:/root/.cache/ -v C:\Playground\XTTS\finetuned_models:/venv/xtts/finetuned_models -p 7860:7860 aladdin1234/xtts-webui:0.2
Access gradio page at http://127.0.0.1:7860 (or http://localhost:7860) in your preferred browser once started or use the gradio URL (see logs).
Only runs with Nvidia CUDA GPUs
Replace local storage paths with your own.
RVC and OpenVoice do not work (yet)
Content type
Image
Digest
sha256:1f8366a7c…
Size
14.7 GB
Last updated
over 2 years ago
docker pull aladdin1234/xtts-webui:0.2