For the Python TensorFlow implementation, see the main Magenta repo.
UsageTo use in your application, install the npm package @magenta/music-vae, or use the pre-built bundle.
You can then instantiate a
let mvae = new MusicVAE('/path/to/checkpoint')
For a complete guide on how to build an app with MusicVAE, read the Melody Mixer tutorialcl-tutorial.
Pre-trained CheckpointsSeveral pre-trained MusicVAE checkpoints are hosted on GCS. While we do not plan to remove any of the current checkpoints, we will be adding more in the future, so your applications should reference the checkpoints.json file to see which checkpoints are available.
If your application has a high QPS, you must mirror these files on your own server.
- Beat Blender by Google Creative Lab
- Melody Mixer by Google Creative Lab
- Latent Loops by Google Pie Shop
- Neural Drum Machine by Tero Parviainen
yarn installto install dependencies.
yarn buildto produce a commonjs version with typescript definitions for MusicVAE in the
es5/folder that can then be consumed by others over NPM.
yarn bundleto produce a bundled version in
yarn run-demoto build and run the demo.