App API - Video Generation

Video Generation

Generate short AI videos (3 to 10 seconds) with audio.

Plan availability: Video generation is Pro-only - blocked on the Free plan: a Free-plan owner calling this endpoint gets 403 FORBIDDEN with an upgrade message. Don't build a Free-tier app around it.

Text-to-video only - NOT image-to-video. This service takes a prompt and generates a fresh clip; it cannot animate a specific image the user uploaded (there is no image-input parameter). If the app is "upload a photo and bring it to life" / "animate this picture" / any image-conditioned motion, this is not the tool - the generated clip would be an unrelated scene, not the user's photo. Run an image-to-video model (LTX-Video, Stable Video Diffusion) as a GPU job instead: the photo is the conditioning frame and the job returns a clip of that exact image moving. See the jobs skill ("Image-to-video" shape).

Models

gemini-omni-1.1-flash (3-10s clips with sound, 360p to 4K, ~$0.10/sec at 720p)

From the CLI: gipity generate video

gipity generate video "A bird flying over a mountain lake at sunset, slow camera pan" \
  --aspect 16:9 --resolution 1080p -o src/assets/lake.mp4

Options:

• the prompt (required): describe scene, action, camera movement, dialogue
• --model: see models above (default: gemini-omni-1.1-flash). Omit it unless you need to pin one.
• --aspect: 16:9 (landscape), 9:16 (portrait). Default 16:9.
• --resolution: 360p, 720p, 1080p, 4k. Default 720p.
• --duration: clip length, any whole number of seconds from 3 to 10. Default: 8. Shorter clips cost proportionally less.
• -o: output path; write into src/ for a clip your app ships

Generation takes 20-120 seconds. Videos include AI-generated audio.

Pricing: billed per second of video produced (provider rate + 5%), so duration and resolution both matter. A default 8-second 720p clip costs roughly 860 credits; a 4-second clip costs half that. Per second, 360p costs about a third of the 720p rate, 1080p about 1.5x and 4k about 3x. Prefer short 720p clips (or 360p for drafts) unless the app really needs the extra resolution.

Veo models are retired. Google is shutting down the Veo 3.1 models on 2026-10-22, so Gipity no longer serves them. A request that names a veo-* model returns 400 naming the replacement. Drop the model field (or pass gemini-omni-1.1-flash), and note the 1:1 aspect ratio is gone.

App API Endpoint

POST /api/<PROJECT_GUID>/services/video

Request:

{
  "prompt": "Close-up of coffee being poured into a cup",
  "aspect_ratio": "9:16",
  "resolution": "720p",
  "duration_seconds": 5
}

All fields except prompt are optional: model, aspect_ratio, resolution, duration_seconds (3-10, default 8).

Response:

{
  "url": "https://media.gipity.ai/med_abc12345.mp4",
  "content_type": "video/mp4",
  "model": "gemini-omni-1.1-flash",
  "provider": "gemini",
  "size_bytes": 2048000,
  "credits_used": 525
}

CLI

Writes to ./generated.mp4 by default - pass -o <path> to land the clip in your source tree so it deploys.

gipity generate video "a cat playing piano" --duration 4 -o src/assets/video/cat.mp4
gipity generate video "vertical dance" --aspect 9:16 --resolution 1080p -o src/assets/video/dance.mp4

Tips

• Be specific: describe lighting, camera angle, movement, and mood
• Include dialogue in quotes to get matching speech
• 9:16 for social media / mobile content
• A 3-4 second 720p clip is good enough for previews and iterations