Google has rolled out Gemini Omni 1.2 Flash, now generally available across the Gemini API and Gemini for business. The model introduces native video creation of up to 15 seconds, up from 10 seconds in Omni 1.1, and lets users specify duration in one-second increments from 3 to 15 seconds. Creators can produce complete stories, product explainers or full social ad spots in a single generation.
The update also improves reference adherence and consistency. Users can guide generation with character, product or style images, short motion clips of up to three seconds, and audio cues. Faces, garments, packaging typography and brand colors stay consistent across camera angles, which makes it easier to turn product photography into virtual try-on clips, catalog spins and branded video ads. Character, object and scene consistency also hold from the first frame to the last, with less visual drift or morphing during motion and camera transitions.
Multi-turn conversational editing is another key addition. Users can refine a clip turn by turn, swapping a product or background, changing lighting or weather, or switching aspect ratio, rather than starting over. This works across full 15-second clips, allowing teams to produce ad variants for different audiences and placements without re-briefing or regenerating.
Pricing drops 30% from Gemini Omni 1.1 to $0.07 per second for 720p video. The workflow is designed to keep costs down: users can draft quickly at 360p or 720p, fix details with follow-up edits, and upscale final versions to 1080p or 4K. Speech generation has also improved, with more natural dialogue, clearer lip-sync and distinct multi-speaker conditioning.
Source: Google DeepMind Blog · Summarized by HeadlinesBriefing