Skip to content

Audio Separation with KaraFan

KaraFan is a powerful, free tool for separating audio sources. It can extract vocals from a song, remove instruments, and more. This makes it an excellent tool for creating clean datasets for voice model training.

For more information, you can visit the official KaraFan GitHub repository.

You can run KaraFan on your local computer or on Google Colab.

  1. Create a folder on your PC where you want to store the KaraFan project.
  2. Download and install Python 3.11. If you have another version of Python installed, you must uninstall it first.
  3. Download the KaraFan installer (right-click and save as Install.bat).
  4. On Windows 11, you may need to unblock the .bat file. Right-click the file, go to Properties, and click the Unlock button in the General tab.
  5. Run the Install.bat file with administrator rights.
  6. Once the installation is complete, run Setup.py by double-clicking on it.
  7. You can now launch KaraFan by double-clicking on KaraFan.pyw.
  1. Place the audio file you want to process in the Music folder (either locally or in your Google Drive).
  2. In the KaraFan interface, enter the path to your audio file and the path to your output folder.
  3. Choose the desired settings. The recommended settings for separating vocals are shown below.
  4. Click the Start button to begin the separation process.
  5. When the process is complete, you’ll find the separated audio files in your output folder. The main vocal track is usually named Vocal Final.
To separate vocalsTo separate other audio sources
A screenshot of the recommended KaraFan settings for separating vocals.A screenshot of the recommended KaraFan settings for separating other audio sources.

To update your local installation of KaraFan, simply run the Setup.py file again.