CoAI
News

Google Releases Video Generation AI "Gemini Omni 1.2 Flash," Extending Clips to Up to 15 Seconds and Cutting Prices by 30%, With Anyone Able to Make Up to 3 Videos a Month Free in Google Vids

On November 5, 2026, Google released "Gemini Omni 1.2 Flash," an AI model for creating and editing video. The maximum length of a single clip has grown from 10 seconds to 15 seconds, and the API price is 30% lower than the previous version. In the video creation tool Google Vids, anyone with a Google account can make up to 3 15-second videos a month for free.

November 5, 20263 min read
Screenshot of the official Google — Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips page
Google — Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips · SourceCaptured: November 6, 2026

Screenshots show the official pages on the capture date and may differ from the pages at publication. Select an image to enlarge it.

On November 5, 2026 (US time), Google released "Gemini Omni 1.2 Flash," an AI model for creating and editing video. Compared with the previous version, Omni 1.1, it can make longer clips and costs less. Google also made the new model available to try for free in its video creation tool, Google Vids.

What changed

The main changes Google highlighted are as follows.

  • Length: a single video can be up to 15 seconds long (the previous version allowed 10 seconds), and you can specify anywhere from 3 to 15 seconds in 1-second steps
  • Resolution: draft quickly at 360p or 720p, then upscale the ones you like to 1080p or 4K
  • Reference fidelity: it is now easier to keep the face, clothing and colors of a reference person consistent throughout the video
  • Visual drift: reduced the effect where the look gradually changes as frames progress
  • Audio: speech sounds more natural, lip-sync mismatches are reduced, and multiple speakers are supported
  • Editing: you can revise the same video many times through back-and-forth conversation

Videos it creates carry "SynthID," an invisible watermark indicating that they were made by AI.

Pricing and where to use it

The API price is 30% lower than the previous version. For 720p video, it costs $0.07 per second.

Gemini Omni 1.2 Flash is available in the following places.

  • The Gemini API and Google Cloud (Vertex AI) for developers: generally available; you can also try it in Google AI Studio
  • Flow (Google Labs), a filmmaking tool
  • Google Vids, a video creation tool
  • The Gemini app: rolling out to subscribers of the top-tier Google AI Ultra
  • Google Ads (Asset Studio)

Up to 3 free videos a month in Google Vids

In Google Vids, you can create up to 3 15-second videos a month for free, whether you use a personal Google account or a Google Workspace subscription. Google showcases uses such as creating product introduction videos in one go, and turning still images into videos while preserving the look of the people and scenes. Google Vids is available at vids.new.

CoAI's take

In video generation AI, while OpenAI's Sora has ended its app and API, Google as well as China's Kling, Seedance, Hailuo and others continue to make improvements. Omni 1.2 Flash is not a top-tier model aiming for the highest quality, but a version that prioritizes speed and low cost. At 15 seconds, clips are long enough for short social media videos and product introductions.

The Google Vids free allowance of 3 videos a month is on the small side, but being able to try it with a personal account makes it easy to get started. However, the announcement does not say whether it is available in Japan or how good the Japanese-language audio is. If you use it for work, check the quality of the videos you actually create, and how people and trademarks are handled, before putting it to use.

Sources

Tools mentioned in this article

Back to news