Plain-AyI
← All projects
Speech & audio

Spleeter

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

Research-backed

What it does

Spleeter, from the music service Deezer, separates a recorded song into its parts. It can split it into two tracks (vocals and music), four (vocals, drums, bass, other) or five (adding piano).

It comes with already-trained AI models, so you can use it straight away. Its makers say it is very fast on a computer with a graphics card.

Its makers say its models are used inside several professional audio and DJ apps. It can be used from the command line, from Python code, with Docker, or tried online in Google Colab.

Who it's for

Musicians, DJs, karaoke fans, audio researchers and developers.

Can I use it without coding?

With some setup. Installed with Python and run from the command line. You can also try it in your browser through Google Colab. New to this? Start here.

Can I run it?

Cost
Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
Runs on
Mac, Windows, Cloud
Privacy
Your choice: run it on your device or use an online service
API key
Not needed

Try it

  1. Try it without installing anything using the project's Google Colab notebook.
  2. Or install ffmpeg and libsndfile, then install Spleeter with Python's package installer.
  3. Give it a song and it saves the vocals and the backing music as separate files.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it