About Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash is Google's omni-modal video model that handles text-to-video, first/last frame keyframing, reference-guided generation from images and short video clips, and video editing and extension in a single model. Every clip ships with synchronized native audio (dialogue, sound effects, and music directed from the prompt), and camera work is described in natural language.
Each generation is a 3 to 10 second clip at 24 fps in 16:9 or 9:16, rendered at 360p (a fast, low-cost draft tier), 720p (the default), or upscaled to 1080p or 4K. Pin a first frame, or a first and last frame, to control a shot's start and end; add up to 3 reference images and up to 3 reference videos of at most 3 seconds each to carry a character, object, or style into the scene (audio in reference videos is ignored). Supply a video to edit it by instruction while preserving everything the prompt does not mention, or to extend it: extensions append 3 to 10 seconds at a time, use up to 10 seconds of prior footage as context, and can stack to a cumulative 40 seconds.
Ready to build with Gemini Omni 1.1 Flash?
Try Gemini Omni 1.1 Flash in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "gemini-omni-1-1-flash",
"prompt": "A cinematic wide shot of a lighthouse on a rocky cliff at dusk, waves crashing below, the beam sweeping across the dark sea. Distant gulls, wind, and the low rumble of surf.",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 8
}'