🔍 Read the full analysis: Gemini Omni 1.2 Flash Balances AI Speed, Cost, And Clip Length on ThorstenMeyerAI.com
Get the latest gadgets delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
TL;DR
Google announced Gemini Omni 1.2 Flash on Nov. 5, saying it can generate and edit videos up to 15 seconds and costs $0.07 per second for 720p output. That rate is 30% below Google’s stated price for Omni 1.1, but independent performance results and prices for other resolutions were not provided.
Google announced Gemini Omni 1.2 Flash on Nov. 5, saying its AI model can generate and edit video clips of up to 15 seconds and that 720p output costs $0.07 per second. Google says that rate is 30% below the price for version 1.1, giving developers and business customers a longer clip limit and a lower stated generation price, though independent comparisons of the model were not included.
Google says users can choose clip lengths in one-second increments from three to 15 seconds. The prior version, Omni 1.1, had a maximum native clip length of 10 seconds, according to the company. Google also describes a multi-turn editing feature: users can issue follow-up prompts to change elements such as a background or lighting instead of generating the entire clip again.
The company says the model can work from reference images, motion clips up to three seconds long, and audio cues. Google describes improvements in following those references and maintaining characters, products, and scenes across frames, as well as in speech, lip-sync, and camera movement. These are Google’s product claims; the announcement did not include independent test results, a benchmark methodology, or comparative failure rates.
Google lists the 720p rate as $0.07 per second, a 30% reduction relative to Omni 1.1, according to its announcement. It says users can draft at 360p or 720p and upscale selected clips to 1080p or 4K. The supplied announcement does not give prices for those resolutions or explain how upscaling is billed. Google also says outputs carry 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 Rates for Short Video Work
The changes target practical constraints for teams creating short ads, explainers, and social videos: a longer maximum clip, edits made through follow-up prompts, and a lower stated 720p generation rate. If the editing feature reliably preserves the rest of a scene when users request a change, it could reduce repeated work when producing alternate versions. That potential depends on results in real projects; Google did not quantify time saved or how often edits preserve requested details.
The price comparison is limited to Omni 1.1. It does not show how Omni 1.2 Flash compares in cost with other video services, nor does the per-second rate establish the full cost of a finished production. Higher-resolution output, upscaling, revisions, and access arrangements may all affect the total. For businesses and developers generating video at scale, those missing details are relevant to deciding whether the model fits a workflow.
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
Apple MacBook Air 13.6-inch with M5 Chip, 16GB Memory, 512GB SSD, Sky Blue
EcoFlow Delta 3 Max Portable Power Station – 2048 Wh LiFePO4 Battery, 2400 W Output (3400 W X‑Boost)
As an affiliate, we earn on qualifying purchases.
What Changed From Omni 1.1
Google presents Omni 1.2 Flash as an update to Gemini Omni 1.1, which the company says generated clips of up to 10 seconds. The new version raises that maximum to 15 seconds and adds conversational editing for making changes across prompts. The announcement also emphasizes reference adherence, continuity, and speech generation.
Google cited examples such as virtual try-on sequences, animated product posters, and scenes with multiple speaking characters. Those examples show the kinds of uses the company is promoting, but they are not independent evaluations. Google says development continues in areas including fast sports action, rapid script changes, and complex physics, indicating that the company has identified ongoing challenges in those tasks.
Google says the model is rolling out through the Gemini API and Gemini for business, and directs developers to Google AI Studio for prototyping. The company also points to availability in Flow and Google Vids. Its announcement says the release is rolling out across its products and platforms, but does not give a schedule for each service or account.
“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 does not establish how reliably Omni 1.2 Flash preserves faces, text, products, or scene details during generation and editing. It provides no independent benchmarks, detailed testing methodology, or failure rates for reference following, continuity, speech, or lip-sync. Google’s examples illustrate intended uses but cannot establish performance across varied footage and production needs.
Pricing beyond 720p remains unclear: Google did not state rates for 360p, 1080p, or 4K, or explain whether upscaling carries a separate charge. The announcement also lacks a platform-by-platform or region-by-region rollout schedule. Google has identified fast action, rapid script changes, and complex physics as areas where development is continuing, but supplied no dates for further updates.
Rollout and Independent Testing
Google says access is beginning across the Gemini API, Gemini for business, Flow, and Google Vids, with Google AI Studio available for developer prototyping. The company has not said when every account or platform will receive access. Users and developers will be able to evaluate the model as it becomes available, but Google did not announce a date for broader test results or for changes addressing the areas still under development.
The next useful information will include independent evaluations across different kinds of footage, clearer rates for higher resolutions and upscaling, and details on rollout timing. Until those are available, the 15-second limit and stated 720p price are announced product terms; the extent of the claimed quality gains remains to be tested.
Key Questions
What did Google announce?
Google announced Gemini Omni 1.2 Flash, an AI video model that the company says can generate and edit clips up to 15 seconds long.
How much does 720p generation cost?
Google lists 720p video at $0.07 per second and says this is 30% below the price for Omni 1.1. The announcement does not provide rates for other resolutions.
How does editing work?
Google says users can make changes through follow-up prompts, such as changing a background or lighting, rather than regenerating the full clip. The company has not published independent results showing how reliably edits preserve other details.
Where is Gemini Omni 1.2 Flash available?
Google says rollout is beginning through the Gemini API and Gemini for business, and also points to Flow and Google Vids. A schedule for availability across platforms and accounts was not provided.
Have the model’s quality claims been independently tested?
The announcement did not include independent benchmarks or comparative failure rates. Google’s statements about reference following, continuity, speech, and lip-sync remain company claims pending outside evaluation.
Primary source: Google AI · via ThorstenMeyerAI.com
