Nvidia on Monday showed off a brand new generative AI (genAI) model that might be used to create every kind of sounds and music: Fugatto (which stands for Foundational Generative Audio Transformer Opus 1).
By entering a text prompt, a user could make Fugatto create mainly any sound, similar to a trumpet barking like a dog. The genAI model can be used to alter the dialect of a singer or turn a piano piece right into a song, in keeping with Reuters.
Fugatto has been trained on open source data, and there’s currently no official release date. Nonetheless, the concept is that the model will eventually be utilized in the production of music, movies and games.
