Gemini Omni: video that speaks

    Give it text, references, exact frames or a clip of yours, and get back a 3 to 15 second video. Omni Video and 1.1 Flash add 30 built-in voices.

    Try Gemini Omni VideoCompare models
    Gemini Omni Video
    Gemini Omni 1.1 Flash
    Gemini Omni Video

    The lineup

    Prompt: Cinematic side-profile tracking shot of a silver sports coupe driving along a sunny coastal highway. The camera dollies smoothly alongside the car at matching speed, keeping the car centered in perfect side view (90-degree profile). Bright midday sunlight, deep blue ocean and a low guardrail on the right, clear sky, distant coastline. The car rolls steadily left-to-right; wheels spinning, subtle motion blur on the road and background rushing past. Clean automotive-commercial look, glossy paint reflections, smooth continuous motion. Locked, stable framing of the vehicle in profile.

    • 16:9
    • 4s
    • HD

    Prompt: Keep the exact same shot as the reference video: identical sunny coastal highway, same deep blue ocean and low guardrail behind, same road surface, same bright midday lighting, same side-profile camera tracking move at the same speed, same left-to-right motion and motion blur. Change ONLY the vehicle: replace the car with a bright glossy red modern sports coupe (candy-red paint with rich reflections, low sleek stance, sporty alloy wheels). The red sports car occupies the exact same position and framing in perfect 90-degree side profile, wheels spinning, rolling steadily. Everything else in the scene stays identical to the reference.

    • 16:9
    • 4s
    • HD

    Prompt: The frog character sits calmly on a large dewy leaf deep in a lush tropical rainforest at golden morning light. Soft mist drifts, water droplets glisten, ferns and glowing bokeh greenery fill the background. The frog blinks slowly and looks around, content in its natural habitat. Slow cinematic push-in, shallow depth of field, warm natural ambience.

    • 16:9
    • 4s
    • HD

    Gemini Omni Video

    The original Omni: references, voices and edits to your footage.

    The first Omni model. It generates from text, images and saved characters, and rebuilds clips you already have: attach a source video, pick a window of up to 10 seconds inside its first 30, describe the change.

    Best for

    • Restyling footage you already shot
    • Narrated spots in one of 30 voices
    • A recurring character across several shots

    Pick another model for

    • Fixed first and last frames (use a Flash version)
    • Driving the clip with your own audio file

    Specs

    Inputs
    Text plus 7 reference slots
    Source video
    Uses 2 slots, 10 s window
    Length
    4, 6, 8 or 10 s
    Resolution
    720p, 1080p, 4K
    Aspect ratio
    16:9 or 9:16
    Audio
    With the clip, 30 voices
    Try Gemini Omni Video
    See prices

    Price

    OptionRateUnit
    720p or 1080p, 4 s110credits
    720p or 1080p, 6 s140credits
    720p or 1080p, 8 s170credits
    720p or 1080p, 10 s200credits
    720p or 1080p, with a reference video260credits
    4K, 4 s230credits
    4K, 6 s260credits
    4K, 8 s290credits
    4K, 10 s320credits
    4K, with a reference video380credits
    Current rates in credits.

    Prompt: A lighthouse keeper in a wool sweater climbs the last turn of a spiral staircase at dusk, lights the great lamp and says quietly: "Forty years, and it still feels like the first night." Wind against the glass, the lamp mechanism clicking into rotation.

    • 4s
    • 360p
    • 9:16

    Gemini Omni 1.1 Flash

    Adds first and last frames, 360p drafts, longer prompts.

    Everything Omni Video does, plus a first and last frame mode: give it an opening still and an optional closing one, and it animates between them. That mode stands alone, with no references, characters or source video.

    Best for

    • 360p drafts before the final render
    • Opening and closing on exact frames
    • Shot lists or scripts as the prompt

    Pick another model for

    • Mixing frame mode with references in one generation
    • Driving the clip with your own audio file

    Specs

    Inputs
    Text plus 7 reference slots
    Frame mode
    First frame, optional last frame
    Source video
    Uses 2 slots, 10 s window
    Length
    4, 6, 8 or 10 s
    Resolution
    360p, 720p, 1080p, 4K
    Audio
    With the clip, 30 voices
    Try Gemini Omni 1.1 Flash
    See prices

    Price

    OptionRateUnit
    360p, 4 s110credits
    360p, 6 s140credits
    360p, 8 s170credits
    360p, 10 s200credits
    360p, with a reference video260credits
    720p, 4 s120credits
    720p, 6 s150credits
    720p, 8 s180credits
    720p, 10 s210credits
    720p, with a reference video270credits
    1080p, 4 s130credits
    1080p, 6 s160credits
    1080p, 8 s190credits
    1080p, 10 s220credits
    1080p, with a reference video280credits
    4K, 4 s230credits
    4K, 6 s260credits
    4K, 8 s290credits
    4K, 10 s320credits
    4K, with a reference video380credits
    Current rates in credits.

    Gemini Omni 1.2 Flash

    Any length from 3 to 15 seconds, and edits of whole clips.

    The newest Omni. Pick any whole-second length from 3 to 15 and render from text with up to six reference images, from a first frame, or between a first and a last frame (up to 10 seconds there).

    Read more

    Edits take the whole clip, up to 15 seconds, with no window to pick, and the result runs as long as the clip. It has no saved characters, voices or audio references: use 1.1 Flash for those.

