Image: Provided
Google has officially introduced Veo 3, its newest model for video generation, which is now accessible to all subscribers of Google AI Pro throughout the region. This innovative tool allows users to convert written descriptions into rich, audio-infused videos, catering to creators, developers, and businesses aiming to enhance their AI-driven content production.
Embedded within the Gemini application, Veo 3 enables individuals to articulate a scene through a “prompt,” which is then utilized to generate a custom eight-second video at 720p resolution, featuring built-in sound, dialogue, and music. This technology was first showcased at Google I/O, the company’s annual developer conference held in May.
With a focus on providing high levels of realism and accurate prompt interpretation, Veo 3 boasts native audio generation capabilities, facilitating precise layering of sound effects, background noise, and spoken dialogue. Furthermore, it sets a benchmark in physics simulation and visual quality.
Related news: Google to enhance Gemini and Search AI features in MENA following I/O 2025
In alignment with its commitment to responsible AI practices, every video produced by Veo 3 carries a SynthID watermark, a secure digital identifier for AI-generated content. Google has also rolled out the SynthID Detector to a limited number of testers and intends to broaden its availability in the future. Moreover, a visible watermark will be included on all videos except those made by Ultra members using Flow, Google’s latest tool tailored for AI filmmakers.
The Veo 3 model is now available for Google AI Pro subscribers, who can start producing AI-enhanced video content without delay.