Google Gemini Omni 1.2 Flash Adds 15 Second AI Video at 30% Lower Cost

Summary

Google launched Gemini Omni 1.2 Flash on November 5, 2026, extending native video generation from Omni 1.1’s 10 seconds to 15 seconds and allowing durations from 3 to 15 seconds in one second increments. The 720p price falls 30% to $0.07 per second. Creators can draft at 360p or 720p, revise clips through multi-turn conversations instead of regenerating them, and upscale selected outputs to 1080p or 4K. Editing can replace products or backgrounds, alter lighting, weather and aspect ratios, and create audience or placement variants while preserving other elements.

Google says Omni 1.2 Flash follows character, product and style images, audio cues, and motion references up to three seconds more closely, reducing drift in faces, garments, packaging typography, brand colors, objects, scenes and continuous camera moves. It also improves dialogue, lip sync and multi-speaker conditioning. Demonstrations included three outfits from front and back product shots, a five-layer poster animation, four character references with one second voice samples, a four-shot science explainer, motion transfer across two turns, and a 10 second crash zoom, although minor changes remained between first and last frames. General availability covers the Gemini API, Gemini for business and Google Cloud, with Provisioned Throughput, enterprise security and imperceptible SynthID watermarks. Access also spans Google AI Studio, Flow, Google Ads and Google Vids, where 15 second clips carry no additional charge with a Google account or Workspace subscription. Gemini app access is rolling out to Google AI Ultra subscribers. Fast sports action, rapid script changes and complex physics still need improvement.