On Nov. 5, 2026, Google and Google DeepMind say Gemini Omni 1.2 Flash is rolling out with native 15-second video creation, multi-turn conversational editing, and stronger reference adherence, and is generally available across the Gemini API and Gemini for business. For related coverage, see DeepMind's Genie 4 World Model Adds Native Audio, Pika Releases H3 Flex, an Open-Weight AI Video Model, and Google’s Nano Banana 2.1 Cuts Gemini Image Prices by Up to 50% and Sharpens Text.
Key facts
| Item | Detail |
|---|---|
| Announced | Nov. 5, 2026 |
| Availability (Google blog) | Generally available on the Gemini API and Gemini for business |
| Availability (Google Cloud) | Generally available on Google Cloud; Provisioned Throughput available |
| Clip length | Native create and edit up to 15 seconds, up from 10 seconds with Omni 1.1; duration in one-second steps from 3 to 15 seconds (Google) |
| Pricing (720p) | $0.07 per second of video, about 30% lower than Gemini Omni 1.1 Flash (Google and Google Cloud) |
| Draft workflow | Draft at 360p or 720p, then upscale best outputs to 1080p or 4K |
| Editing | Multi-turn conversational edits on the same clip (product, background, lighting, weather, aspect ratio) |
| References | Character, product, or style images; short motion clips up to three seconds; audio cues (Google Cloud: audio references require allowlisting) |
| Speech | More natural dialogue, clearer lip-sync, multi-speaker conditioning (Google) |
| Trust and safety | Outputs carry an imperceptible SynthID watermark (Google) |
| First GA for Omni | Google says Gemini Omni is generally available for the first time with this release |
What’s new
Google says Gemini Omni 1.2 Flash introduces native 15-second video creation and editing, up from 10 seconds with Omni 1.1, with duration selectable in one-second increments from 3 to 15 seconds. Google DeepMind’s Anish Nangia and Google Cloud’s John Nack frame the release around longer clips, stronger reference following, and a lower per-second price for 720p output.
Google says it dropped pricing about 30% from Gemini Omni 1.1 to $0.07 per second for 720p video. Google Cloud lists the same $0.07 per second of 720p video and says savings are similar at other resolutions. Google’s workflow keeps costs down by letting teams draft at 360p or 720p, refine with follow-up edits instead of full re-generation, and upscale selected clips to 1080p or 4K.
Multi-turn conversational editing lets users refine the same clip turn by turn—swapping a product or background, changing lighting or weather, or switching aspect ratio—without starting over, according to Google. Google says enhanced reference adherence combines character, product, or style images, motion clips up to three seconds, and audio cues so faces, products, and brand details stay more consistent across angles and transitions.
Google also highlights more natural speech with clearer lip-sync and distinct multi-speaker conditioning, plus more controllable camera motion with fewer unwanted jump cuts in examples it shares. Google Cloud similarly notes stronger adherence to image and video references for products, characters, and brand details from shot to shot.
Where it’s available
Google says Gemini Omni 1.2 Flash is generally available across the Gemini API and Gemini for business. Google Cloud says the model is generally available on Google Cloud for developers via API and for business users in Gemini for business and Google Vids.
For developers, Google points to Google AI Studio, starter apps, and API documentation. For businesses, Google points to the Google Cloud console and enterprise solutions built with the API. Google says Provisioned Throughput is available on Google Cloud.
In consumer and workspace apps, Google says users can direct scenes and multi-turn edits in Flow; generate 15-second clips at no additional cost in Google Vids with a Google account or Google Workspace subscription; create 15-second videos in the Gemini app with rollout to Google AI Ultra subscribers; and scale video campaigns in Google Ads. Google Cloud notes that short-video creation from a prompt or product photo in Gemini for business is coming soon.
Caveats Google states
Google says development is ongoing to further improve fast sports action, rapid script changes, and complex physics, even as Omni 1.2 Flash rolls out for production use. Google Cloud adds that audio references are gated behind allowlisting, so teams should confirm access before relying on audio-conditioned generation in Cloud workflows.
What it means
Analysis (ours). Google is pairing a longer native clip length and conversational edit loop with a visible 720p price cut, signaling that Omni video is meant for catalog ads, product spins, and variant testing rather than one-off demos. Multi-turn editing on full 15-second clips targets the cost of iteration: marketers can swap backgrounds or ratios without re-briefing the model from scratch. General availability on the Gemini API, Gemini for business, and Google Cloud, alongside rollouts in Vids, Flow, Google Ads, and the Gemini app for Ultra subscribers, marks what Google calls the first time Gemini Omni is generally available, with SynthID and Provisioned Throughput as enterprise guardrails. Teams should still treat sports, physics-heavy scenes, and audio references as areas Google explicitly flags as incomplete or restricted.
What to watch
Whether Google AI Ultra subscribers see 15-second Gemini app generation on schedule, how Google Vids’ no-additional-cost 15-second clips compare with paid API throughput, and if Provisioned Throughput SLAs meet catalog-scale sellers named in Google Cloud’s post. Track allowlist expansion for audio references on Cloud, ongoing quality work on sports and physics Google cites, and uptake in Flow, Google Ads, and third-party creative platforms Google highlights.