Google is adding a powerful new trick to its Gemini AI. Users can now turn ordinary photos into short videos complete with sound effects. This feature, available to paying subscribers of Google AI Pro ($19.99/month) and Ultra ($249.99/month) plans, creates eight-second video clips from still images.
The technology behind this is Veo 3, Google’s latest video generation model unveiled in May. Since its launch, users have created over 40 million videos using Veo 3 across Gemini and Flow (Google’s specialized filmmaking tool).
Google CEO Sundar Pichai highlighted the feature’s popularity on social media: “Now our new photo to video feature in the Gemini app lets you create clips inspired by the world around you.”
Using the tool is simple. Users open Gemini on their computer, select “Videos” from the menu, upload a photo, and describe what they want to happen. They can specify movements, actions, and sounds in their instructions. After a few minutes of processing, Gemini delivers an MP4 video file in 720p resolution with a widescreen 16:9 format.
The feature works especially well with everyday objects, drawings, paintings, and nature scenes. Google admits that animating human faces is still challenging, with improvements planned for future updates.
“You can get creative by animating everyday objects, bringing your drawings and paintings to life or adding movement to nature scenes,” Google explained in its announcement.
Safety measures are built into the system. Every video contains both a visible watermark and an invisible digital “SynthID” watermark embedded in each frame. These identify the content as AI-generated. Google also prohibits creating videos of recognizable public figures like celebrities or politicians and blocks content that shows dangerous activities.
Before releasing this feature, Google conducted extensive testing to identify and fix potential problems. This “red teaming” process aims to prevent misuse of the technology, addressing growing concerns about deepfakes and copyright issues.
The new capability gives Google a stronger position against competitors like OpenAI’s Sora and specialized video startups like Runway AI. By integrating video creation directly into Gemini’s interface, Google makes advanced video technology accessible to people without technical expertise.
Similar Posts
For content creators and social media users, this tool could be particularly valuable. Video has become essential for building online audiences, but creating fresh content regularly can be challenging.
“Video content has replaced static posting as the best method for businesses, influencers and marketers to build a large audience online,” noted Brendan Gahan, CEO at Creator Authority. This technology could help creators save time while focusing on connecting with their audiences.
Currently, the feature is available on Gemini’s website, with mobile app support coming soon. Users in the European Economic Area, Switzerland, and the United Kingdom cannot access the feature yet, likely due to regional regulations.
As AI video creation becomes more mainstream, it continues to raise important questions about jobs in creative industries, copyright protection, and the responsible use of this powerful technology.
