StemDeck

What StemDeck is

StemDeck separates songs into stems for practice, study, transcription, remixing, and other creative audio work. Its Demucs htdemucs_6s model separates vocals, drums, bass, guitar, piano, and other sounds. You can import MP3, WAV, FLAC, OGG/Opus, MP4, and M4A files, or use YouTube URLs. The workspace has waveform lanes, mute and solo controls, volume adjustment, and looping, with exports for individual stems or a custom mix. Song analysis includes BPM, key, scale, confidence, integrated LUFS, and sample peak level. StemDeck says processing runs locally and that the app does not transmit, store, cache, or redistribute audio. Internet access is needed for YouTube downloads and an initial model fetch of about 170 MB; the model is cached afterward. The project documents Docker and Unraid deployment, running the web server from source, and a local REST API. It is free, with no account, quota, uploads, or subscription, but handles one job at a time, supports up to six stems, and has no mobile app. Processing speed depends on local hardware.