Create Generative AI Music from text with Audiocraft Part 1 – Local setup

About

In this video we'll use Audiocraft, an open source library from Facebook, to create a fully customizable interface for generating AI audio. Because the instructions and latest code seem to not work for most people, this video will show you how to get around the issues, and up and running smoothly.

0:00 - Stable Audio Demo 0:55 - Hosted AudioCraft Demo on Hugging Face 2:26 - Install Prerequisites 3:48 - Install Audiocraft 5:30 - Modifying the code to fix install issues 7:00 - Run the music generator in your browser

Links

- Code Repo: https://github.com/facebookresearch/audiocraft/ - [Hosted Demo: https://huggingface.co/spaces/facebook/MusicGen - Install Issue: https://github.com/facebookresearch/audiocraft/issues/105 - How to manage virtual environments in Python: https://python.land/virtual-environments/virtualenv

About Me: I am a Staff Design Technologist on Mozilla's Innovation Team. All opinions and explorations are my own. Learn more about Mozilla Innovation at future.mozilla.org

Dependencies:

- Python 3.9+ - Pip - VirtualEnv - FFMpeg - Sourcetree (optional)

- Code editor (recommend VSCode)

Human-made No record of this work says a model made it. What this means.