# Google releases Gemini Omni 1.2 Flash video generation model

> Matthew Berman says Google's Gemini Omni 1.2 Flash is faster and about 30% cheaper than its predecessor, with longer clips and in-chat editing.

- Status: reported (One outlet, not independently verified yet.)
- Topic: Products
- Published: 2026-11-11T11:00:25+00:00
- Updated: 2026-11-11T11:11:05.609237+00:00
- Web page: https://ai-news.ikangai.com/story/google-releases-gemini-omni-1-2-flash-video-generation-model/
- Seen in: Forward Future (Matthew Berman)
- Change: capability (New capability)
- Applies to: Gemini Omni 1.2 Flash, Omni 1.1, Gemini API, Google Cloud, Google Vids, Gemini app

## What changed

Gemini Omni 1.2 Flash is generally available with native 15-second video clips, up from 10 seconds in Omni 1.1, and costs 30% less, at $0.07 per second for 720p video.

Google has made Gemini Omni 1.2 Flash generally available. According to Google's announcement, the video generation model can now produce native 15-second clips, up from 10 seconds in Omni 1.1, and costs 30% less. Google's post, written by product manager Anish Nangia, prices the model at $0.07 per second for 720p video. Matthew Berman, who covered the release in his AI news roundup, summarized it as faster and 30% cheaper, with longer clips, editing inside the conversation, more natural speech and more controllable shots.

The cost change also depends on workflow. Google says users can draft at 360p or 720p, fix a detail with a follow-up edit instead of regenerating the whole clip, and only then upscale the final take to 1080p or 4K. Clip length is set in one-second increments from 3 to 15 seconds.

Google's description of reference handling is more specific than the commentary. Users can combine character, product or style images, motion clips of up to three seconds, and audio cues. Google says the model keeps faces, garments, packaging typography and brand colors consistent across camera angles. Multi-turn editing works on full 15-second clips, so a user can swap a background or change the lighting in a follow-up instruction rather than rebuilding the clip from scratch. The post offers examples but no independent measurements of consistency.

Google's post describes the model as offering faster generation but gives no timing numbers, so the speed improvement is the announcement's characterization rather than a measured result. Berman also said Google is one of the few frontier labs with a video generation model at this point, and added that OpenAI had shuttered Sora.

Google's post also lists what is still in development: fast sports action, rapid script changes and complex physics. Availability is spread across several products. Developers can use the Gemini API and Google Cloud. Google Vids offers 15-second clips at no additional cost with a Google account or Workspace subscription, and the Gemini app is rolling out to Google AI Ultra subscribers. Outputs carry an imperceptible SynthID watermark.

## Why it matters

Teams building video features may get lower generation costs and longer outputs from a faster model.

## Original source

- [Gemini Omni 1.2 Flash: 15-second video and lower pricing](https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash/)

---

AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it.

Cite as: IKANGAI AI News, "Google releases Gemini Omni 1.2 Flash video generation model", 2026-11-11, https://ai-news.ikangai.com/story/google-releases-gemini-omni-1-2-flash-video-generation-model/
