Google’s latest video-generating AI model, Veo 3, can create audio to go along with the clips that it generates.
On Tuesday during the Google I/O 2025 developer conference, Google unveiled Veo 3, which the company claims can generate sound effects, background noises, and even dialogue to accompany the videos it creates. Veo 3 also improves upon its predecessor, Veo 2, in terms of the quality of footage it can generate, Google says.
Veo 3 is available beginning Tuesday in Google’s Gemini chatbot app for subscribers to Google’s $249.99-per-month AI Ultra plan, where it can be prompted with text or an image.
“For the first time, we’re emerging from the silent era of video generation,” Demis Hassabis, the CEO of Google DeepMind, Google’s AI R&D division, said during a press briefing. “[You can give Veo 3] a prompt describing characters and an environment, and suggest dialogue with a description of how you want it to sound.”
The wide availability of tools to build video generators has led to such an explosion of providers that the space is becoming saturated. Startups including Runway, Lightricks, Genmo, Pika, Higgsfield, Kling, and Luma, as well as tech giants such as OpenAI and Alibaba, are releasing models at a fast clip. In many cases, little distinguishes one model from another.
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, nor are models to create video sound effects. But Veo 3 uniquely can understand the raw pixels from its videos and sync generated sounds with clips automatically, per Google.
Here’s a sample clip from the model:
