🔍 Read the full analysis: A Guide To Gemini Omni 1.2 Flash And Its Longer AI 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 video generation and editing for clips up to 15 seconds and setting 720p pricing at $0.07 per second. Google says the model is generally available through its Gemini API and Gemini for business, but the announcement offered no independent tests of its performance claims or prices for other resolutions.
Google announced Gemini Omni 1.2 Flash on Nov. 5, adding AI video generation and editing for clips up to 15 seconds and setting 720p pricing at $0.07 per second, as detailed in the original analysis. Google says the model is generally available through the Gemini API and Gemini for business; the company’s announcement did not include independent performance tests or prices for resolutions other than 720p.
The new version raises the maximum native clip length from 10 seconds to 15 seconds, compared with Gemini Omni 1.1 Flash, according to Google. Users can choose a duration in one-second increments from three to 15 seconds. Google says they can then request changes in follow-up prompts, such as replacing a background or adjusting lighting, instead of generating the entire clip again.
Google lists the price for 720p video at $0.07 per second, which it says is 30% below the price for version 1.1. The company says users can draft videos at 360p or 720p and upscale selected clips to 1080p or 4K. It did not provide pricing for those other resolutions or explain how upscaling is billed in the supplied announcement.
The company says the model accepts reference images, motion clips of up to three seconds and audio cues. Google describes improvements to reference following, continuity across frames, speech, lip-sync and camera movement. These are claims made by Google; the announcement did not provide standardized comparisons, independent results or detailed failure rates.
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
What Longer Clips Change for Creators
The longer limit and follow-up editing are aimed at common constraints in short-form video production: clips may need more time to develop an idea, and revisions can require repeated generation. If edits preserve the existing scene as Google describes, creators and production teams could make variations without rebuilding each video. That may be useful for ads, explainers and social content.
The listed 720p price could also matter for developers and businesses producing many clips. But the practical savings are not established by the announcement alone. Total costs depend on the chosen resolution, any upscaling charges and how often users need to regenerate or correct results. Google’s 30% price comparison is against version 1.1, not against other video services.
Quality will shape whether the editing features reduce work in practice. A model that changes a requested background but also alters a product, face or other scene detail may require further corrections. Google says the release improves consistency and reference adherence, but did not quantify how often it preserves those details across different kinds of footage.
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)
EcoFlow Delta 3 Portable Power Station – 1024 Wh, 1800 W
As an affiliate, we earn on qualifying purchases.
How Omni 1.2 Differs From 1.1
Gemini Omni 1.2 Flash follows Gemini Omni 1.1, which Google says generated clips up to 10 seconds long. The new version extends that maximum to 15 seconds and adds conversational editing across follow-up prompts. Google presents the release as a broader update to reference handling, continuity and speech generation, not just a change in clip length.
In its announcement, Google pointed to possible uses including virtual try-on sequences, animated product posters and scenes with multiple speaking characters. Those examples show the kinds of projects the company is targeting; they do not amount to independent evaluations of how reliably the model performs. Google also says development continues on fast sports action, rapid script changes and complex physics, areas that could challenge video consistency.
Google says the model is rolling out across its products and developer platforms, including the Gemini API, Gemini for business, Flow and Google Vids. The company directs developers to prototype through Google AI Studio. Its announcement also says outputs carry an imperceptible SynthID watermark and that Provisioned Throughput is available.
“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
What Performance and Pricing Leave Open
The announcement provided no independent benchmarks or detailed methodology for its claims about continuity, reference adherence, speech or lip-sync. It is not clear how often follow-up edits preserve requested character, product and scene details, or how the model handles difficult footage. Google itself identifies fast sports action, rapid script changes and complex physics as areas where development is continuing.
Pricing details are also incomplete. Google named a rate for 720p video only, without specifying the costs of 360p, 1080p or 4K output, or how upscaling affects a bill. The supplied announcement did not give a region-by-region rollout schedule or say when every eligible account would have access. Those details matter to users deciding whether the listed rate reflects the full cost of their workflow.
Rollout and Independent Testing
Google says access is rolling out across its platforms, but has not provided a schedule for every product, region or account. Developers can test the model through Google AI Studio and the Gemini API, while Google also lists availability through Gemini for business, Flow and Google Vids. The timing of access may vary; the announcement does not give a complete rollout calendar.
The next evidence to watch is how the model performs in varied real-world workflows, including whether edits keep requested details intact and how often users must regenerate footage. Clearer pricing for resolutions beyond 720p and upscaling would help users compare the full cost of production. Google says work will continue on fast action, rapid script changes and complex physics, but announced no dates for those improvements.
Key Questions
What is Gemini Omni 1.2 Flash?
It is Google’s video-generation and editing model announced on Nov. 5. Google says it creates clips up to 15 seconds and supports edits through follow-up prompts.
How much does 720p video cost?
Google lists a price of $0.07 per second for 720p video and says that is 30% below the price of Gemini Omni 1.1. The announcement did not give rates for other resolutions.
Where is the model available?
Google says it is rolling out through the Gemini API and Gemini for business, and also points to Flow and Google Vids. The company did not provide a schedule for access on every platform or account.
Are Google’s performance claims independently verified?
Not in the supplied announcement. Google describes improvements to reference following, continuity, speech and lip-sync, but did not provide independent tests, standardized comparisons or failure rates.
What remains uncertain about the cost?
Google provided a rate for 720p but did not specify prices for 360p, 1080p or 4K, or explain how upscaling is billed. That leaves the full cost of higher-resolution workflows unclear.
Primary source: Google AI · via ThorstenMeyerAI.com
