Gemini Omni 1.2 Flash: What's New and How Creators Can Use the Multimodal Update

Key takeaway: Google launched Gemini Omni 1.2 Flash on 5 November 2026. It’s Google’s video model for making and editing clips from text, images, audio and video. The update brings 15-second clips (up from 10), editing by conversation, closer reference following and a 30% lower API price: about $0.07 a second at 720p (USD). Creators can try it at no cost in Google Vids (three 15-second videos a month) and Google Flow (50 credits a day, clips up to 10 seconds).

• Best fit: short vertical b-roll, product clips, ad variants and explainer scenes that you then cut into your own edit.
• Watch out for: credit costs at 720p, 15-second clips needing a paid plan in Flow, and YouTube’s rules on disclosing realistic AI content.

Research-based guide. We haven’t generated any videos with Omni 1.2 Flash. Facts come from Google’s own pages, checked 10 November 2026. Prices are in USD and exclude tax.

What Google launched

Google’s launch post is dated 5 November 2026. The Google DeepMind model card describes the model as “our next step towards models that can create and edit anything from any input—starting with video”.

• Name and ID: Gemini Omni 1.2 Flash, model ID gemini-omni-1.2-flash.
• Inputs: text, images, audio and video files.
• Output: video with audio.
• Status: generally available on the Gemini API and Google Cloud. The Google Cloud docs list the release date as 5 November 2026.

What’s new in Omni 1.2 Flash

From Google’s launch post and the Google Cloud announcement:

1. Longer clips. Generate and edit videos up to 15 seconds, up from 10 with Omni 1.1. You can set the length in one-second steps from 3 to 15 seconds.
2. Editing in conversation. Refine the same clip turn by turn: swap a product or background, change the lighting or weather, or switch the aspect ratio, without starting again.
3. Closer reference following. Guide a clip with character, product or style images, short motion clips (up to three seconds) and audio cues. Google says faces, garments, packaging text and brand colours stay more consistent across camera angles.
4. More natural speech. Google cites more fluid dialogue, clearer lip-sync and distinct voices for several speakers.
5. Smoother camera moves. Google says long moves such as fly-throughs and orbits have “significantly fewer unwanted jump cuts”.
6. Draft cheap, then upscale. Make drafts at 360p or 720p, then upscale the ones you keep to 1080p or 4K.
7. Lower price. 30% less than Omni 1.1 Flash on the API.

Google is also clear about limits. It says work is ongoing on “fast sports action, rapid script changes and complex physics”. The model card says Google is restricting the ability to change people’s speech during edits for now. Audio references on Google Cloud are “gated behind allowlisting”.

All outputs carry Google’s invisible SynthID watermark. The Cloud docs also list support for C2PA Content Credentials.

These quality claims are Google’s own. We haven’t tested them.

Specs creators care about

From the Google Cloud model docs, checked 10 November 2026:

Spec	Gemini Omni 1.2 Flash
Clip length (generate or edit)	3 to 15 seconds
Extend a clip	adds 3 to 10 seconds
Aspect ratios	16:9 and 9:16
Resolutions	360p, 720p, 1080p, 4K
Reference images	up to 10 per prompt
Input video for editing	up to 15 seconds

These are the API limits. The apps can set lower limits, as the next section shows.

Where you can use it, and what it costs

Google Vids: the simplest free route

Google says Vids now runs on Omni 1.2 Flash. Anyone with a Google account or a Google Workspace subscription can make up to three 15-second videos a month at no cost. Vids also lets you add avatars, music and voice-over, which suits quick promos and explainers.

Google Flow: daily free credits

The Flow credits page says everyone gets 50 Flow credits a day, with or without a subscription. Unused daily credits don’t roll over. Omni Flash 1.2 costs:

In Flow	Who can use it	Cost
Clips up to 10 s, 360p	All users	1 credit a second
Clips up to 10 s, 720p	All users	3 credits a second
Clips of 11 to 15 s	Google AI Plus, Pro and Ultra only	2 (360p) or 6 (720p) credits for each extra second
Extend by 3 to 10 s	Plus, Pro and Ultra only	1 (360p) or 3 (720p) credits a second
Upscale to 1080p	Plus, Pro and Ultra only	0 credits for 1 to 10 s
Upscale to 4K	Ultra only	50 credits for 1 to 10 s

Our maths: 50 free credits cover one 10-second 720p clip (30 credits) plus two 10-second 360p drafts (10 credits each). Without a subscription, Google says you may not be able to make videos at peak times, roughly 2 pm to 5 pm UTC.

