Nvidia introduced the AI-based Fugatto service, which can generate various sounds and voice performances based on the user’s text description. This is stated in a message on the company’s website. The launch date of the service is unknown.
Author:
https://rb.ru/author/bmuzichenko/
Subscribe to RB.RU on Telegram
Fugatto can create a piece of music based on your request, remove or add instruments to an existing song, or change the accent or emotion of your voice.
The AI service allows, among other things, to “make a trumpet bark” or “make a saxophone meow.” Nvidia wanted to make a tool that “understands and generates sound like humans do,” explained the company’s director of applied audio research, Rafael Valle.
The chipmaker suggested using Fugatto to quickly create a “prototype song,” for video game sounds or changing the accent of a voiceover in an ad for different regions.
OpenAI and Google DeepMind already have their own AI tools for generating audio, but they can’t create the “unique” sounds that Nvidia claims Fugatto can generate.
Author:
Bogdan Muzychenko
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
