Google is expanding its Gemini Omni 1.2 Flash AI video model, enabling users to generate longer clips and edit them through a chat-style interface. Reports say the model can create AI videos up to 15 seconds long, and that editing can be done over multiple conversational turns, with improvements aimed at reducing mistakes.
Several outlets also highlight video quality and usability changes. Digital Trends says the update improves lip-sync and offers “fewer frustrating mistakes,” while Android Authority focuses on a claim that the new model produces clips roughly half again as long as before. The Next Web adds more pricing context, describing the model as generally available and stating it is 30% cheaper, including an estimated cost per second for 720p video. Across coverage, all sources present the announcement as an expansion of what Gemini Omni 1.2 Flash can do for AI video creation and editing.
