Skip to content

Split a song into parts

Demucs

SOTA stemming model for voice, drums, bass, guitar and more.

Made by Meta35 creditsper 5 s Pro
What it needs

Opens the audio studio with Demucs ready to use. You can look around as a guest. Running it takes the Pro plan or higher.

Sample output

What Demucs makes, what it needs and what you get

What it makes

Split a song into parts

Splits a song into separate tracks such as vocals, drums and bass.

What you need

  • The song to split

What you get

Separate audio tracks

  • WAV and MP3 files

About Demucs

Demucs splits a song into separate tracks such as vocals, drums and bass. It is made by Meta.

To use it, you provide the song to split. You get separate audio tracks. Options include WAV and MP3 files.

A 5 s result costs about 35 credits. Longer or shorter results cost in proportion, about 7 credits per second. It is included from the Pro plan and up. You run it in the audio studio, in your browser.

Best for

Typical uses for this kind of model.

  • Remixes and mashups
  • Karaoke and backing tracks
  • Isolating one instrument to study

How to use Demucs

  1. 1

    Add the song to split

    Upload your files, or pick them from your library. Nothing else is needed to start.

  2. 2

    Check the settings

    Pick the options you want. The cost updates as you choose, and is shown before you generate.

  3. 3

    Generate your audio clip

    Separate audio tracks. Your result appears in the studio, ready to download.

Other models for this job

Same job: split a song into parts. Compare before you choose.

See all models for this job
Audio Pro Open
Sam Audio Text-guidedSplit a song into parts

Audio separation with SAM Audio. Isolate any sound using natural language—professional-grade audio editing made simple for creators, researchers, and accessibility applications.

Open Source500 creditsper run