Audiola vs Pymss

Audiola is a free desktop audio studio for Windows, macOS, and Linux. It separates songs into vocals, drums, bass, guitar, piano, and other stems with Demucs running locally, without cloud processing or uploads. The multitrack studio supports cutting, moving, fading, looping, undo history, snapping, and effects. Karaoke view shows lyrics and the original melody, scores singing, and can tune a recorded take toward that melody. Mastering tools provide EQ, compression, EBU R128 loudness targeting, live A/B comparison, and 14 profiles. Users can create local or ElevenLabs voice profiles, swap a clip’s voice, and generate speech from text; the maker advises using only owned or licensed voices. Tracks can be placed in a 7.1.4 spatial bed, which the maker says can be exported. Exports include WAV, MP3, and AAC-M4A. A contact form accepts questions and reports without an account.

Pymss is an open-source music source-separation toolchain that runs on the user's own machine and separates audio into vocals, drums, bass, and other stems. Its Studio desktop workspace handles model management, batch jobs, and stem editing. Users can import files or folders, choose a downloaded model, configure inference, and queue work. Studio can browse, download, resume, and delete model files, with storage cleanup controls. Waveform previews, mix controls, saved projects, and stem export support work on the results. Pymss can chain models so each workflow step uses the preceding step's output. The inference package lists WAV, FLAC, MP3, M4A, AAC, Opus, Vorbis, and Ogg output. Other components include ComfyUI custom nodes, a VST3 ARA plugin for compatible DAWs, and a browser interface bundled with the server. The ARA plugin provides per-stem mute and solo controls; its README gives Reaper and Studio One as host examples. The repositories have separate licenses: Studio is listed under AGPL-3.0 and the inference package under MIT. Studio remains at an early development stage, and changes between versions may break things.