Audio Separator
A command-line tool and Python package that separates songs into stems using pre-trained UVR models.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About Audio Separator
Audio Separator splits a song into stems such as vocals and instrumental. It uses a range of pre-trained separation models, mostly from Ultimate Vocal Remover (UVR), and can be run from the command line or imported as a Python package.
It suits people who want UVR-quality separation in scripts or batch jobs rather than through a graphical app, for example to make karaoke tracks. The project is actively developed on GitHub, with around 1,400 stars and several hundred commits.
Strengths
- Uses many pre-trained UVR separation models
- Works from the command line or as a Python library
- Suited to scripting and batch processing
Limitations
- No graphical interface
- Needs a Python environment and model downloads
Details
- Pricing
- FreeFree and open source.
- License
- MIT
- Developer
- Nomad Karaoke
- Platforms
- Command line
- How it runs
- Downloadable app
- Account
- Not required
- Best suited for
- Scripted vocal and instrumental separation, such as making karaoke tracks
- Categories
- Audio tools, CLI tools, AI music
- Last verified
- Added
Alternatives to Audio Separator
Compare allSoftware that can replace Audio Separator for an important use case, and what changes if you switch.
Ultimate Vocal Remover
Desktop app that separates vocals and instruments in songs using neural network models on your computer.
Ultimate Vocal Remover is the MIT-licensed desktop app behind the UVR models, offering a graphical interface on Windows, macOS and Linux instead of command-line scripting.
LALAL.AI
An AI service that splits songs into vocal and instrument stems and cleans up voice recordings.
LALAL.AI is a paid, closed-source service on web, desktop and mobile that separates many stem types, with web processing uploading your files.
MVSEP
An online service that separates music into vocals, drums, bass and other stems using many AI models.
MVSEP is a hosted freemium service with many separation models and ratings, so audio is processed on its servers rather than locally.
Moises
An AI app for musicians that separates songs into stems for practice and remixing.
Moises is a proprietary hosted app for web and mobile that separates stems for practice, with paid tiers.
Vocal Remover
A free web tool that splits a song into a vocal track and an instrumental track.
Vocal Remover is a free web tool that splits songs into vocals and instrumental in the browser, with no Python setup but uploads required.
Fadr
A browser-based set of AI music tools for splitting songs into stems, remixing and detecting chords.
Fadr is a freemium browser tool with unlimited basic stem splitting plus chord and tempo detection, with songs uploaded to its servers.
Audio Separator as an alternative
Listings that name Audio Separator as an alternative.
AudioShake
An AI service that separates music and film audio into stems such as vocals, instruments and dialogue.
Audio Separator is a free MIT-licensed command-line tool and Python package using UVR models, suited to scripted batch separation but with no graphical interface.
Similar software
Related functionality, not necessarily a direct replacement.
RVC WebUI
A local web interface for training and using retrieval-based voice conversion models.
Basic Pitch
A free, open-source audio-to-MIDI converter from Spotify with pitch bend detection, usable in the browser.
