DeepMind's new AI generates soundtracks and dialog for videos | TechCrunch
Briefly

DeepMind sees V2A tech as crucial for AI-generated media, complementing video generation models by adding sound effects and dialogue for immersive content creation.
V2A takes sound description paired with a video, using deepfake-combatting SynthID technology, to create music, effects, and dialogue matching the video's characters and tone.
Read at TechCrunch
[
|
]