What is new
Gemini Omni 1.2 Flash generates and edits video natively at up to 15 seconds, up from 10 seconds with Omni 1.1. Duration can be set in one-second increments between 3 and 15 seconds. Google says clips can be changed through multi-turn conversations, so users adjust a result rather than starting again. Generation can be guided with character, product or style images, motion clips of up to three seconds, and audio cues.
Access and pricing
The model is generally available on the Gemini API and Google Cloud. Google lists $0.07 per second for 720p video, which it describes as a 30% drop from Omni 1.1. Users can draft at 360p or 720p and upscale to 1080p or 4K, but Google did not publish prices for those resolutions. Developers can prototype in Google AI Studio, and the capabilities are also rolling out in Google Vids and Gemini for business. Google did not say which countries can access the model, or what rate limits and quotas apply.
What it means for creators and sellers
Longer clips and conversational edits may reduce the number of separate generations needed for a short product or social video. A lower per-second price may matter for teams that run many drafts, though only the 720p figure is public. Because outputs carry an invisible SynthID watermark, creators who label synthetic media may want to check how that fits their workflow. Google says fast sports action, rapid script changes and complex physics still need improvement, so motion-heavy shots are worth testing before a campaign.
How this was made: the text was written by AI from the source material, then an automatic check compared every claim with the source. The illustration was generated by AI for AISTETIKA and is not a frame from the story.
