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.

Nvidia unveiled a new AI model on Monday called Fugatto that can create sounds, music, and clone and modify voices, based on the user's audio and text prompts.

Fugatto can make music from text prompts, change song instruments, change vocal accents or moods, and create new sounds

Nvidia (NASDAQ:NVDA) unveiled a new AI model called Fugatto for generating music and audio, aimed at people producing music, films and video games. Fugatto (Foundational Generative Audio Transformer Opus) generates or transforms any mix of music,