This AI Tool Lets You Separate Vocals from Songs With Ease

Deezer open-sourced Spleeter

Have you ever surfed across the internet for finding the karaoke version of your favorite song you would love to perform? You may have also wondered if there were any more comfortable ways to do this on your own? Well, your wishes have come true for karaoke versions of any songs, thanks to Deezer’s new audio separation library Spleeter. An AI that helps you separate vocals from the songs.

With Spleeter, you can separate vocals and instrumentals for any song you feed into it without having any in-depth knowledge of sound mixing. This AI tool can be lifesaving for all those DJs, who spend a lot of time doing so on the source tracks.

Deezer says their audio separation library is fast for separating vocals from soundtracks. They even claim Deezer’s Spleeter separates audio tracks 100x faster on GPU than in any real-time. Spleeter contains three pre-trained models for separating all those tricky vocals and others; bass, drums, vocals, and others; bass, drums, piano, vocals, and others.

However, If you’re interested to know how the results are, check out the sample generated by Andy Baio from Waxy below:

Led Zeppelin – “Whole Lotta Love”

Led Zeppelin (Vocals Only)

Led Zeppelin (Music Only)

The AI is not entirely perfect, but it does a decent job of isolating and separating tracks. It is entirely usable, in my opinion. “Spleeter is a neat tool, but in no way do we claim to have “solved” source separation. Hundreds of researchers and engineers working for decades have made the advances and built the tools on which Spleeter is based.”, wrote Deezer in a blog post.

Deezer has an open-sourced Spleeter on GitHub. You can download Spleeter on GitHub from here. All you got to do is provide an input audio file and wait for Spleeter to do its magic. However, make sure you follow the installation guide here and user manual here to use Spleeter with no hiccups.

So, what do you think of Spleeter? Tell us in the comments.