A research team at the French streaming platform Deezer have released a new AI tool called Spleeter that can quickly isolate vocal and instrumental tracks, and separate a song into two, four, or five separate audio tracks.
The software was originally developed for research purposes, but was released on Monday, as an open-source package on GitHub.
Deezer have just unveiled Spleeter, the new AI tool that can quickly split mixed-down audio files into stems for vocals, drums, bass, and other elements.
While many techniques already exist to isolate vocal tracks from a mixed-down audio file, most are difficult, time-consuming, and/or low-quality. Spleeter makes it easier and faster than ever to split recorded tracks into stems for vocals, drums, bass, and other elements.
Spleeter is an audio separation library, for which there’s currently no graphical user interface, so users need to be able to understand command line prompts. However, because the software is open source, there’s no stopping any programmers from developing a streamlined user interface.
The technology is accessible for aspiring remixers, samplers, and karaoke lovers alike, and some seasoned producers are already talking about the incredible potential of the software.
Find out more about Spleeter here.