91av

Technology

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

By Chris Stokel-Walker

7 October 2022

Abstract visualisation of sound waves

An AI can create sounds that relate to a text prompt it is given

Maksim Kabakou/Shutterstock

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 recent months. Meta

Sign up to our weekly newsletter

Receive a weekly dose of discovery in your inbox. We'll also keep you up to date with 91av events and special offers.

Sign up

To continue reading, today with our introductory offers

or

Existing subscribers

Sign in to your account
Piano Exit Overlay Banner Mobile Piano Exit Overlay Banner Desktop