🔍 Read the full analysis: Gemini Omni 1.2 Flash: Fast And Cost-effective With Longer Clips on ThorstenMeyerAI.com
Get business pricing on tech for your team
- Business-only prices and quantity discounts
- Tax-exempt purchasing
- Multiple users, one account, clear invoices
TL;DR
Google announced Gemini Omni 1.2 Flash on Nov. 5, adding native video clips up to 15 seconds and follow-up editing through prompts. Google lists 720p video at $0.07 per second, 30% below the stated price for version 1.1, but the announcement did not include independent performance tests or prices for other resolutions.
Google announced Gemini Omni 1.2 Flash on Nov. 5, introducing AI-generated video clips of up to 15 seconds and follow-up editing through prompts, as detailed in the original analysis. The company says 720p generation costs $0.07 per second, 30% less than the price of version 1.1, and that the model is generally available through the Gemini API and Gemini for business.
The new version raises the maximum native clip length from 10 seconds in Omni 1.1 to 15 seconds. Google says users can choose durations in one-second increments from three to 15 seconds. The company also describes a multi-turn editing feature: users can request changes such as replacing a background or adjusting lighting without generating an entirely new clip.
Google says the model can work from reference images, motion clips up to three seconds long and audio cues. It describes improvements in reference following, continuity of characters and products across frames, speech, lip-sync and camera movement. The company’s announcement included examples such as virtual try-on sequences, animated product posters and scenes with multiple speaking characters; those examples are product demonstrations, not independent evaluations.
The stated $0.07-per-second rate applies to 720p video. Google says users can draft at 360p or 720p and upscale selected clips to 1080p or 4K, but the supplied announcement does not state prices for those resolutions or explain how upscaling is billed. Google also says generated outputs include an imperceptible SynthID watermark and that Provisioned Throughput is available.
Gemini Omni 1.2 Flash Longer clips, lower stated cost
Google’s update brings longer video generation and conversational editing. Its price and quality claims still need independent evaluation.
What changes for creators
The update targets short video workflows that need multiple versions and revisions.
More room for a scene
The maximum rises from 10 to 15 seconds, with duration selectable in one-second increments.
Revise with prompts
Users can request changes such as a new background or lighting adjustment without regenerating the whole clip.
Guide the generation
Google says the model can use reference images, motion clips up to three seconds, and audio cues.
Where it is rolling out
Google says access is beginning across its products and developer platforms.
What the price covers
The announced rate applies to 720p video; other resolution and upscaling costs were not provided.
Google says creators can choose either resolution for drafts.
The stated $0.07-per-second rate is for 720p video.
Selected clips can be upscaled to 1080p or 4K, but those prices were not stated.
Claims awaiting testing
Google describes improvements, but the announcement supplies no independent benchmarks or standardized comparisons.
- Better reference following and continuity
- Improvements to speech, lip-sync, and camera movement
- Edits can preserve scene details across changes
- Reliability across varied scenes and demanding footage
- Failure rates and time saved in real workflows
- Total cost, including higher resolutions and upscaling
Lower Costs for Short Video Work
The combination of longer clips, prompt-based revisions and a lower stated 720p rate could matter to developers and businesses making short ads, explainers and social videos. If an edit can preserve the original scene as Google describes, teams may be able to produce alternate versions without rebuilding each clip. That could reduce time spent on repeated creative changes, especially for projects that require many variations.
The announced price reduction is a comparison with Gemini Omni 1.1, not with competing video-generation services. The practical cost also depends on resolution, the number of generations and revisions, and any upscaling charges. Google has not quantified how much time or money the new editing workflow saves, so the potential production benefits remain dependent on real-world performance and a fuller accounting of costs.
Products Worth Considering
Bose SoundLink Flex Bluetooth Speaker (2nd Gen) – Portable Outdoor Speaker with Hi‑Fi Audio, Waterproof and Dustproof, USB‑C, Up to 12 Hours
EcoFlow Delta 3 Max Portable Power Station – 2048 Wh LiFePO4 Battery, 2400 W Output (3400 W X‑Boost)
Apple MacBook Air 13.6-inch with M5 Chip, 16GB Memory, 512GB SSD, Sky Blue
As an affiliate, we earn on qualifying purchases.
What Changed From Omni 1.1
Gemini Omni 1.2 Flash follows Google’s Omni 1.1 model, which the company said generated clips up to 10 seconds long. The new release extends that limit by five seconds and adds multi-turn conversational editing, alongside Google’s claims of improvements to reference adherence, continuity and speech generation.
Google says the model is rolling out across its Gemini API and Gemini for business, and points developers to Google AI Studio for prototyping. The company also lists availability in products including Flow and Google Vids. Its announcement describes a rollout across Google’s platforms but does not give a schedule for when each product, account or region will receive access.
“Gemini Omni 1.2 Flash introduces native 15-second video creation, multi-turn conversational editing capabilities, and enhanced reference following.”
— Google DeepMind, in its Nov. 5 product announcement
Performance and Pricing Still Open
The announcement did not provide independent benchmarks, a detailed testing method or comparative failure rates for consistency, reference following, speech or lip-sync. It is not yet clear how reliably the model preserves faces, text, product details or scene continuity across demanding projects. Google’s examples show intended use cases, but do not establish how the model performs across varied footage and prompts.
Google says work is continuing on fast sports action, rapid script changes and complex physics. The supplied information does not specify the prices for 360p, 1080p or 4K output, how upscaling is billed, or the rollout schedule by region and product. These gaps limit comparisons of total production cost and make it difficult to judge access for particular users.
Rollout and Real-World Testing
Google says the model is rolling out through its products and developer platforms, but has not announced dates for availability in every service or account. Developers can use Google AI Studio to prototype, according to the company. A clearer picture of the model’s usefulness should emerge as users test it across different scenes, editing requests and production workflows.
Further details that would help users assess the release include pricing beyond 720p, the cost of upscaling and comparative evaluations that report both successful results and failure rates. Google has said development continues on fast action, rapid script changes and complex physics, but has not provided a schedule for those improvements.
Key Questions
What is new in Gemini Omni 1.2 Flash?
Google says the model generates native video clips up to 15 seconds long, up from a 10-second limit in version 1.1, and supports follow-up edits through prompts.
How much does Gemini Omni 1.2 Flash cost?
Google lists 720p video at $0.07 per second, which it says is 30% below the price of Omni 1.1. Prices for other resolutions and upscaling were not provided in the supplied announcement.
Where is the model available?
Google says rollout is beginning through the Gemini API and Gemini for business, with availability also listed in products including Flow and Google Vids. The company did not provide a complete schedule by product or region.
Have the claimed quality improvements been independently tested?
The announcement did not include independent benchmarks or standardized comparisons. Google’s statements about reference following, continuity, speech and lip-sync remain company claims until tested through independent evaluations.
Can users edit a clip without generating it again?
Google says users can request changes in follow-up prompts, including replacing a background or adjusting lighting. The announcement does not quantify how reliably edits preserve other details in a clip.
Primary source: Google AI · via ThorstenMeyerAI.com
