voice-note-to-midi

Convert voice audio into quantized MIDI tracks for DAWs.

Updated Jan 29, 2026

Search Tags:#audio #quantization #machine-learning #midi #pitch-detection #key-detection #humming

Ready to run

npx skills add https://github.com/DanBennettUK/voice-note-to-midi --skill voice-note-to-midi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: voice-note-to-midi
Source: https://github.com/DanBennettUK/voice-note-to-midi/tree/main
Command: npx skills add https://github.com/DanBennettUK/voice-note-to-midi --skill voice-note-to-midi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert voice audio into quantized MIDI tracks for use in digital audio workstations, removing manual transcription and timing tasks.

Core Features & Use Cases

Stem Separation (HPSS) to isolate melodies from noise and background sounds.
ML-powered pitch detection using Spotify's Basic Pitch model to extract fundamental frequencies.
Automatic key detection and key-aware quantization for accurate musical output.
Post-processing steps including octave pruning, harmonic removal, and legato merging for clean MIDI output.
Real-world use cases: capture melodies from voice memos and export ready-to-edit MIDI for DAWs.

Quick Start

Run hum2midi on a sample WAV file to generate a MIDI file ready for editing.

Frequently Asked Questions about voice-note-to-midi

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert a voice memo to MIDI for my DAW?▼

To convert a voice memo to MIDI, you can use a pipeline that applies stem separation and pitch detection to extract melodies, automatically outputting a clean, quantized MIDI file ready for editing in digital audio workstations.

Can I transcribe humming into quantized MIDI automatically?▼

Yes, you can transcribe humming into quantized MIDI automatically by using machine-learning pitch estimation combined with key detection, which processes the audio to produce accurate musical timing and note data.

Does voice to MIDI conversion work with background noise in the recording?▼

Voice to MIDI conversion handles background noise by applying HPSS-based stem separation to isolate the melodic audio from unwanted sounds before running pitch detection and quantization.

Do I need Python to run audio to MIDI conversion?▼

Yes, you need Python 3.11 or higher to run the audio to MIDI conversion, along with the provided installation script to set up the environment and optional FFmpeg for processing audio files.

What is the best way to clean up pitch detection errors in generated MIDI?▼

The best way to clean up pitch detection errors in generated MIDI is to use post-processing steps like octave pruning, harmonic removal, and legato merging, ensuring the extracted notes are accurate and musically coherent.

Why does my extracted MIDI have timing issues?▼

Extracted MIDI can have timing issues if key-aware quantization is not applied; utilizing automatic key detection and post-processing aligns the extracted pitch data to a clean musical grid.