Gemini Omni 1.2 Flash

For scenes with automatically generated sound: create from text or images, edit an existing video up to 15 seconds, or extend one by 3–10 seconds. Creation supports 3–15 seconds; first-and-last-frame generation is limited to 10 seconds. Version 1.1 remains separate.

Cost

from 12 tokens

VideoProvider: Google

Try Gemini Omni 1.2 Flash in Givon AI

Open a working project for regular creation, or use Playground to inspect the model parameters.

Use through API

Request fields, constraints, and ready-to-use examples for developers. The user workflow starts above.

Run generation
IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"gemini-omni-1.2-flash","input":{"prompt":"cinematic drone shot over a city at night","mode":"create","aspectRatio":"9:16","resolution":"360p","duration":3,"referenceAssetUris":["asset://asset_..."]}}'

Input fields

* required
modemode
Type
string
Default
create
Allowed
create, edit, extend
prompt*prompt

Generation prompt describing the scene, action and direction.

Type
string
Default
—
Allowed
up to 20000 chars
aspectRatioaspectRatio
Type
string
Default
9:16
Allowed
16:9, 9:16
resolutionresolution
Type
string
Default
360p
Allowed
360p, 720p, 1080p, 4k
durationduration
Type
number
Default
3
Allowed
3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
Start imagestartImage

Asset input for the startImage slot.

Type
string
Default
—
Allowed
image · asset, https, data
End imageendImage

Asset input for the endImage slot.

Type
string
Default
—
Allowed
image · asset, https, data
Reference imagesreferenceAssetUris

Optional reference assets as asset:// URIs, HTTPS URLs, or data URIs. The item limit applies to physical references after repeated owned asset identities and identities already bound to video slots are excluded. URL entries remain distinct; every supplied item is validated.

Type
array
Default
—
Allowed
image · up to 7 · asset, https, data

Cost

from 12 tokens
360p- 3sdefault12 tk
360p- 4s16 tk
360p- 5s20 tk
360p- 6s24 tk
360p- 7s28 tk
360p- 8s32 tk
360p- 9s36 tk
360p- 10s40 tk
360p- 11s44 tk
360p- 12s48 tk
360p- 13s52 tk
360p- 14s56 tk
360p- 15s60 tk
720p- 3s30 tk
720p- 4s40 tk
720p- 5s50 tk
720p- 6s60 tk
720p- 7s70 tk
720p- 8s80 tk
720p- 9s90 tk
720p- 10s100 tk
720p- 11s110 tk
720p- 12s120 tk
720p- 13s130 tk
720p- 14s140 tk
720p- 15s150 tk
1080p- 3s45 tk
1080p- 4s60 tk
1080p- 5s75 tk
1080p- 6s90 tk
1080p- 7s105 tk
1080p- 8s120 tk
1080p- 9s135 tk
1080p- 10s150 tk
1080p- 11s165 tk
1080p- 12s180 tk
1080p- 13s195 tk
1080p- 14s210 tk
1080p- 15s225 tk
360P4 tk/s
720P10 tk/s
1080P15 tk/s
4k- 3s90 tk
4K30 tk/s
4k- 4s120 tk
4k- 5s150 tk
4k- 6s180 tk
4k- 7s210 tk
4k- 8s240 tk
4k- 9s270 tk
4k- 10s300 tk
4k- 11s330 tk
4k- 12s360 tk
4k- 13s390 tk
4k- 14s420 tk
4k- 15s450 tk
360P4 tk/s
720P10 tk/s

The variant is selected automatically from request fields, so you do not need to send it.

Capabilities

Modestext_to_videoimage_to_videofirst_last_frame_to_videovideo_editvideo_extendtext_image_to_video
Asset slotsstartImage:imageendImage:imagereferenceAssetUris:image[]<=7
Get API key

Where to use this model