Costs $1 from your balance per run.

Audio to MIDI

Transcribe audio into a MIDI file, plus a music analysis of the transcription (key with confidence, pitch range, note density, polyphony) — measured, not guessed. Costs $1. Often performs better on stem isolations — running Stem Separation first is recommended; if the input looks like a full mix the response carries a dense-mix flag saying so. By default every instrument group is transcribed; pass a focused instruments list (e.g. ['voice'] for vocal melodies, ['bass'] for bass lines) for cleaner results on stems. Returns one .mid file with its music_analysis.

How it works

Drop a file or paste a direct link, pick what you want, confirm. Runs take about 5 minutes. Stems come back as individual WAV files plus a zip of everything, with download links valid for an hour. Failed runs are refunded automatically.

Pick by ear, not by benchmark

Benchmarks do not always match your material. Run the same song through several models at once, listen to the results side by side, and keep the one that sounds right. Failed models refund automatically so you only pay for stems you receive.

Use it from your assistant

Music Assistant, our MCP server, runs the same operations from inside Claude, ChatGPT, Cursor, Zapier, and Make. One URL, one free key.

Connect Music Assistant