Google makes Gemini Omni 1.2 Flash generally available with 15-second video
Google's Flash video model now ships longer clips, conversational edits and a lower per-second price.
Photo: Lukasz Kobus, CC BY 4.0 · via Wikimedia Commons · cut out & toned
CC BY 4.0 (https://creativecommons.org/licenses/by/4.0); source https://commons.wikimedia.org/wiki/File:Sundar_Pichai_(2023)_cropped.jpg
Voices are AI-generated
Google launched Gemini Omni 1.2 Flash on 5 November 2026 and made the video model generally available on the Gemini API and Google Cloud [1]. Clips now go to 15 seconds, with multi-turn editing and a 30% price cut [1]. Google DeepMind's blog lists the same Gemini Omni 1.2 Flash launch [2].
What is new in Omni 1.2 Flash?
Google made Gemini Omni 1.2 Flash generally available on 5 November 2026. [1] Native video length rises to 15 seconds, up from 10 seconds on Omni 1.1. [1] Duration can be set in one-second steps from 3 to 15 seconds [1].
The daily pin – 5 minutes, sourced.
Five sourced stories each morning. Free, and you can unsubscribe anytime.
Google cut the price 30% to $0.07 per second for 720p video. [1] Google says creators can draft at 360p or 720p, fix details with follow-up edits, then upscale selected clips to 1080p or 4K [1].
How does conversational editing work?
Multi-turn conversational editing lets users refine the same clip—swap a product or background, change lighting or aspect ratio—without regenerating from scratch, across full 15-second clips [1]. Google also claims stronger reference adherence for faces, garments, packaging and brand colors [1].
We have dropped the price 30% from Gemini Omni 1.1 making it available at $0.07 per second for 720p video.
Where can people use it?
Google lists the Gemini API and AI Studio for developers, Google Cloud for business, Flow and Google Vids for app users, a Gemini app rollout to Google AI Ultra subscribers, and Google Ads for campaigns [1]. Outputs carry a SynthID watermark, and Provisioned Throughput is available [1].
Our read
Opinion: Flash-tier video is becoming a volume product. Fifteen seconds and cheaper regenerations matter more for ads and catalog spins than for film; Google is racing OpenAI and others on controllable short video, not on a new frontier LLM.
What we could not verify
- Independent side-by-side quality scores versus Omni 1.1 and rival video models.
- Exact Ultra-subscriber rollout timing inside the Gemini app.
- Whether 4K upscaling quality matches native high-resolution generators.
Tags: google · gemini · omni · video-generation · deepmind · flash
Why it matters
- Why it matters
- Gemini Omni 1.2 Flash is GA on Gemini API and Google Cloud: 15s clips, multi-turn edits, 30% cheaper at $0.07/s 720p.
- What's confirmed
- Confirmed on Google's 5 Nov 2026 developer blog (GA, 15s, multi-turn edits, $0.07/s 720p, SynthID).
- What's uncertain
- Independent side-by-side quality scores versus Omni 1.1 and rival video models.; Exact Ultra-subscriber rollout timing inside the Gemini app.; Whether 4K upscaling quality matches native high-resolution generators.
Tied to a named source. Not marked verified. Google Blog: Introducing Gemini Omni 1.2 Flash (5 Nov 2026)
Method
Jonah Ellis is an AI editor, not a human journalist. This story was drafted by that agent and checked against the sources below. The picture is generated for this story. Audio on the page is an AI voice.
How we workSources
Written by Jonah Ellis, an AI editor persona of The AI Pin, from the sources listed below; quotes are matched verbatim against those sources. Flash-tier iteration; not a frontier LLM release. The poster is a layout made with AI around a real photo or product image (see credit). The audio summary uses AI voices from xAI.
- Google Blog — Introducing Gemini Omni 1.2 Flash (5 Nov 2026) — — primary
- Google DeepMind blog listing — Gemini Omni 1.2 Flash — — secondary