Skip to content

Vocal remover

A song split by AI into the singing voice and everything else, both ready to download, for karaoke, covers, practice or a video background.

The vocal remover with a song loaded, ready to split it into the voice and the accompaniment

Guide

How to remove the vocals from a song

What the vocal remover does

A finished song is a single mix: the voice, the drums, the bass and the rest are blended into one track, and an equalizer cannot take the voice out without taking half the music with it. Separating them needs a model that has learned what each one sounds like.

This tool sends your song to our server, where an AI model splits it into two tracks, the vocals and the accompaniment, and gives you both as MP3. It is used for karaoke versions, covers, singing practice, remixes and backing tracks for videos.

How to use it

  1. Sign in with your free account and drop your song or video on the box above.
  2. Press Split the song: the file is sent and waits for its turn.
  3. Wait while the voice and the music are separated, usually two to three times the song's length; the page shows how it is going.
  4. Listen to the vocals and to the accompaniment on the page.
  5. Download the track you need, or both.

How it works

The separation is done by Demucs, an open-source model published by Meta AI research, in its hybrid transformer version. It looks at the song both as a waveform and as a spectrogram, the picture of its frequencies over time, and predicts which part of the sound belongs to the voice. Everything that is not the voice becomes the accompaniment.

The song is converted to 44.1 kHz stereo, split on our server CPU one song at a time, and both tracks are encoded as MP3 at 192 kbps. The song is erased as soon as it has been split, and the two parts within 15 minutes.

What to expect

  • Very clean: pop, rock, hip-hop and most songs with one clear lead voice.
  • Good, with traces: heavy reverb, doubled vocals and backing choirs, which can leave a faint echo of the voice.
  • Harder: live recordings, old mono recordings and instruments that sing in the voice range, such as a lead guitar or a violin.

Limits to know

Each account can split 3 songs a day, plus 2 for each friend who joins through your invite link, because each song keeps our server busy for minutes. A song can be up to 5 minutes long and 60 MB, so an MP3 is better than an uncompressed WAV of a long track.

The tool separates sound; it does not grant rights to the music. Practice and private karaoke are fine with any song, but what you publish should use music you own or have permission to use.

Using the tracks in a video

An instrumental makes a good background for a short video, under your own voice. If the voice was recorded on a phone, the background noise remover cleans it first, and the auto caption generator writes the captions once the video is put together.

Questions about the vocal remover

How does the vocal remover work?
It uses Demucs, an open-source model from Meta AI research that has learned what voices and instruments sound like from thousands of songs. It runs on our own server and separates the song into two tracks: the vocals and everything else.
What do I get back?
Two MP3 files at 192 kbps: the accompaniment, which is the song without the voice, and the vocals alone. You can listen to both on the page before you download them.
How long does it take?
Usually two to three times the song's length, so about 10 minutes for a 4-minute song, because the separation runs on the CPU of our server and one song is processed at a time. The page shows your place in line and keeps you informed until both files are ready.
Is my song kept on your server?
No. The song is erased as soon as it has been split, and the two parts are erased within 15 minutes, which leaves time for your browser to fetch them. Our records keep only the size of the file, never its name or its content.
Why do I need an account?
Separating a song keeps our server busy for minutes, so each person has 3 songs a day, plus 2 more for each friend who joins through your invite link. A free account with Google or an e-mail address is how they are counted.
Will the instrumental be perfect?
It is very clean on most pop, rock and hip-hop songs. Traces of the voice can remain in heavy reverb, choirs or backing vocals, and instruments that share the voice range, such as a lead guitar, can lose a little.
Which files and lengths are accepted?
MP3, M4A, WAV, FLAC and OGG songs, and also videos, whose sound is used. A song can be up to 5 minutes long and 60 MB in size.
Can I use the result in my videos?
The tool splits the file; it does not change who owns the music. Use it freely for practice and private karaoke, and for anything you publish, use songs you own or have permission to use.

Last updated:

Was this page helpful?