Paid plans add monthly Flow credits: 200 on Google AI Plus, 1,000 on Pro, and 10,000 or 25,000 on the two Ultra tiers. Google’s plans page lists Ultra at $99.99 or $199.99 a month in the US. The page didn’t show Plus and Pro prices when we checked, so look them up there for your country.

The Gemini app: paid plans only

According to Gemini Apps Help, making videos in the Gemini app needs a Google AI plan on a personal account, or a qualifying Workspace licence. It isn’t available to users under 18.

• Clips run 3 to 10 seconds, or up to 15 seconds on Google AI Ultra.
• You can keep editing a clip in the same conversation, and extend it by up to another 10 seconds.
• You can download a video or use Share on YouTube.
• Uploading your own videos for edits, and creating an avatar from your face and voice, aren’t available in the EEA, Switzerland, the UK and some US states.

The Gemini API: pay per second

The Gemini API pricing page lists Omni 1.2 Flash on the paid tier only. There’s no free API tier. Input costs $1.50 per million tokens and video output $12 per million tokens. Google converts that to effective prices per second of video:

Resolution	About per second	10-second clip	15-second clip
360p	$0.023	$0.23	$0.35
720p	$0.07	$0.70	$1.04
1080p (upsampled)	$0.104	$1.04	$1.56
4K (upsampled)	$0.209	$2.09	$3.13

The 360p, 1080p and 4K clip prices are our maths from Google’s per-second figures. From 3 December 2026, API requests to gemini-omni-1.1-flash will route to 1.2 and be billed at 1.2 rates.

The model card also lists YouTube among Omni 1.2 Flash’s channels. We didn’t find a YouTube page naming the 1.2 version, so we haven’t covered it here.

How creators can use it: a simple workflow

1. Plan the shot list first. Write down the three to five short clips your video needs, such as an opening hook, product close-ups and a closing card. Generated clips work best as parts of your edit, not the whole video.
2. Gather references. Use product photos you took, or character images you have the rights to use. Google’s help pages say to upload only images you have the right to use.
3. Draft at 360p in Flow. It costs 1 credit a second, so you can try several ideas from the free 50 credits.
4. Fix details by conversation. Change the background or lighting in a follow-up edit instead of starting again.
5. Make your final clip. Use Vids for a free 15-second version, Flow at 720p, or upscale on a paid plan.
6. Choose the shape for the platform. Use 9:16 for Shorts, Reels and TikTok, and 16:9 for YouTube b-roll.
7. Disclose where needed. If a clip looks like a real event or person, follow our YouTube AI disclosure checklist.

Good starter ideas: a product turning on a table, a 15-second explainer scene, ad variants with different backgrounds, or a cutaway for a talking-head video.

Less good fits, by Google’s own account: fast sports action and complex physics.

How it compares

For a wider look at Google Flow, Kling and Runway, see our best AI video generator comparison. Kling’s latest model is covered in our Kling 4 launch news. We haven’t tested these tools side by side.

Turn one video into many

Generated clips are one input. Getting each finished video out as clips, posts and articles is another job. Creator Autopilot does that, posted with your approval or on rules you set. That’s our own service.

FAQ

What is Gemini Omni 1.2 Flash?

It’s Google’s video generation and editing model, launched on 5 November 2026. It makes video with audio from text, images, audio and video inputs. Model ID: gemini-omni-1.2-flash.

What’s new in Gemini Omni 1.2 Flash?

Clips up to 15 seconds (up from 10), multi-turn editing by conversation, closer reference following, more natural speech, and an API price 30% lower than Omni 1.1 Flash.

Is Gemini Omni 1.2 Flash free?

There are free routes. Google Vids gives three 15-second videos a month at no cost. Google Flow gives everyone 50 credits a day, enough for clips up to 10 seconds. The Gemini app needs a paid Google AI plan, and the API has no free tier.

How much does the Gemini Omni 1.2 Flash API cost?

About $0.07 a second of 720p video (USD), or roughly $1.04 for a 15-second clip. 360p is about $0.023 a second, and 4K about $0.209.

Can Gemini Omni 1.2 Flash make vertical videos?

Yes. Google’s docs list 9:16 and 16:9.

Are Gemini Omni videos watermarked?

Yes. Google says outputs carry an invisible SynthID watermark. The Cloud docs also list C2PA Content Credentials.