Spleeter
Spleeter is a Deezer audio source parsing library with pre-trained models developed using Python and TensorFlow. It can split audio files into 2, 4, or 5 different channels, including vocals, accompaniments, drums, bass, piano, and other instruments. In addition to being available from the command line, it can be integrated into the development processes as a Python library and can go far above the real-time processing speed on GPU.
Spleeter
95deezer · Music & Audio Technology
Common commercial products in this category: Adobe Audition, Ableton Live, Spotify
- You can split audio files into vocal and instrument components.
- Using pre-trained models, you can perform a 2, 4 or 5 channel stem parsing.
- You can use the library from the command line or by integrating it into your own Python development stream.
- • NeutralHacker News
Spleeter: Extract voice, piano, drums, etc. from any music track
“I encoded the source in MP3 for your convenience. But the source that I fed into Spleeter was FLAC. Edit: I uploaded the original FLAC to my web server last night, before I decided that MP3 would be more convenient:”
- ↑ PositiveHacker News
Spleeter – Music Source-Separation Engine
“I often have voice recordings with a lot of background noise (e.g. a public lecture in a room with poor acoustics, recorded from a phone in the audience — there's usually sounds of paper rustling, noises from the street, etc). Is this "source-separation" the sort of thing that…”
Verified against README · Oct 26, 2026 · source
My note
Alternative pages
More in: Music & Audio Technology
- mediapipe★ 37,481 · today
- howler.js★ 25,422 · 11 mo ago
- AudioCraft (Meta)★ 23,778 · 8 mo ago
- Beets★ 15,873 · today
- speechbrain★ 11,914 · 16 days ago
- PyDub★ 9,804 · 7 mo ago