Veo 3

The landmark addition: native audio generation. For the first time, a video model generates synchronized dialogue, sound effects, and ambient noise alongside the visuals in a single pass. Lip-sync accuracy under 120ms. In practice, this collapses what was previously a multi-tool workflow into a single generation. No more generating video, then finding sound effects, then syncing dialogue. The model imagines the entire audiovisual scene at once.