Today, we’re announcing the launch of Veo 3, our newest video generation model in Gemini , which empowers people to realize their creative vision through a combination of different visuals and sounds. Veo 3 is now available to all Google AI Pro subscribers across the Middle East and North Africa.
With Veo 3 now integrated into the Gemini app, people can type the scene they want to see into the prompt and the model can create a personalized eight-second video with audio, dialogue, and music, in 720p quality.
Veo 3 was launched at Google’s annual developer event, Google I/O, last May. The model allows users to add sound effects, ambient noise, and even dialogue to their creations—generating all audio tracks in a completely original and fresh way. It also offers best-in-class quality, excelling in physics, realism, and adherence to scripted requests.
An invisible watermark (SynthID) is present on content generated by Google’s generative AI models, including Veo 3. The company recently launched SynthID Detector for a number of early testers and aims to expand access soon. As a further step to help people identify AI-generated content, a visible watermark will be added to all videos generated by the model, except for those created by Ultra subscribers in Flow, Google’s latest AI-powered tool for filmmakers.