Vocal Extractor UI is a simple web-based interface for extracting vocals from .mp3 or .wav audio files using Demucs and Gradio.
It lets you process entire folders of music files and isolates the vocals automatically β perfect for remixing, karaoke, or audio analysis.
- β Extract vocals using Demucs (deep learning model)
- β Simple and intuitive Gradio-based interface
- β Process all audio files in a folder at once
- β Compatible with local machine or Google Colab (auto-detect)
Make sure you have:
- Python 3.8+
- pip
- Demucs
Linux/macOS:
git clone https://github.com/adigayung/vocal-extractor-ui
cd vocal-extractor-ui
chmod +x install.sh
bash install.sh
source venv/bin/activateWindows:
git clone https://github.com/adigayung/vocal-extractor-ui
cd vocal-extractor-ui
install.batπ§ͺ Run :
python main.pyβοΈ Run on Google Colab Copy the script into a Google Colab notebook
The app will automatically launch with a public URL using Gradio share=True
π License This project is open-source under the MIT License.