Google has officially launched Gemini Omni 1.2 Flash, the latest iteration of its lightweight generative model. This release brings general availability to developers through the Google Cloud platform and the company's API services. Alongside the broader rollout, Google has implemented a 30 percent price reduction for the model compared to the previous Gemini Omni 1.1 Flash version, aiming to lower the barrier for enterprise and developer integration.
A primary feature of the Omni 1.2 Flash update is its enhanced video generation capability, which is now integrated into Google Vids. Users can generate 15-second video clips directly within the video creation and editing tool. The model is designed to maintain visual consistency across scenes, allowing users to upload reference images to ensure characters and environments remain stable from the beginning to the end of a generated sequence.
The integration within Google Vids includes improved speech narration features intended to make audio output sound more natural for social media content, concept explainers, and promotional teasers. Google states that the model can produce these clips without requiring cuts, facilitating the creation of continuous, professional-grade promotional materials from simple text descriptions.
Access to these new video generation features is available to all users with a standard Google account or a Google Workspace subscription. Under the current rollout, users are permitted to generate up to three 15-second videos per month at no additional cost. The tool is accessible through the dedicated web portal at vids.new, where users can begin generating content based on their specific prompts and reference materials.
