free-music-demixer is an AI-based music demixer that allows users to separate different instruments from a music recording into individual tracks. It is a web application that can be accessed for free and has no usage limits.
The demixing process is performed using the Open-Unmix AI model with pre-trained UMX-L weights. This tool runs locally in the user's browser and does not store any data.
It is important to note that while it will perform well on computers, it may run slowly on smartphones. Users can upload a song to the demixer and break it down into bass, drums, vocals, others, and karaoke using the AI model.
The demixing process is performed entirely in the user's browser, ensuring data privacy as files are never uploaded anywhere. The tool also supports batch demixing, although it is labeled as experimental. The free-music-demixer is developed and maintained by Sevag H, and support for the tool can be provided through GitHub Sponsors or PayPal.
Additionally, companies in the professional music field have the opportunity to advertise on this platform for targeted visibility within the music and technology community. Important limitations include restrictions on the commercial use of the resulting tracks and the need for patience during the demixing process as it may require significant CPU and memory resources.
Users are encouraged to report bugs or make feature requests through the project's issue page on GitHub. Input files can be in almost any audio format, but the resulting tracks will always be stereo WAV files with a sampling frequency of 44100 Hz.
