Meta’s text-to-audio AI can create common sounds and generate music
Meta’s AudioGen text-to-audio artificial intelligence model could create sound for video games, film soundtracks or music production
Technology
7 October 2022
An artificial intelligence model developed by Facebook owner Meta can generate sounds from a text prompt.
AudioGen, an AI worked on by Meta and the Hebrew University of Jerusalem, turns text prompts such as “whistling with wind blowing” into an audio file that sounds like the scenario described. It is the sound-based equivalent of popular AI-based systems that generate images from text prompts, such as DALL-E or Midjourney, and that have captured the public imagination in …