Gemini Omni gemini-omni

video model · provider: google · typical generation time ~220s

Capabilities

Credits

Example

curl -X POST "https://api.aiveed.io/v1/generate/video" \
  -H "X-API-Key: $AIVEED_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-omni",
  "prompt": "The presenter smiles and says: \"Welcome to our spring collection.\"",
  "character_asset_ids": [
    1234
  ],
  "voice_asset_ids": [
    5678
  ],
  "resolution": "1080p",
  "duration": "8",
  "aspect_ratio": "9:16"
}'

The response is a job — poll GET /v1/jobs/{id} or use webhooks/SSE; when status is completed, result_url is the hosted output.

Good to know

• Aspect ratios are limited to 16:9 and 9:16.
• Requires voice_asset_ids and a character — character_asset_ids or reference_image_urls. List your ids (starter characters and voices included) with GET /v1/assets.
• No image-to-video — image_url, first_frame_url, last_frame_url, and generate_audio return 422.
• Prompt cap: 20,000 characters.

← All models