    Best for

    • Clips longer than 10 seconds
    • Editing a whole clip of up to 15 seconds
    • Exact lengths such as 7 or 12 seconds

    Pick another model for

    • Saved characters or a chosen voice (use Omni 1.1 Flash)
    • Driving the clip with your own audio file

    Specs

    Inputs
    Text plus up to 6 images
    Frame mode
    First frame, optional last frame
    Source video
    Whole clip, up to 15 s
    Length
    3 to 15 s, any whole second
    Resolution
    360p, 720p, 1080p, 4K
    Aspect ratio
    16:9, 9:16 or auto
    Try Gemini Omni 1.2 Flash
    See prices

    Price

    OptionRateUnit
    360p7credits / sec
    720p15credits / sec
    1080p17credits / sec
    4K35credits / sec
    Current rates in credits.

    Omni Video, 1.1 Flash and 1.2 Flash

    ModelResolutionLengthFirst and last frameVoices and charactersPrompt limit
    Gemini Omni Video720p, 1080p, 4K4, 6, 8 or 10 sNoYes5,000 characters
    Gemini Omni 1.1 Flash360p, 720p, 1080p, 4K4, 6, 8 or 10 sYesYes20,000 characters
    Gemini Omni 1.2 Flash360p, 720p, 1080p, 4K3 to 15 sYesNo20,000 characters

    Which Omni model should I use?

    How the family fits together

    Omni is built around references: seven slots per generation, where an image or saved character takes one and a source video takes two. On Omni Video and 1.1 Flash, speech, ambience and music come out of the same render, voiced by one of 30 built-in voices.

    Read more

    Omni 1.2 Flash is the newest version. It renders any length from 3 to 15 seconds and edits whole clips up to 15 seconds, but has no saved characters, voices or audio references. Omni Video and 1.1 Flash stay available for those.

    Working with Gemini Omni

    • Count slots: 7 in total, a source video uses 2, so 5 remain for images or characters.
    • Trim the source first. Omni Video and 1.1 Flash use a window of up to 10 seconds inside the first 30; 1.2 Flash uses the whole clip, up to 15 seconds.
    • Put spoken lines in quotes and preview voices in the picker before you render.

    Pick a plan

    One credit balance covers images, video and audio. Pick the size that fits how much you make.

    Most popular

    Studio Pro

    Studio value with extra headroom.

    49 EURmonth
    6,400credits / month
    Team seats

    2 seats included

    What you'll generate

    • Images~1,600
    • Songs~457
    • Videos~640
    • Separations~1,066
    • Caption Minutes~213
    • All modelsIncluded
    Select plan

    Starter

    Low tier generations for regular use.

    10 EURmonth
    1,100credits / month

    What you'll generate

    • Images~275
    • Songs~78
    • Videos~110
    • Separations~183
    • Caption Minutes~36
    • All modelsIncluded
    Select plan

    Pro

    Access full experience.

    20 EURmonth
    2,600credits / month

    What you'll generate

    • Images~650
    • Songs~185
    • Videos~260
    • Separations~433
    • Caption Minutes~86
    • All modelsIncluded
    Select plan

    Powerhouse

    Most cost efficient.

    99 EURmonth
    13,000credits / month

    13,000 credits/mo

    Team seats
    3 seats

    Extra seats €19/seat/mo

    What you'll generate

    • Images~3,250
    • Songs~928
    • Videos~1,300
    • Separations~2,166
    • Caption Minutes~433
    • All modelsIncluded
    Select plan

    Enterprise

    For teams that outgrow standard plans.

    Custom

    Pricing tailored to your team

    What's included

    • Custom number of seats
    • Custom credit volume
    • Invoice billing
    • Priority support
    Contact sales
    Or pay-as-you-go

    Test any model with one-time credit packs

    Credits never expire and don't require a subscription — buy a pack, generate, see if Kubeez fits.

    Quick refill

    Quick refill for short bursts of generation.

    Credits

    500

    You pay

    €6

    Standard pack

    Mid-size pack at the standard per-credit rate.

    Credits

    1,500

    You pay

    €18

    −5%

    Volume pack

    Larger pack with a volume discount built in.

    Credits

    5,000

    You pay

    €60€57

    −10%

    Production pack

    Best per-credit price for sustained production.

    Credits

    15,000

    You pay

    €180€162

    Frequently asked questions

    • Create one from a single image and a short description, optionally with a voice. It stays in your library, works in Omni Video and 1.1 Flash and uses one reference slot. 1.2 Flash does not take saved characters.

    • No. On Omni Video and 1.1 Flash, pick the closest of the 30 built-in voices, each with a preview, and describe tone and pace in the prompt. 1.2 Flash takes no voice or audio input.

    • 4, 6, 8 or 10 seconds on Omni Video and 1.1 Flash. On 1.2 Flash, any whole second from 3 to 15, or up to 10 with both a first and a last frame. An edit follows the source: a window of up to 10 seconds on the older two, the whole clip up to 15 seconds on 1.2 Flash.

    • Per second of video, at the rate of the resolution you pick. An edit is billed on the length of your clip as Kubeez measures it. The live rates are in the price table on this page.

    • 16:9 and 9:16 on all three models. 1.2 Flash also offers auto.

    • No. On both Flash versions, frame mode is exclusive: a request that also includes reference images, characters or a source video is rejected before it runs.

    Guides and comparisons

    Tests, comparisons and how-tos for Gemini Omni from the Kubeez blog.

    All blog posts

    Open Gemini Omni in the studio

    Pick the model that fits your job, write your prompt and run it.

    Open the studioAll model families