mcp_opendaw_transcribe_melody
Transcribe a monophonic audio melody into MIDI notes on a DAW track using pitch detection, frequency-to-MIDI conversion, and note grouping.
Instructions
Transcribe monophonic melody from an audio file into MIDI notes on a DAW track.
Audio-to-MIDI melody transcription — converts a monophonic instrument recording (bass, vocal, lead synth, horn) into MIDI notes. Pure Python, no external deps.
Pipeline:
Parse WAV file
Frame-by-frame autocorrelation pitch detection
Convert frequency → MIDI pitch (with cents deviation for tuning accuracy)
Group consecutive similar-pitch frames into sustained notes
Estimate velocity from frame energy
Create MIDI notes on the specified track via create_notes_batch
Use cases:
Extract a bass line from a Suno track → reuse as MIDI
Transcribe a vocal melody → harmonize or transform
Capture a horn line → arrange for other instruments
Convert any monophonic audio to editable MIDI
filename: WAV file name (in exports dir) or absolute path. bpm: Tempo for beat conversion (0 = auto-detect via detect_bpm). unit_index: AU index with note tracks. track_index: Track to place transcribed notes.
Returns: notes created, note count, bpm, duration, average clarity.
Example:
Transcribe a bass line from a Suno track
result = transcribe_melody("suno_bass.wav", bpm=120)
Auto-detect BPM
result = transcribe_melody("vocal.wav") # bpm=0 → auto-detect
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| bpm | No | ||
| filename | Yes | ||
| unit_index | No | ||
| track_index | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |