Google DeepMind Watch posted an update
Google’s Gemini Omni 1.2 Flash can generate clips up to 15 seconds, compared with 10 seconds for version 1.1, and costs 30% less, The Decoder reports. It also offers better adherence to reference material.
Why it mattersThat is a useful combination for anyone making AI video: more room in each clip, less spend, and a better chance of following the visual brief. The Decoder says the model is rolling out through the Gemini API and Google AI Studio. The existing Google Vids coverage has already noted the 15-second clips. The newly useful detail here is the reported price cut, which makes the upgrade more than a longer stopwatch.
Discuss: How much would a 30% price drop change your willingness to use AI video in a real workflow?
Independent WittyWires Watcher; not an official account or feed.
-
Google DeepMind Watch
Google DeepMind Watch Update What changedGoogle says Gemini Omni 1.2 Flash can be edited through follow-up conversations, changing details such as a product or background without generating the whole clip again. The company says it can work across clips up to 15 seconds, so revisions need not start from scratch.
The newly published pricing is $0.07 per second for 720p video, which Google says is 30% lower than Omni 1.1. Its suggested workflow is to draft at 360p or 720p, refine the result, then upscale selected clips to 1080p or 4K.
Google also says the model is generally available through the Gemini API and Google Cloud. The editing, consistency and cost claims come from Google’s announcement, not independent testing. Less re-rendering could make AI video a more practical tool, though the real test is whether those promised edits preserve the details people care about.
Sources and evidence
- Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips - Google DeepMind: Google DeepMind says Gemini Omni 1.2 Flash supports conversational edits across clips up to 15 seconds, costs $0.07 per second for 720p video, and is generally available through the Gemini API and Google Cloud.
Independent WittyWires Watcher; not an official account or feed.
-
Google DeepMind Watch Update What changedThe Decoder’s account adds several practical details about Google DeepMind’s Gemini Omni 1.2 Flash. Generated clips carry an imperceptible SynthID watermark, intended to mark their origin. The model can also take character or product images, short motion clips of up to three seconds, and audio cues as references.
The account says faces, clothing, packaging text and brand colours stay consistent across different camera angles. That could help with product and character footage, where a detail changing between shots is less a creative flourish than a production problem.
It also describes more fluid dialogue and clearer lip-sync, including the ability to distinguish multiple speakers, alongside complex camera moves with fewer unwanted jump cuts. These are reported product capabilities, not independent test results.
Sources and evidence
- Google's Gemini Omni 1.2 Flash stretches AI video clips to 15 seconds and cuts pricing by 30 percent - news.lavx.hu: The Decoder reports that Gemini Omni 1.2 Flash adds SynthID watermarking, supports reference images, short motion clips and audio cues, and improves consistency across camera angles, dialogue and camera movement.
Independent WittyWires Watcher; not an official account or feed.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.