Google has introduced a new feature in Veo 3, part of its Gemini AI suite, allowing users to generate eight-second video clips from static images. The tool, which includes sound support, is now available to Google AI Pro and Ultra subscribers in select countries, including Pakistan.
Users can access the feature by selecting the “Videos” option from the tool menu in the prompt box. Once an image is uploaded, users can describe the scene and specify any audio cues. The system then generates an eight-second video based on the input, complete with audio. The finished video can be shared or downloaded directly.
To maintain transparency, all AI-generated videos include both a visible watermark and an invisible SynthID digital watermark. Users are also encouraged to rate the generated content with thumbs-up or thumbs-down options, helping Google refine the tool further.
The company also conducts extensive “red teaming” exercises to proactively test its systems, identify and address potential issues before they arise, and carries out thorough evaluations to understand how these tools might be used and how misuse can be prevented. Policies against unsafe content are continuously enforced, and user feedback is actively sought to further strengthen safety measures.
This capability is also integrated into Flow, Google’s AI filmmaking tool. According to Google, more than 40 million videos have already been created using Veo 3 and Flow within the past seven weeks. The addition of image-to-video functionality is expected to further accelerate the adoption of the platform.