Open-source library behind MusicGen, AudioGen and the EnCodec codec
Audiocraft is Meta's research library for audio generation and the home of MusicGen, AudioGen and the EnCodec neural audio codec. It bundles training and inference code, so you can generate music from text or a melody, produce sound effects and environmental audio, and compress or reconstruct audio at low bit rates. Running it locally needs a GPU and a Python environment, but it gives full control: fine-tune on your own material, batch-generate, and read the pipeline end to end. The code is permissively licensed, while the pretrained weights carry separate non-commercial terms that matter if you plan to ship something.
Last updated: 2026-09-20. This site only provides an index; for exact features, pricing, and licensing, see the official website.
audio research, model fine-tuning, game sound prototyping and ml projects
If you're comparing similar products, check the alternatives below, or browse all tools in the AI Audio & Music category.
The code is permissively licensed, but the pretrained model weights are released under research terms that restrict commercial use. Treat the two separately and read the model card for the checkpoint you intend to use.
MusicGen for music, AudioGen for sound effects and environmental audio, EnCodec for compression and reconstruction, plus the training code that ties them together. Each has checkpoints in several sizes.
Yes, the repository includes training and fine-tuning scripts, which is a common reason teams pick it over a hosted service. Expect to supply a suitable dataset and to manage GPU memory carefully.
Text-to-speech voices that are hard to distinguish from humans
Professional audio workstation for editing, restoration and podcast mixing
Browser audio cleanup that makes phone recordings sound studio grade
Automatic audio post-production for loudness, levels and noise