Nvidia’s Fugatto is designed for ‘film or audio productions,’ but it can also create the sound of a saxophone howling like a dog.

Nvidia says its new AI music editor can create “sounds never heard before” — like a trumpet that meows. The tool, called Fugatto, is capable of generating music, sounds, and speech using text and audio inputs it’s never been trained on.

Nvidia's new model was trained on open-source data, and the company said it is still debating whether and how to release it publicly.