AI video model

Gemini Omni Flash 1.2

Google's native-audio video model, from fast 360p drafts to 4K

Gemini Omni Flash 1.2 is Google's video model that writes picture and sound in one pass: dialogue, music and effects come out of the same generation as the image. On Aicut you pick it from the same prompt box as every other model, at a price shown before you generate.

360p / 720p / 1080p / 4k

16:9 / 9:16

3-15s

Generate with Gemini Omni Flash 1.2

Free account. The token price is shown before anything is generated.

Made with Gemini Omni Flash 1.2

Real clips from the model, unedited.

Why creators use Gemini Omni Flash 1.2

Speech, ambience and effects are generated together with the picture, so a talking scene, an interview or a product reveal arrives with its sound already in place instead of needing a separate voiceover pass.

The same model spans four resolution tiers. A cheap 360p draft lets you test an idea, and the prompt that works can be rendered again at 1080p or 4K for the version you post.

What you can make with Gemini Omni Flash 1.2

•Talking clips and street-interview formats with spoken dialogue in the same render.
•Product reveals and ads that keep a product consistent across shots from up to six reference images.
•Image-to-video from a start frame, or a controlled transition between a start and an end frame.
•Fast low-cost drafts at 360p before committing to a 1080p or 4K final.

How to generate with Gemini Omni Flash 1.2

01
Select Gemini Omni Flash 1.2
Open the AI Video Generator and pick Gemini Omni Flash 1.2 from the model list, or start straight from this page.
02
Write the shot, including what is heard
Describe the action and camera, then the sound: quote any spoken line exactly and name the effects or music you want, because the model generates them with the picture.
03
Add a start frame or reference images if you have them
Upload a start frame, optionally with an end frame, or up to six reference images of a product, character or style. Frames and reference images are separate modes and cannot be combined.
04
Pick length and resolution, then generate
Choose 3 to 15 seconds and a resolution from 360p to 4K. The price on the button updates as you change them, and the finished clip is ready to download or publish to TikTok, YouTube Shorts and Instagram Reels.

What every Gemini Omni Flash 1.2 clip includes

Native audio, always on
Dialogue, music and sound effects are generated in the same pass as the picture.
3 to 15 seconds
Any length in one-second steps, priced per second of the clip you choose.
360p to 4K
Four resolution tiers, from a cheap draft to a 4K final, each with its own per-second rate.
Start and end frames
Animate a still from a start frame, or guide the clip between a start and an end frame.
Up to six reference images
Keep a product, character or look consistent by showing the model what it should match.
Vertical or horizontal
9:16 for Shorts, Reels and TikTok, or 16:9 for YouTube and the web.

What Gemini Omni Flash 1.2 does best

•Sound comes with the picture: spoken lines, ambience and effects are generated in the same render, which suits talking and interview formats.
•One prompt scales from a cheap 360p test to a 4K final, so an idea can be tried quickly before paying for the high-resolution version.
•Reference images keep a product or character consistent, which Google names as a focus of this release.

What to know before you generate

•One clip is at most 15 seconds, so longer pieces are built from several clips in the editor.
•Reference videos and video editing are not offered for this model on Aicut yet; it takes text, frames and reference images.
•Google says fast sports action, rapid scene changes and complex physics are still being improved, so simpler staging gives steadier results.

What does Gemini Omni Flash 1.2 cost?

The price below is per second of video at the pay-as-you-go rate. A multishot sequence is billed for the combined length of every scene at these same rates, never multiplied per scene.

Resolution	Price per second	Length
360p	0.1 tokens ($0.06/s)	3-15s
720p	0.25 tokens ($0.15/s)	3-15s
1080p	0.3 tokens ($0.18/s)	3-15s
4k	0.6 tokens ($0.36/s)	3-15s

Gemini Omni Flash 1.2 FAQ

What is Gemini Omni Flash 1.2?

It is Google's video model that generates picture and sound together from text, a start or end frame, or reference images. Version 1.2 extends clips to 15 seconds and, according to Google, follows references more closely and improves dialogue and lip-sync over 1.1.

Does every clip have sound?

Yes. Audio is always on for this model: dialogue, music and effects are generated with the picture, and there is no silent mode to switch to.

Does the price change with resolution or clip length?

Yes. Gemini Omni Flash 1.2 is priced per second of video at a rate set by the resolution, so 360p is the cheapest per second and 4K the most expensive, and a longer clip costs more at that rate. The exact price is shown on the button before you generate.

Can I use my own images?

Yes. Use a photo as the start frame, add an end frame to guide where the clip ends, or upload up to six reference images of a product, character or style. Frames and reference images cannot be combined in the same generation.