Video generation model Veo3 can now generate audio in addition to video, demonstrated by generating an owl flapping its wings with corresponding sound effects, and showing dialogue between characters (though the dialogue was mostly unintelligible).

factualpending

Speaker

Casey Newton

Evidence Quote

“the video generating model VO3 can also generate sound...they exchanged some dialogue which was basically incomprehensible, just pure sloth”

Source

Google DeepMind C.E.O. Demis Hassabis on Living in an A.I. Future | EP 137— Hard Fork
Created: 8/11/2026, 6:41:27 AM

Your notes

Loading notes...