Gemini Omni Flash - Ekly API

Google’s conversational video model (preview): text/image-to-video with native audio, plus natural-language refinement of a previous generation. 720p, ~10s clips, model-chosen duration.


Model id	`gemini-omni-flash-preview`
Media	video
Submit to	`POST /v1/videos`
Price	55.748 credits per_generation before discounts
Typical time	about 75.0 s

Request

Required: prompt
Optional: aspect_ratio, first_frame, reference_images, source_video

{
  "model": "gemini-omni-flash-preview",
  "prompt": "Medium close-up, locked-off tripod, no camera movement. A middle-aged uncle in a cream kurta faces a cinema camera with dual monitors in a warm banquet hall. He says: Pehle mera asheerwad wala shot lo. Ambient noise: soft wedding hall murmur. No music. No subtitles. No captions. No on-screen text.",
  "aspect_ratio": "16:9"
}

Field	Allowed	Default
`aspect_ratio`	`16:9`, `9:16`	`"16:9"`
`first_frame`	asset id (up to 1)
`reference_images`	asset ids (up to 3)
`source_video`	asset id (up to 1)

Reference inputs take asset ids from POST /v1/uploads or an earlier output’s asset_id. Prices and allowed values come from the live catalog; GET /v1/models/gemini-omni-flash-preview is always current.