Gemini Omni Flash 1.1

Gemini Omni Flash 1.1 is the 1.1 release of Google's multimodal video model, served on fal as its own text-to-video and image-to-video endpoints next to the original Gemini Omni Flash. fal describes it as generating video with synchronized native audio, grounded in Gemini's real-world knowledge and physics, with camera moves directed in plain language. The endpoints take 3 to 10 seconds at 360p, 720p, 1080p or 4K, and the image endpoint accepts an optional last frame to interpolate towards. There is no audio switch: every clip comes with sound.

Anvisha Pai

Anvisha Pai, Co-founder & CEO, Voyager

Tested

Google DeepMind · released

Gemini Omni Flash 1.1 filming itself as robot barista, generated by us.
›What we asked for

A self-portrait of Gemini Omni Flash 1.1, Google's conversational video model: a friendly robot barista pulls an espresso, steams milk and slides the cup across the counter to camera with a wink, cafe ambience and the hiss of the steam wand.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

At a glance

Price
$0.10 a second at 720p on fal, $0.03 at 360p, $0.15 at 1080p and $0.30 at 4K, read October 22, 2026. A five-second 720p clip is $0.50.
Measured wait
31 to 60 seconds from queue submission to a five-second 720p clip, across nine prompts in one batch. Not a service guarantee.
Length
3 to 10 seconds in whole seconds; fal's default is 8.
Audio
Always on. The endpoints have no switch to turn it off, and every one of our clips carried an audio track.
Inputs
Text, or a first frame with an optional last frame that the model interpolates towards.

Other Gemini Omni models: Gemini Omni Flash. Compare all 2.

Anvisha's take

Gemini Omni Flash 1.1 is a cheaper and steadier Omni Flash, with one habit it has not lost. At $0.10 a second at 720p it undercuts the original's $0.13 on fal, every clip came back in 31 to 60 seconds, and the hard prompts went well: both title lines spelled correctly, a two-handed kettle pour into a paper filter with the grounds blooming, a dense market with the dog on its lead and the busker's open guitar case, and a woodblock storm with visible wood grain in the sky. The habit is product invention. The turntable dripper grew a handle, and in image-to-video our plain dripper grew a handle again and filled with coffee like a mug, exactly as version 1 did. The spill also turned three ice cubes into six. Use it for scenes and type; check every frame of a product shot. Observations come from sampled frames; audio was generated on every clip but not scored by ear.

Gemini Omni Flash 1.1 real output: the same 9 clips every model gets

Every video model on this site gets the same 9 clips, so you can compare like with like. These are the clips Gemini Omni Flash 1.1 returned, one try each, nothing re-rolled or retouched. Each tile shows one frame of the clip until you press play. Generated on . The 9 clips took 31 to 60 seconds each and cost $4.50 in total.

Product turntable5s clip · 31s wait · $0.50

A clean product shot that holds its shape through a full slow rotation.

›What we asked for

A matte black ceramic pour-over coffee dripper rotating slowly on a white turntable, soft studio light, seamless white background, product video, no text.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

Person speaking5s clip · 41s wait · $0.50

A face, lip sync and a spoken line, where the model makes audio.

›What we asked for

A woman in her 40s with short grey hair stands in a bright kitchen, looks at the camera and says 'Good morning, the coffee is ready', natural window light, handheld feel, she smiles at the end.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

Animated title card5s clip · 47s wait · $0.50

Set text that stays spelled correctly while it moves.

›What we asked for

A title card reading 'MODA SUMMER SESSIONS' animates in over slow-motion footage of a festival crowd at dusk, then a smaller line 'Friday 12 June' fades in beneath it. Bold condensed type, tangerine on navy.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

Camera move5s clip · 47s wait · $0.50

A steady drone push-in with stable geometry.

›What we asked for

Drone shot pushing slowly forward over a coastal town at sunrise, terracotta roofs, fishing boats in the harbour, long shadows, cinematic and steady.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

Physics5s clip · 31s wait · $0.50

A spill in slow motion: does water behave like water.

›What we asked for

A glass of water tips over on a wooden table and spills in slow motion, water and three ice cubes sliding across the wood, macro lens, morning light.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

Hands at work5s clip · 60s wait · $0.50

Hands, a kettle and a steady pour without extra fingers or teleporting objects.

›What we asked for

Close-up of hands pouring hot water from a gooseneck kettle in slow circles into a pour-over coffee dripper, steam rising, shallow depth of field, warm cafe light.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

Busy scene5s clip · 47s wait · $0.50

Many people and objects moving at once without merging.

›What we asked for

A crowded Saturday farmers market seen from slightly above, shoppers with tote bags, a dog on a leash, a busker with a guitar, bunting swaying, late morning light, gentle camera drift.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

Specific art style5s clip · 47s wait · $0.50

A named style held across every frame rather than drifting to photoreal.

