Nvidia has introduced Fugatto, an artificial intelligence capable of generating unique sounds that did not exist before. The model allows you to create audio from text descriptions, edit music and even transform sounds.
This is reported by The Independent.
AI that creates new sounds
Nvidia has developed an AI called Fugatto that can generate sounds that never existed before. The model is being pitched as a “Swiss Army knife of sound,” capable of editing or creating audio using text queries.
Fugatto can perform tasks like removing instruments from songs, changing accents, or even creating sounds that the user describes with text.
“Fugatto can make a trumpet bark or a saxophone meow. Anything the user can describe, the model can create,” — said Nvidia's Richard Kerris.
For example, the model produced audio on demand that was “deep, rumbling bass pulses paired with intermittent, high-pitched digital chirps, like the sound of a massive intelligent machine waking up.” In another experiment, Fugatto transformed the sound of a train into the music of a string orchestra.
The AI took over a year to develop. To train the Fugatto model, the developers listened to millions of audio files.
“This thing is wild. Sound is my inspiration. It's what drives me to make music. The idea that I can create completely new sounds on the fly in the studio is incredible,” said Ido Zmishlani, a producer participating in the Nvidia Inception program.
Despite its unique capabilities, the model raises concerns about its potential impact on the work of musicians and other creators. However, the developers are confident that Fugatto should revolutionize the music industry by creating new sounds.