Google Gemini Introduces AI Photo-to-Video Tool with Sound Using Veo 3 Model

Google Gemini, the tech giant’s AI platform, has launched an innovative new feature that allows users to transform static photos into dynamic 8-second video clips with sound. Powered by Google’s advanced Veo 3 generative video model, this creative tool is currently available to Gemini Advanced users on the Ultra and Pro plans in select regions, offering a new dimension of AI-driven visual storytelling.

To use the feature, users must select the ‘Videos’ option from the tool menu in the Gemini prompt box. After uploading an image, they can enter a text prompt describing how they want the photo to be animated, along with any desired audio instructions, such as background music, ambient sounds, or even dialogue. Once generated, the video can be shared or downloaded directly from the platform.

“You can get creative by animating everyday objects, bringing your drawings and paintings to life, or adding movement to nature scenes,” Google explained in an official blog post, highlighting the creative possibilities for artists, designers, marketers, and content creators.

 

Each video generated by Gemini includes both a visible watermark and an invisible SynthID digital watermark to clearly indicate that the content is AI-generated, reinforcing transparency and ethical AI use.

This feature builds on Google’s previous rollout of similar capabilities through Google Flow, its AI video generation tool for filmmakers, launched in May 2025. With Gemini’s integration of photo-to-video conversion, Google continues to position itself at the forefront of AI content creation tools, competing with platforms like Runway, Pika, and OpenAI’s Sora.

As generative AI evolves, tools like this underscore a major shift in how users will produce videos—turning simple images into immersive multimedia experiences with just a few clicks. Expect broader access in the coming months as Google expands regional availability.