Meta’s AudioGen text-to-audio synthetic intelligence mannequin might create sound for video video games, movie soundtracks or music manufacturing
Expertise
7 October 2022
An AI can create sounds that relate to a textual content immediate it’s given Maksim Kabakou/Shutterstock
A synthetic intelligence mannequin developed by Fb proprietor Meta can generate sounds from a textual content immediate.
AudioGen, an AI labored on by Meta and the Hebrew College of Jerusalem, turns textual content prompts equivalent to “whistling with wind blowing” into an audio file that sounds just like the state of affairs described. It’s the sound-based equal of fashionable AI-based programs that generate photos from textual content prompts, equivalent to DALL-E or Midjourney, and which have captured the general public creativeness in …