MusicGen

This is the demo for MusicGen, a simple and controllable model for music generation presented at: "Simple and Controllable Music Generation".
for longer sequences, more control and no queue.

More details

The model will generate 15 seconds of audio based on the description you provided. The model was trained with description from a stock music catalog, descriptions that will work best should include some level of details on the instruments present, along with some intended use case (e.g. adding "perfect for a commercial" can somehow help).

You can optionally provide a reference audio from which a broad melody will be extracted. The model will then try to follow both the description and melody provided. For best results, the melody should be 30 seconds long (I know, the samples we provide are not...)

You can access more control (longer generation, more models etc.) by clicking the (you will then need a paid GPU from HuggingFace). If you have a GPU, you can run the gradio demo locally (click the link to our repo below for more info). Finally, you can get a GPU for free from Google and run the demo in a Google Colab..

See github.com/facebookresearch/audiocraft for more details. All samples are generated with the stereo-melody model.