Tech Desk 
Nov 25, 2024
Nvidia announced its new artificial intelligence (AI) model, Foundational Generative Audio Transformer Opus 1 (Fugatto) on Monday, that can efficiently generate music and audio, transform voices, and create novel sounds.
This innovation places Nvidia among other leading platforms in the fledgling field of generative AI, including startups like Runway and established players like Meta, famous for improved audio and video generation capabilities.
What distinguishes Fugatto
Fugatto’s standout feature is its AI-driven capability to receive and modify existing audio, setting it apart from its competitors. By leveraging advanced AI-powered techniques, the model opens new doors for creativity in music production, video game, sound design, and content creation.
Nvidia Applied Deep Learning Research Vice President Bryan Catanzaro stated: "If we think about synthetic audio over the past 50 years, music sounds different now because of computers, because of synthesizers, I think that generative AI is going to bring new capabilities to music, to video games and to ordinary folks that want to create things."
Fugatto: A well trained AI-based model
The model has been meticulously trained on open-source data, ensuring outstanding results and versatility. However, Nvidia hasn’t announced any plans for its public release.
"Any generative technology always carries some risks, because people might use that to generate things that we would prefer they don't, we need to be careful about that, which is why we don't have immediate plans to release this,"Catanzaro added.
Developers of Fugatto are currently grappling with ways to eliminate the misuse of generative AI models such as the generation of misinformation and copyrights violations.
