Open Source & Free

Audiocraft Lite

Run AI Music Studio locally on your machine. An optimized, lightweight version of Meta's AudioCraft - completely free and open-source.

Why Audiocraft Lite?

A streamlined, optimized version designed for developers and creators who want full control

Optimized & Lightweight

Streamlined version of Meta's AudioCraft for better performance and lower resource usage.

Run Locally

Generate music on your own machine. No API keys, no cloud costs, complete privacy.

MIT Licensed

Free and open-source. Use, modify, and distribute for personal or commercial projects.

Easy Setup

Simple installation process with clear documentation. Get started in minutes.

Quick Start Guide

Choose your preferred setup method

One-Click Setup (Recommended)

No installation headache! Just double-click and run.

  1. 1Double-click AudioCraft-Lite.bat
  2. 2Wait for browser to open (10-15 min first time)
  3. 3Choose music or sound effects
  4. 4Select quality level
  5. 5Describe what you want
  6. 6Generate and enjoy!

Manual Setup (Advanced)

01

Clone Repository

Terminal
git clone https://github.com/Yogesh1290/Audiocraft-Lite.git
02

Install Backend Dependencies

Terminal
cd Audiocraft-Lite && pip install -r requirements.txt
03

Install Frontend Dependencies

Terminal
cd frontend && npm install
04

Run Backend Server

Terminal
python app.py
05

Run Frontend (New Terminal)

Terminal
cd frontend && npm start

About This Project

Audiocraft Lite is an optimized, lightweight version of Meta's AudioCraft framework. This project aims to make AI music generation more accessible by reducing resource requirements while maintaining quality output.

Original Project

Based on AudioCraft by Meta's Fundamental AI Research (FAIR) team. AudioCraft is a PyTorch library for deep learning research on audio generation.

Created By

Y

Yogesh Singh

AI Music Studio

MIT License

Free to use, modify, and distribute for personal or commercial projects. See the LICENSE file in the repository for full details.

Ready to Get Started?

Star the repository, contribute, or just try it out locally