Google's Gemini Omni 1.2 Flash generates 15s AI video clips at 30% lower cost

google deepmind releases gemini omni 1.2 flash, an updated video-generation model that creates clips up to 15 seconds long, supports conversational editing, and costs 30 percent less than its predecessor at $0.07 per second for 720p video. the model improves visual consistency, reference adherence, and produces more fluid dialogue with clearer lip-sync. conversational editing allows users to tweak generated clips step by step without regenerating the entire clip. this update rolls out through the gemini api, google ai studio, google cloud console, and other platforms.