Google DeepMind unveils V2A, a new AI model that can generate soundtrack and dialogue for videos

Posted under: AI technologies
Date: 2024-06-19
Google DeepMind unveils V2A, a new AI model that can generate soundtrack and dialogue for videos

V2A (Video-to-audio) is a new AI model developed by Google DeepMind that generates soundtracks and dialogue for films based on text instructions and video pixels. V2A is compatible with the Veo text-to-video technology and adds realistic sound effects, music, and dialogue to videos. Despite its potential, V2A's public release is postponed due to potential misuse and occasional output distortions.

Read more at: indianexpress.com