Muse is a free, open-source desktop app that turns recorded or uploaded audio into MIDI, with separate workflows for piano and multiple instruments. Its piano mode isolates piano from a mix, transcribes the notes, and divides them between left and right hands. Multi-instrument mode can transcribe up to 13 tracks in one pass without source separation. Audio can be recorded through a microphone or imported as MP3, WAV, OGG, or FLAC. Built-in playback uses a grand piano synth, with per-track mute and solo controls. Processing runs locally, and the maker says audio never leaves the user’s machine. GPU acceleration supports CUDA and Apple Silicon MPS. Builds are listed for Windows, macOS on Apple Silicon and Intel, and Linux Debian/Ubuntu and AppImage. Setup requires Python 3.10 or later and downloads about 3 GB of machine-learning models on first run. The maker estimates multi-instrument CPU processing at roughly two minutes per 30 seconds of audio; MIDI is available now, while MusicXML export is on the roadmap.
Who it is for
Muse suits musicians or arrangers who want to turn recordings into editable MIDI on a desktop computer. It may be a better fit for users able to meet its Python and model-download requirements, especially if they have supported GPU acceleration.
What is good
- Transcribes up to 13 instrument tracks in one pass.
- Accepts microphone recordings and four audio formats.
- Processing runs locally, according to the maker.
- Supports CUDA and Apple Silicon MPS acceleration.
- Available for Windows, macOS, and Linux.
What to know first
- First run downloads about 3 GB of models.
- Requires Python 3.10 or later.
- CPU processing is estimated at roughly two minutes per 30 seconds.
- MusicXML export is on the roadmap, not available now.
Verdict
Muse offers distinct piano and multi-instrument MIDI workflows, and keeps processing on the desktop according to its maker. Account for the setup download and CPU time, and note that its current output is MIDI rather than MusicXML.
Muse plans and pricing
All plansCompared on AI music generators
- Free plan
- Yes
- Polyphonic transcription
- Yes
- Notation export
- No
- Audio input formats
- MP3, WAV, OGG, FLAC
