Nvidia wants to let you knowthat your weirdest audio whims are now possible.
The companys latest AI project, along with itsAI NPCsandin-game chatbot,is a text-to-audio AI called Fugatto.
Fugatto is actually an acronym for the obnoxiously long Foundational Generative Audio Transformer Opus 1.
Jensen Huang, co-founder and CEO of Nvidia, holds up the company’s AI accelerator chips for data centers.© Photo: Akio Kon/Bloomberg via Getty Images
It can also modify existing sound sources.
Its silly to call anything a sound never heard before, especially if it comes from AI.
This means it can overlay two distinct audio effects to create something new.
It can also create the sound of a rainstorm that fades into the distance.
These are capabilities we havent seen before.
Plenty of AI audio toolsalready take text prompts and turn them into audio tracks.
Adobe has shoppedits own Project MusicGenAI Control toolto unscrupulous musicians.
Big tech companies like Meta have already promoted their audio models to the movie industry.
Last month,Meta debuted Movie Gen,which can generate soundscapes for AI-generated films.
Fugatto potentially has more utility than merely giving an excuse for movie production companies to replace human audio engineers.
Nvidia claims it can remove or add instruments to existing music.
It can also isolate and modify specific noise from existing sources.
News from the future, delivered to your present.
Two banks say Amazon has paused negotiations on some international data centers.
