stem-separator is an open-source command-line tool that uses AI models (Demucs) to separate audio files into individual stems such as vocals, drums, and bass. It is designed for audio engineers, musicians, and producers who need to isolate or extract specific elements from music tracks.
In the AI & ML space, stem-separator takes a focused approach. It focuses on extracting individual instrument or vocal tracks from mixed audio files using AI. It is built as an open-source project for audio engineers and music producers. stem-separator is open source under the MIT license. stem-separator is available on the command line, and it can be self-hosted.
It is developed by Su1ph3r, and the product first shipped in 2025. Development happens publicly on GitHub with 3 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — stem-separator occupies a relatively distinct niche. Key capabilities include audio separation, stem extraction, and AI-powered.
Latest indexed changes and source events
stem-separator discovered by the PulseGate indexer
Other apps tracked under the same category.
