Latest Release v2.0

Released on June 8, 2025

This release includes volume control & FluidSynth integration, enhanced transport controls, and various bug fixes for improved stability.

Windows macOS Linux
Windows
macOS
Linux
Source Code

Windows Installation

MIDI-GEN v2.0 - Portable

AI-Powered Music Generation Tool. No installation required - portable application with built-in Python runtime.

Download Portable ZIP

Minimum Requirements:

  • Windows 10/11 (64-bit)
  • 4 GB RAM
  • 2 GB free disk space
  • Internet connection (for initial setup)

Recommended for GPU Mode:

  • NVIDIA GeForce GTX 1060 or better
  • 8 GB RAM or more
  • CUDA 12.1 compatible graphics card

Installation Instructions

  1. Download the portable application

    Download the MidiGenV2.zip file from the link above.

  2. Extract the application

    Extract the ZIP file to your desired location on your computer.

    Keep all files in the same folder structure.

  3. Setup FluidSynth

    Create a directory: C:\tools\

    Copy the fluidsynth folder from the extracted package

    Paste it into C:\tools\ (final path should be C:\tools\fluidsynth\)

  4. Install PyTorch Dependencies

    Double-click install.bat to run the installer

    Choose your preferred option when prompted:

    [1] CPU Installation - Works on any computer (Universal compatibility) [2] GPU Installation - For NVIDIA graphics cards only (Requires compatible NVIDIA GPU)

    Wait for installation to complete - This process may take 5-15 minutes depending on your internet speed.

  5. Read Important Notes

    Open and read IMPORTANT.txt for additional setup details

  6. Launch the application

    Double-click MidiGenV2.exe to start the application

    Begin creating music with AI assistance!

Important: You MUST run install.bat before using the application for the first time. This installs the required AI/ML dependencies (PyTorch) for music generation.

FluidSynth location is critical! The application expects FluidSynth to be installed at C:\tools\fluidsynth\ for proper audio playback.

Troubleshooting Tips:

  • If installation fails, check your internet connection and try running as Administrator
  • For CUDA errors, install latest NVIDIA drivers or fallback to CPU installation
  • First launch may take longer as AI models initialize
  • Generated MIDI files are saved in the output folder
  • Check IMPORTANT.txt for additional troubleshooting steps

macOS Installation

Python Installation (recommended)

Install the application using Python for the best experience on macOS.

Download Source

System Requirements:

  • macOS 10.14 or later
  • Python 3.8 or higher
  • 4 GB RAM

Installation Instructions

  1. Install Python

    If you don't have Python 3.8+ installed, download and install it from python.org.

  2. Clone the repository

    Open Terminal and run:

    git clone https://github.com/WebChatAppAi/midi-gen.git cd midi-gen

    Alternatively, download and extract the ZIP file from GitHub.

  3. Install dependencies

    In Terminal, run:

    pip install PySide6 pretty_midi numpy pygame fluidsynth

    Note: You may need to install FluidSynth separately using Homebrew:

    brew install fluid-synth
  4. Run the application

    In Terminal, run:

    python app.py

    Or use the provided startup script:

    chmod +x start.sh ./start.sh

Tip: For better performance on macOS, consider creating a virtual environment for the application:

python -m venv venv source venv/bin/activate pip install PySide6 pretty_midi numpy pygame fluidsynth

Linux Installation

Python Installation

Install the application using Python on any Linux distribution.

Download Source

System Requirements:

  • Any modern Linux distribution
  • Python 3.8 or higher
  • 4 GB RAM

Installation Instructions

  1. Install system dependencies

    For Debian/Ubuntu-based distributions:

    sudo apt-get update sudo apt-get install python3-pip python3-dev fluidsynth libfluidsynth-dev

    For Fedora/RHEL-based distributions:

    sudo dnf install python3-pip python3-devel fluidsynth fluidsynth-devel

    For Arch-based distributions:

    sudo pacman -S python-pip fluidsynth
  2. Clone the repository

    Open Terminal and run:

    git clone https://github.com/WebChatAppAi/midi-gen.git cd midi-gen

    Alternatively, download and extract the ZIP file from GitHub.

  3. Install Python dependencies

    In Terminal, run:

    pip install PySide6 pretty_midi numpy pygame fluidsynth
  4. Run the application

    In Terminal, run:

    python app.py

    Or use the provided startup script:

    chmod +x start.sh ./start.sh

Tip: For better performance, consider creating a virtual environment for the application:

python -m venv venv source venv/bin/activate pip install PySide6 pretty_midi numpy pygame fluidsynth

Note: If you encounter issues with FluidSynth, make sure you have a soundfont installed:

# For Debian/Ubuntu: sudo apt-get install fluid-soundfont-gm # For Fedora: sudo dnf install fluid-soundfont-gm

Building from Source (All Platforms)

GitHub Repository

Clone or download the source code directly from GitHub.

View on GitHub

Requirements:

  • Git client (optional)
  • Python 3.8 or higher
  • FluidSynth library

Build Instructions

  1. Clone the repository
    git clone https://github.com/WebChatAppAi/midi-gen.git cd midi-gen
  2. Install dependencies
    pip install PySide6 pretty_midi numpy pygame fluidsynth
  3. Run the application
    python app.py

Tip: Use the startup scripts for convenience:

  • Windows: start.bat
  • Linux/macOS: sh start.sh (or ./start.sh after chmod +x start.sh)

Development Environment

For development, you may want to set up a virtual environment:

# Windows python -m venv venv venv\Scripts\activate # macOS/Linux python -m venv venv source venv/bin/activate # Install dependencies pip install PySide6 pretty_midi numpy pygame fluidsynth

Note: This project is licensed under a custom Non-Commercial Software License. See the LICENSE file for details.

How To Use

1

Open the app

Launch the MIDI Generator Piano Roll application using the executable or script.

2

Pick a plugin

Select a plugin from the Plugin Manager panel.

3

Configure settings

Click Configure to adjust the plugin's parameters.

4

Generate notes

Click Generate to create MIDI notes based on your settings.

5

Play or export

Press Play to hear your composition or Export MIDI to save it as a .mid file.

Frequently Asked Questions

What is MIDI Generator Piano Roll?

MIDI Generator Piano Roll is a plugin-powered standalone application written in Python that allows you to generate MIDI notes using various algorithms, visualize them on a piano roll, play them back with a built-in synthesizer, and export them to standard MIDI files.

How do I create my own plugins?

You can create your own plugins by writing Python classes that inherit from the PluginBase class and implement the necessary methods. Check out our Plugin Documentation for detailed instructions and examples.

Can I use the generated MIDI in my DAW?

Yes, you can export your generated compositions as standard MIDI (.mid) files, which can be imported into any digital audio workstation (DAW) such as FL Studio, Ableton Live, Logic Pro, or Studio One.

Is this application free to use?

Yes, the application is free to use for personal and non-commercial purposes under the terms of our Non-Commercial Software License. See the LICENSE file for complete details.

I'm having trouble with the application. Where can I get help?

You can get help by opening an issue on our GitHub Issues page or by joining the discussion in our GitHub Discussions forum.

Ready to Create MIDI?

Download MIDI Generator Piano Roll now and start making music!