Understand this story
On November 5, 2026, TestingCatalog discovered a reference record for the Gemini Omni 1.2 Flash model on GCP, and stated that it would be a minor upgrade to the current Omni 1.1 Flash video generation model. The next day, Google DeepMind officially launched Gemini Omni 1.2 Flash, which natively supports video generation of up to 15 seconds and allows durations to be specified between 3 and 15 seconds in 1-second increments; its price is 30% lower than that of Gemini Omni 1.1, at $0.07 per second for 720p video. The new version enhances adherence to reference images and consistency of characters, products, and scenes, and supports multi-turn conversational editing, allowing products or backgrounds to be replaced without regenerating the entire video. The model is fully available in the Gemini API and Gemini for business, and its output carries a SynthID watermark.
AI-generated from public reports
Latest development · Report
Gemini Omni Flash 1.2 launches on fal, supporting video generation and editing with native audioDevelopments
2 confirmed developments
- Source:Google DeepMind
- Source:Testing Catalog
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 6
falSelected
Gemini Omni Flash 1.2 launches on fal, supporting video generation and editing with native audio
Google's Gemini Omni Flash 1.2 is now available on fal and can generate videos with native audio from text, images, or reference clips. The model can also edit existing footage with natural language instructions, extend any video by 3 to 10 seconds, and upscale clips to 1080p or 4K, with outputs up to 15 seconds long.
Gemini
Google Releases Gemini Omni 1.2 Flash Video Generation Model
Gemini Omni 1.2 Flash is rolling out to all Google AI subscribers starting today, supports multi-turn conversational video editing in the Gemini app, and improves visual stability. Google AI Ultra subscribers can generate and edit videos up to 15 seconds long. According to Google, the model supports draft generation at 360p or 720p ($0.07/s) followed by upscaling to 1080p or 4K, at 30% lower cost, and supports any duration from 3 seconds to 15 seconds, multi-speaker dialogue, and more coherent camera movement.
Testing Catalog
Google Omni 1.2 Flash Video Generation Model Launches on AI Studio and Gemini API
Google's Omni 1.2 Flash video generation model is now available on Google AI Studio and the Gemini API, supporting videos up to 15 seconds long and up to 4K resolution, with a 30% cost reduction.
RunwayRelated discussion
Runway joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Unite.AI
Google Gemini Omni 1.2 Flash is now generally available, with native clips extended to 15 seconds
On November 5, 2026, Google announced the general availability of Gemini Omni 1.2 Flash, raising the native video clip limit from 10 seconds in Omni 1.1 to 15 seconds and adding multi-turn conversational editing. Pricing for 720p output has been cut by 30% to about $0.07 per second, billed at $12 per million video output tokens, meaning a 10-second clip costs about $0.70 and a 15-second clip about $1.04, with no free tier offered. A comparative evaluation by Google DeepMind shows that 1.2 beats 1.1 on text-to-video visual consistency by 62% to 38%; after a four-week transition period, 1.1 will be automatically routed to 1.2 on December 3, 2026.
Logan Kilpatrick
Google Launches Gemini Omni Flash 1.2, Extending Video Generation to 15 Seconds
Google has released Gemini Omni Flash 1.2, extending video generation duration to 15 seconds and strengthening cinematic control over camera perspectives. The new version supports multi-turn conversational editing, reduces visual drift, and is priced 30% lower than Omni Flash 1.1.
Philipp SchmidSelected
Gemini Omni 1.2 Flash Launches on Gemini API and GoogleAIStudio
Gemini Omni 1.2 Flash is now available on Gemini API and GoogleAIStudio, supports 15-second video clips, and improves conversational video editing and consistency. The model maintains fast speeds, and the 720p price has been reduced by 30% to $0.07/s.
Google AISelected
Google Releases Gemini Omni 1.2 Flash, Extending Video Generation Length to 15 Seconds
Google has released Gemini Omni 1.2 Flash, raising the maximum length for video generation and editing to 15 seconds, and improving visual issues such as scene consistency over time, character speech, and jump cuts, with higher fidelity to uploaded reference materials. The model now offers 15-second video generation in Flow, Google Vids, and the Gemini App, and API pricing is 30% lower than the previous generation, at $0.07 per second for 720p video.
Google AI BlogRelated discussion
Google AI Blog joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Nov 5
Testing Catalog
Gemini Omni 1.2 Flash Appears on GCP
A reference record for the Gemini Omni 1.2 Flash model has appeared on GCP. It is said to be a minor upgrade to the current Omni 1.1 Flash video generation model.
Google DeepMindFirst-partySelected
Google DeepMind releases Gemini Omni 1.2 Flash, supporting 15-second video and cutting prices by 30%
Google DeepMind launches Gemini Omni 1.2 Flash, with native support for video generation of up to 15 seconds, priced 30% lower than Gemini Omni 1.1, at $0.07 per second for 720p video. The new version enhances reference image adherence and consistency of characters, products, and scenes, and supports multi-turn conversational editing, allowing products or backgrounds to be replaced without regenerating the entire video. The model is fully available in the Gemini API and Gemini for business, and outputs carry a SynthID watermark.
Google AI BlogFirst-partySelected
Google Releases Gemini Omni 1.2 Flash: Supports 15-Second Videos, Price Reduced by 30%
Google has released Gemini Omni 1.2 Flash, which natively supports video generation of up to 15 seconds and allows durations to be specified between 3 and 15 seconds in 1-second increments. This version is priced 30% lower than Omni 1.1, at $0.07 per second for 720p video, while also enhancing reference image adherence and multi-turn conversational editing capabilities. The model is fully available in the Gemini API and Gemini for business, and outputs carry a SynthID watermark.