Google launched Gemini Omni 1.2 Flash, adding native 15-second video creation, multi-turn conversational editing, and stronger adherence to reference images, clips and audio cues, according to the company.
Google said the update aims to lower costs and improve consistency for video production at scale. The company said it reduced the price by 30% from Gemini Omni 1.1 to $0.07 per second for 720p video.
The release is generally available on the Gemini API and Google Cloud, Google said. The company said the capabilities are also rolling out across Google Vids and Gemini for business, with access points for developers, businesses and users of Google apps.
Google said creators can now generate and edit videos up to 15 seconds, up from 10 seconds in the prior version, and set durations in one-second increments from three to 15 seconds. The company said workflows can draft quickly at 360p or 720p, allow follow-up edits without re-generating an entire clip, and then upscale to 1080p or 4K.
Reference following is designed to hold character, product and style details from start to finish, Google said. The company said faces, garments, typography and brand colors remain consistent across camera angles, and short motion clips up to three seconds and audio cues can guide generation.
Google said the model produces stronger character, object and scene consistency from first to last frame, with less visual drift across motion and camera transitions. The company said editing can happen turn by turn on the same clip, including swapping products or backgrounds, changing lighting or weather, or switching aspect ratios.
Speech generation is intended to sound more fluid and natural, with clearer lip-sync and multi-speaker conditioning, according to Google. The company also said camera control supports continuous movements like first-person flythroughs, dramatic zoom-outs and orbits with fewer unwanted jump cuts.
Google said businesses, startups and creatives are already using Omni 1.2 Flash, and that outputs carry an imperceptible SynthID watermark. The company said Provisioned Throughput is available.
Google outlined access routes across its products and platforms. Developers can use the Gemini API via Google AI Studio and related documentation, the company said. Businesses can try the model in the Google Cloud console and build with the API, and users can direct scenes and multi-turn edits in Flow, generate 15-second clips at no additional cost in Google Vids with a Google account or Google Workspace subscription, create 15-second videos in the Gemini app as it rolls out to Google AI Ultra subscribers, and scale video campaigns in Google Ads, according to the company.
Google said development continues on areas like fast sports action, rapid script changes and complex physics. The company did not provide a timeline for those improvements.