OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Neuralnote

Neuralnote is an open-source audio plugin and standalone application that uses deep-learning models to transcribe audio into MIDI for digital audio workstation workflows.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Neuralnote — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Neuralnote when a recorded performance or audio file needs to become MIDI for editing in a DAW. Select the known instruments when possible; use Automatic when they are not known.

Who it is for

  • Music producers who want to turn audio on a DAW track into editable MIDI.
  • Musicians who want to transcribe live input or supported audio files.
  • Developers interested in an Apache-2.0 C++ audio-to-MIDI project.

Documented uses

  • Record or import audio and generate MIDI notes.
  • Transcribe multiple instruments in a full mix, with notes grouped by instrument.
  • Preview the transcription with the built-in synth and adjust instrument levels.
  • Export the result by dragging MIDI to a DAW MIDI track or saving a MIDI file.
Before you choose

Requirements & limits

The project documents installers for Apple Silicon macOS and Windows x64. The macOS installer includes standalone, VST3 and AU; the Windows installer includes standalone and VST3. Prebuilt Linux binaries are described as forthcoming, with source builds as the interim option. The project is open source under Apache-2.0.

  • Neuralnote supports VST3, AU and standalone use, but the documented installer formats vary by operating system.
  • The model is downloaded separately; small, medium and large downloads are approximately 210 MB, 620 MB and 2.7 GB.
  • Model size trades speed for quality. The project strongly recommends a GPU for medium and large models.
  • Transcription runs locally; internet access is used for model downloads and update checks.
  • The project reports that testing covers only a few machines and GPUs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Transcribe audio and export MIDI

Convert a DAW track, live recording or supported audio file into MIDI for further editing.

Before you start

  • Neuralnote as a VST3, AU or standalone app.
  • A transcription model downloaded within Neuralnote.
  • A source track or audio file; supported file types are WAV, AIFF, FLAC, MP3 and OGG Vorbis.

Steps

  1. Apply the AudioFX plugin to the track, record input, or drop a supported audio file onto the plugin.

  2. Choose the instruments to transcribe, or select Automatic.

  3. Click Transcribe and monitor progress; transcription runs in the background.

  4. Preview the decoded result and adjust the source-to-synth mix or instrument levels.

  5. Drag the MIDI onto a MIDI track or save it as a MIDI file.

Expected outcome

An editable MIDI transcription that can be previewed in Neuralnote and moved to a MIDI track or saved.

Guide limitations

  • The transcription model is not included and must be downloaded on first use.
  • The project says transcription quality tends to improve when the correct instruments are selected.
  • Speed depends on model size and hardware; a GPU is strongly recommended for medium and large models.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
DamRsn/NeuralNote · Official homepage title · retained in its source language
How we review sourcesSuggest a correction