At the Google I/O 2025 conference, Google introduced Veo 3, a video-generating AI capable of creating synchronized sound effects, background noises, and dialogue alongside its generated visuals. This innovation offers users the ability to input prompts describing characters, environments, and desired dialogue tones. Available to subscribers of Google's AI Ultra plan, Veo 3 aims to set itself apart in a competitive landscape by improving audio integration in video creation, building on prior developments in video-to-audio technology from DeepMind.
"For the first time, we're emerging from the silent era of video generation," Demis Hassabis, the CEO of Google DeepMind, said during a press briefing.
Audio output stands to be a big differentiator for Veo 3, if Google can deliver on its promises. AI-powered sound-generating tools aren't novel, but Veo 3 uniquely can comprehend the raw pixels from its videos and automatically sync generated sounds.
Collection
[
|
...
]