Nvidia had quite recently amazed the tech world with its latest creation, Fugatto, a generative AI innovation that recasts imagination in sound. Announced on Monday by the company, the technology can generate new sounds on its own, mimic strange sounds such as a trumpet that sounds like a dog and even change the tone of vocals by human performers with astonishing authenticity. With a focus on music producers, filmmakers and game developers, Fugatto promises to turn the process of creating soundtracks and effects into a new art form.
While competitors like Meta and Runway use AI to turn text descriptions into sounds, Nvidia’s Fugatto does much more than that. It basically turns existing audio into something new like piano melodies or spoken words and also transforma changing accents, moods, or even converting notes into human-like vocals.
“If we think about synthetic audio over the past 50 years, music sounds different now because of computers, because of synthesizers,” said Bryan Catanzaro, Nvidia’s vice president of applied deep learning research. “Generative AI is going to bring new capabilities to music, video games, and ordinary folks that want to create things.”
However, instead of making Fugatto a public tool, Nvidia has secluded it for the same ethical reasons to prevent it being used, for instance, to post fake news, or violate copyrights. “It is essential to have admit that any generative technology always compromises certain risks”, Catanzaro said. Nvidia trained Fugatto on open source data and is considering the pros and cons of going open source as well.
This happened as the Hollywood and AI meet at a crucial point in Hollywood production techniques. Though firms like OpenAI are discussing with movie production companies on this, the film industry is still struggling with concerns, defined by the recent controversy with Scarlett Johansson who complained that her voice was mimicked by AI without her permission.
Nvidia’s modern technology places it in the league with other corporations, startups to innovate and bring out the best creativity. But as the company debates whether Fugatto performs live, it watches and contemplates on what the world receive as profit and shed as a loss in this new sonic leap.