›What we asked for

A lighthouse on a rocky cliff in a storm, in the style of a Japanese ukiyo-e woodblock print, waves crashing in flat colour with visible wood grain, animated like moving paper cutouts.

google/gemini-omni-flash/v1.1/text-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

Image to video5s clip · 47s wait · $0.50

Bring a still product photo to life without changing the product.

›What we asked for

The coffee dripper slowly fills as coffee drips through it, steam rising, the camera drifting gently around it, the dripper itself unchanged. (starting from The Nano Banana Pro product shot from the image fixture set.)

google/gemini-omni-flash/v1.1/image-to-video
aspect_ratio: 16:9, resolution: 720p, duration: 5
returned 1280 by 720 pixels

How the cost under each picture was worked out: fal's Gemini Omni Flash 1.1 rate of $0.10 per second at 720p (fal.ai/models/google/gemini-omni-flash/v1.1/text-to-video, read 2026-10-22; the pricing API's $0.03 a second is the 360p rate) for the 5 seconds requested; fal does not return the charge.

Compare Gemini Omni Flash 1.1

Gemini Omni Flash 1.1 pricing

WhereUnitPriceSource
falSecond at 720p
Audio included. The same rate applies to text-to-video and image-to-video. fal's pricing API reports $0.03 a second, which is the 360p rate.
$0.10fal model page, read
falSecond at 360p
The draft resolution.
$0.03fal model page, read
falSecond at 1080p$0.15fal model page, read
falSecond at 4K$0.30fal model page, read

Is Gemini Omni Flash 1.1 free?

The fal endpoints are paid per second of video. We have not found a free allowance for this version on fal.

  • •The 360p draft rate, $0.03 a second, is the cheapest way to test a prompt before paying for 720p or above.

fal model page, read

Where to use Gemini Omni Flash 1.1

  • fal, text-to-video · Hosted API and playground; the endpoint used for eight of the clips below.
  • fal, image-to-video · First frame plus an optional last frame; used for the image-to-video clip.
  • Voyager · Runs inside Voyager, the agent for creative work, with your own fal key.

Voyager

Run Gemini Omni Flash 1.1 inside Voyager

Voyager is an agent for creative work that runs every model in this reference, Gemini Omni Flash 1.1 included. Brief it, and it picks the model, makes the thing and hands back something you can edit. Create an account to get started.

What we noticed running Gemini Omni Flash 1.1

Gemini Omni Flash 1.1 limits and API parameters

LimitValue
Duration3 to 10 seconds, in whole seconds; 16:9 or 9:16 only.
fal API schema, read
Output sizeEvery clip came back at 1280 by 720, 24 frames a second, 5.03 seconds long. The square product photo was cropped to 16:9 because the endpoint offers no square or automatic ratio.
fal API schema, read
›Every setting, for developers

fal (google/gemini-omni-flash/v1.1/text-to-video)

fal API schema, read

ParameterTypeValuesDefault
promptstringUp to 20,000 characters
Required.
durationinteger3 to 108
resolutionenum360p, 720p, 1080p, 4k720p
aspect_ratioenum16:9, 9:1616:9

Gemini Omni Flash 1.1 image-to-video

fal API schema, read

ParameterTypeValuesDefault
image_urlURLImage
Required; the first frame.
end_image_urlURLImage
Optional; the model interpolates from the first image to this one.

What Gemini Omni Flash 1.1 will not make

The hosted endpoints apply fal's content checks on top of Google's own. None of our nine prompts was refused. Review the provider terms for your intended use.

fal model page, read

Alternatives to Gemini Omni Flash 1.1

Frequently asked questions

How much does Gemini Omni Flash 1.1 cost?

On fal, $0.10 a second at 720p, read October 22, 2026: $0.50 for a five-second clip. 360p drafts are $0.03 a second, 1080p $0.15 and 4K $0.30, audio included at every size.

What changed from Gemini Omni Flash?

On fal, a lower 720p price ($0.10 a second against $0.13), a 360p draft tier, 4K output and an optional last frame on image-to-video. On our prompts it still adds a handle to the handleless dripper, as version 1 did.

Can I turn the audio off?

No. The 1.1 endpoints on fal have no audio setting; every clip comes with sound.

How this page is made

Prices, limits and settings are read from the linked vendor and host pages on the dates shown. Every picture was generated by us through fal with the request shown under it, and the original files are kept unedited. A generation that failed is shown as a failure. Model and vendor names are used to identify the products; no vendor imagery appears on this page.

Anvisha Pai

Anvisha Pai

Co-founder & CEO, Voyager

Anvisha is the CEO of Voyager and a repeat, Y Combinator-backed startup founder. She was previously a PM at Dropbox. She believes nobody should need a design degree to make something that looks great.