Gemini Omni Flash
Google multimodal model that builds video from text, images, and video, and can edit an existing clip conversationally. Use it when you need to transform footage or mix inputs rather than generate a shot from scratch. Native audio, up to 4K.
Cost
from 20 tokens
curl -X POST https://api.givon.ai/api/v1/generations \
-H "Authorization: Bearer $GIVON_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"video","model":"gemini-omni-video","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"9:16","resolution":"720p","duration":4,"referenceAssetUris":["asset://asset_..."]}}'Input fields
* required| Field | Type | Default | Allowed |
|---|---|---|---|
prompt* promptScene / motion description. | string | — | up to 5000 chars |
aspectRatio aspectRatio | string | 9:16 | 9:16, 16:9 |
resolution resolution | string | 720p | 720p, 1080p, 4k |
duration duration | number | 4 | 4, 6, 8, 10 |
Start image startImageAsset input for the startImage slot. | string | — | image · asset, https, data |
Source video sourceVideoAsset input for the sourceVideo slot. | string | — | video · asset, https, data |
Reference images referenceAssetUrisOptional reference assets as asset:// URIs, HTTPS URLs, or data URIs. | array | — | image · up to 7 · asset, https, data |
promptScene / motion description.
- Type
- string
- Default
- —
- Allowed
- up to 5000 chars
aspectRatio- Type
- string
- Default
- 9:16
- Allowed
- 9:16, 16:9
resolution- Type
- string
- Default
- 720p
- Allowed
- 720p, 1080p, 4k
duration- Type
- number
- Default
- 4
- Allowed
- 4, 6, 8, 10
startImageAsset input for the startImage slot.
- Type
- string
- Default
- —
- Allowed
- image · asset, https, data
sourceVideoAsset input for the sourceVideo slot.
- Type
- string
- Default
- —
- Allowed
- video · asset, https, data
referenceAssetUrisOptional reference assets as asset:// URIs, HTTPS URLs, or data URIs.
- Type
- array
- Default
- —
- Allowed
- image · up to 7 · asset, https, data
Cost
from 20 tokensThe variant is selected automatically from request fields, so you do not need to send it.
Capabilities
text_to_videoimage_to_videovideo_to_videoreference_to_videostartImage:imagesourceVideo:videoreferenceAssetUris:image[]<=7Run Gemini Omni Flash
Get an API key and the same request shape will work across every model in the catalog.