Google Launches Gemini Omni 1.2 Flash With 15-Second AI Video
Google's new Gemini Omni 1.2 Flash generates AI video clips of up to 15 seconds, allows edits through ongoing chat and cuts generation costs by 30%.
SUMO· the number puzzle
Dialo· learn languages by speaking
ediviewer· read EDI files like documents
giftdetect· the right gift in minutesGoogle has released Gemini Omni 1.2 Flash, a new AI video generation model that extends clips to 15 seconds, lets users edit a video through a continuous conversation and lowers generation costs by 30% compared with the previous version. The update targets content creators, developers and businesses.
According to the announcement on Google's official blog, the model is available through the Gemini API and Gemini services for business. Generating video at 720p costs about $0.07 per second. Google also says the model better preserves the look of characters, products and visual elements as they move and as camera angles change.
Edit a clip through conversation
Instead of regenerating a video after every change, users can create a clip and then request successive edits within the same chat. Examples include swapping the background or the product on screen, adjusting lighting and weather, or changing the video's aspect ratio. The clip stays the same and is refined step by step.
Longer clips, higher resolution
Gemini Omni 1.2 Flash produces videos between 3 and 15 seconds in one-second increments, up from the previous 10-second limit. Work can start at 360p or 720p, and the selected result can then be upscaled to 1080p or 4K.
The model accepts images of characters, products and visual references, as well as short motion clips and audio cues to guide generation. Google says these improvements reduce changes in the appearance of clothing, faces and objects between scenes.
Use cases and caveats
Google points to product ads, visual presentations, explainer clips and testing different versions of the same video. The claims about consistency and motion quality are based on the company's own evaluations and demonstrations, so identical results are not guaranteed across every project.
Apps worth a look
SUMO: the number puzzleTap the right tiles, add them up, hit the target. Easy to learn, hard to master. Free, for all ages.
Dialo: learn languages by speakingTalk to an AI conversation partner; every sentence comes back corrected and explained in your language. 9 languages, A1 to C2.
ediviewer: read EDI files like documentsOpen EDIFACT and X12 messages, see every segment explained, convert to JSON/XML, export PDF and Excel. Runs locally, no upload.
giftdetect: the right gift in minutesPick who it is for, the occasion and their personality. The search engine reads product descriptions from local shops and ranks what fits. Free, no sign-up.
More from this day
See all →
Citus Demonstrates GPS-Free Firefighter Tracking, Eyes Military Use
Google Cloud expands CodeMender and AI agent security tools
Operation Ghostbusters: 830,840 Suspected Ghost Students Found
