Skip to main content

Audio STEM Separation powered by Spleeter

Project description


Audio STEM Separation powered by Spleeter

Download Youtube Audio to WAV and Separate Stems

What is a stem?

Stems are the different components that make up a music, in most cases you have vocals, drums, bass, and other instrumentation. According to the current scientific status, there will never be an algorithm that restores the exact master tracks before mixing, but with machine learning some people have developed some methods for estimation. There are different approaches largely depending on how much spare time you have on your hands.

  1. Method: Train your own neural network & Build your own database: Not possible unless you have a lot of experience and a lot of work. (Use work synonomous for time because time and space are connected)

  2. Method: Train your own network with someone else's dataset, possible good results require a lot of experience + work

  3. Method: Use someone else's pretrained network, that is what the Audiostems Project is, It depends on the Spleeter Network developed by a team at

  4. Method: Use someone else's shitty website that requires you to login to process a reasonable amount of data.

As you can see the goal of this Project is to provide creative minds with the right tools. This is more like a toolbox.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

audiostems-1.0.1.tar.gz (4.8 kB view hashes)

Uploaded source

Built Distribution

audiostems-1.0.1-py3-none-any.whl (5.1 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page