Google launches Imagen 4 and Veo 3; Now AI will create photos, videos, add audio automatically

At the keynote presentation at Google I/O 2025, Google unveiled its latest AI-powered image and video generation technology, Imagen 4 and Veo 3. Aside from being able to generate images and video vignettes from text or image descriptions, the new AI models now generate automatic and accurate audio in the video through Veo 3.

According to Google, Veo 3 is its most sophisticated video generation model yet. It can perform tasks such as enhanced movement and motion handling, consistency between scenes, and enhanced interaction with the surroundings. Users can now create a few seconds of a video clip by simply inputting text or images into it, in which audio will be included automatically. Veo 3 is now available in beta for Gemini app users with the Google AI Ultra plan and Flow (Google's new AI filmmaking platform). Enterprise customers can access it in Vertex AI.

Veo 3 now, continuity can be maintained in the scene by uploading an image of a person, object, or style. Apart from this, camera movements like pan, zoom, and rotate can now be decided by the prompt. Now the video can be extended beyond its current frame. It is now possible to add or remove an object in a frame. Also, light and shadow adjust automatically.

Google has also launched Imagen 4, which is a new AI image generator. It supports high-quality images up to 2K resolution, along with texture detailing - such as clothing, reflections, fur, etc., and output in a variety of styles ranging from photo-realistic to illustrative.