Corona Virus - Please Be Careful

We're all going through a very hard time right now.
Let's all be responsible and do the right thing. Stay inside!

We'd rather see you all safe and healthy, together, and with family.

Thank you for using Splitter, we love you.

With love, from Sweden ❤️

PS: And stop hoarding goods. Our elderly and medical workers (true warriors) work hard and need to eat too.

UPDATE: All donations starting tomorrow (23 March) and forward will be used to buy N95 masks and sent to medical centers. Donate any amount you want.

Your file "_download_filename_" will automatically start to download in 3 seconds.
Your file "_in_progress_filename_" is still processing.

5 Stem Model
Drums, Bassline, Piano, Other, Vocals

2 Stem Model
Instrumental + Acapella


Accepting WAV, MP3, OGG, M4A, WMA, FLAC and MKA files, 0.5 MB to 50MB, up to 20 minutes.


We're working on it

This shouldn't take more than a minute.

Your email will be used exclusively to notify you, nothing else.

Thanks. We'll let you know when it's done.


How does this work?

Isolating instruments from music is now possible using AI, and Splitter is based on Deezer's open source research project Spleeter to accomplish this.

Currently a few different models are available; 2 stem, 4 stem and 5 stem models.

The 5 stem model for example, can extract vocals, drums, piano, bass and other (guitar, synths, etc...), while the 2 stem model extracts the instrumental and the vocals.

In the future we'll hopefully see more isolations.

What can I use this technology for?

This platform is intended to be just another tool in your toolbox.

Be careful when isolating and using unlicensed music. Splitter and it's team is not liable for any damages or misuse of Spleeter. You are responsible for your actions and we will work with music authors, artists, labels and publishers to prevent misuse and infringement of their copyrighted material if they make requests.

We assume and expect that you upload your own music only.


Splitter in it's basic functionality as a Deezer Spleeter service is 100% free and will remain free forever. No registration or email is required.
We might add a few features here and there to make it fullfilling to you as the end-user.

Any non Spleeter features will be part of Splitter Pro which is yet to be announced and is planned to be rolled out some time mid 2020 as a paid service with more tools, features and processing options.

If your organization needs to process audio, please contact our sales team.

If you would like to support the free version of Splitter, please do so by Donating.


We want Splitter to be straight forward to use. Select processing model, drop a song and enter your email to get notified.

If you're experiencing any issues or have questions, contact us via Twitter (do follow) or send us an Email.

What are models?

Simply put, the models are snapshots of how the AI should process the data.

What is the 11 kHz option?

It's just another setting to the model. Sometimes it gives better results, sometimes not.

Will there be more models in the future?


Is Splitter really FREE?


Splitter in it's basic functionality is 100% and we intend on keeping it that way. FOREVER!

Future versions of Splitter, which we'll call Splitter Plus and Splitter PRO will have more features and tools and will not be free, and we will make sure that they are affordable.

Why does it take some time to process my file?

As we mentioned earlier, computational power is an expense.

Anyone that uses Splitter Free will have their audio data processed through a shared set of servers.
These servers are what we call Community Servers.

If you want to process a larger set of data, please contact sales.

Users that use Splitter through our website can do so for free to some extent.
When organizations or individuals want to use Splitter for commercial purposes, they basically rent our software and hardware to enable their users to process audio.