Beatlearning: generate osu! beatmaps from audio

Understand the project

Practical overview

Use it when researching or prototyping audio-to-beatmap generation for osu!, particularly if you can work with Python and Jupyter notebooks.

Before you choose

The documented pipeline currently supports osu! beatmaps, not a broad set of rhythm games.
The README says the generator supports simple hit objects but not sliders.
Local setup requires Python 3.12 and installing the repository's listed dependencies.
The README recommends GPU access for the Colab route because CPU song conversion takes a long time.
The project asks users to use only music for which they have rights and to label AI involvement in generated content.

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

Prepare the documented Python environment and access Beatlearning's Jupyter notebooks.

From the repository directory, create a virtual environment with the command below.
Documented command
```
python3 -m venv venv
```
Activate it with source venv/bin/activate, or venv\Scripts\activate on Windows.
Install the required libraries with the command below.
Documented command
```
pip3 install -r requirements.txt
```
Start Jupyter with jupyter notebook to access the example notebooks.

A prepared local environment with access to the repository's example notebooks.

The README does not provide a complete generation walkthrough.
The current pipeline targets osu! beatmaps; the project describes the generator as work in progress, with simple hit objects and no slider support.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 17 October 2026
Original website title: sedthh/BeatLearning · Official homepage title · retained in its source language