Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
About this project
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning. It covers speech and audio, the layer that turns text into voice, voice into text, or raw audio into something structured. It is maintained by facebookresearch and published as a public repository you can read, fork and run yourself.
The repository carries no GitHub topic tags, so the README is the fastest way to judge its scope. Most deployments care about latency and voice quality, so the project usually ships both a batch path and a streaming or real-time one.
It is written mainly in Jupyter Notebook and released under MIT, a permissive license — commercial use is fine as long as copyright notices are kept. The last commit was on March 4, 2026, so development is moving, just not on a daily basis.
To try it, clone the repository and follow its README; that file is the canonical install guide. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.
Key facts as recorded on GitHub: 23,906 stars; 2,714 forks; primary language Jupyter Notebook; license MIT; last commit on March 4, 2026.