Gemini Omni 1.2 Flash: 15-Second Clips, 30% Cheaper, Conversational Editing, Now GA
On November 5, 2026, Google made Gemini Omni 1.2 Flash generally available. Clips stretch to 15 seconds, pricing drops 30% to about $0.07/sec at 720p, and you can edit the same clip turn by turn with stronger reference lock and SynthID watermarks.
What Google shipped on November 5, 2026
On November 5, 2026, Google DeepMind and Google Cloud made Gemini Omni 1.2 Flash generally available across the Gemini API, Google Cloud, Flow, Google Vids, the Gemini app, and Google Ads. The update is a speed-and-cost play for production video: native clips up to 15 seconds (up from 10s on Omni 1.1), multi-turn conversational editing, stronger image/video/audio reference adherence, and a 30% price cut to about $0.07 per second at 720p. This page is the long-form briefing behind the BSH Technologies Instagram carousel.
Longer clips: 3 to 15 seconds
Creators can now generate and edit videos natively up to 15 seconds, with freely selectable lengths in one-second increments from 3 to 15. That is enough for complete social spots, product explainers, and short ads in a single generation — without stitching multiple 10-second takes. For how Google has been pushing frontier Gemini models in parallel, see our note on Gemini 4 Carbon and the earlier Project Suncatcher orbital TPU brief.
30% cheaper, draft-then-upscale workflow
Pricing drops 30% versus Omni 1.1 — Google quotes about $0.07 per second for 720p, with similar savings at other resolutions. The recommended workflow keeps costs down further: draft fast at 360p or 720p, fix a detail with a follow-up conversational edit instead of regenerating the whole clip, then upscale winners to 1080p or 4K. Independent coverage from The Verge highlights the selectable clip lengths and conversational edits.
Conversational multi-turn editing
Instead of starting over, you refine the same clip turn by turn: swap a product or background, change lighting or weather, or switch aspect ratio. Multi-turn editing works across the full 15-second length, which makes ad variants for different audiences cheaper to produce. For comparison with OpenAI's latest generative media push, see OpenAI Images 2.6 (GIFs, Flare, Sunburst).
Stronger reference lock and cinematic control
Omni 1.2 Flash holds character, product, and style references more tightly across camera angles and match cuts. You can combine character or product images, short motion clips (up to three seconds), and audio cues. Google also highlights steadier continuous camera moves — FPV flythroughs, crash zoom-outs, orbits — with fewer unwanted jump cuts. Audio references remain allowlisted. The DeepMind model card frames Omni 1.2 Flash as a step toward create-and-edit-anything models starting with video.
Generally available, with SynthID
For the first time, Gemini Omni is generally available on Google Cloud with enterprise-grade infra, Provisioned Throughput, and an imperceptible SynthID watermark on every output. Business users can create in Gemini for business and Google Vids; developers build via the Gemini API and AI Studio. Cloud details: Gemini Omni 1.2 Flash on Google Cloud. On the agent-safety side of the stack, our note on Nvidia OpenShell + Sentry covers another lab's production guardrails, and OpenAI GPT-6 Cyber shows how gated access tiers are being productised elsewhere.
Why it matters
Video generation is shifting from demo clips to production workflows: selectable length, conversational edits, draft-then-upscale pricing, and provenance watermarks. Omni 1.2 Flash is Google's bid to make high-volume product video, virtual try-ons, and social ads cheap enough to run every day — with the caveat that complex physics and fast sports action are still improving.
Sources
Frequently asked questions
What is Gemini Omni 1.2 Flash?
Google DeepMind's video generation and editing model, made generally available on November 5, 2026. It creates and edits clips up to 15 seconds with stronger reference adherence and a 30% price cut versus Omni 1.1.
How long can Omni 1.2 Flash clips be?
Native generation and editing support clips from 3 to 15 seconds in one-second increments, up from a 10-second maximum on Omni 1.1.
How much does it cost?
Google quotes about $0.07 per second for 720p video — roughly 30% less than Omni 1.1 — with similar savings at other resolutions. Draft at 360p/720p, edit, then upscale.
What is conversational editing?
You refine the same clip turn by turn (swap product, background, lighting, aspect ratio) without regenerating the entire video from scratch, across the full 15-second length.
Where is it available?
Generally available on the Gemini API, Google Cloud (with Provisioned Throughput), Flow, Google Vids, the Gemini app for Ultra subscribers, and Google Ads. Outputs carry a SynthID watermark.
From the blog
View all posts
OpenAI GPT-6 Cyber: Critical Cybersecurity Model, ExploitGym 48.5%, Daybreak Red Access
On November 5, 2026, OpenAI launched GPT-6 Cyber, a cybersecurity model rated Critical under its Preparedness Framework. It scores 48.5% on ExploitGym, stays in scope 99.93% of the time, found 81 novel Firefox vulnerabilities, and is rolling out through Daybreak Red.
OpenAI Images 2.6: GIFs From One Prompt, 50% Faster Images, Flare vs Sunburst and What It Costs
On November 4, 2026, OpenAI released Images 2.6 in ChatGPT, Codex and the API. It generates images 50% faster, can turn a single prompt or a rough sketch into a looping GIF, and gives developers two models, GPT-Image-2.6 Flare and Sunburst, plus image markup, SVG export and a new complexity setting.