#123 · Primary category: Speech & Audio

NeuralNote

audio audio-plugin juce-framework machine-learning midi vst

Audio Plugin for Audio to MIDI transcription using deep learning.

Project last updated:01/16/25

GitHub Stars

2.9K

Forks

190

Contributors

5

License

Apache-2.0

Why we included this project

Turning a recorded performance into editable MIDI usually means transcribing by ear, but NeuralNote automates that step inside a digital audio workstation. It installs as a standard VST3 or AU effect, accepts live audio or dropped-in files, and produces polyphonic MIDI with pitch-bend detection. You can adjust sensitivity and quantization in the piano-roll view while the result plays back, then drag the finished transcription onto a MIDI track. Since the transcription engine is based on Spotify's basic-pitch model and the code and weights ship with the repo, you can also reuse that logic in your own tools. This is a self-contained way to go from sound to notation without leaving your DAW.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category