About Veo 3.0
google/veo-3 is a video generation model designed for text- and image-conditioned video creation with native, synchronized audio.
It excels in generating short, realistic clips with coherent motion, prompt-aligned cinematography, and integrated audio (dialogue, ambient sound, and effects), making it useful for tasks like concept visualization, social content, and pre-visualization for storytellers and filmmakers.
Some other noteworthy use cases of google/veo-3 include creating marketing and educational videos from scripts or reference images, and producing character-driven scenes that maintain visual and audio consistency across shots.
Ready to build with Veo 3.0?
Try Veo 3.0 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": "google-veo-3",
"prompt": "A dog digging on the beach",
"generate_audio": true,
"aspect_ratio": "16:9",
"duration": 8,
"resolution": "1080p"
}'Request parameters
Every field Veo 3.0 accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text description of what you want to generate, or the instruction on how to edit the given image. |
input_image | stringuri | No | — | Image to use as reference. Must be jpeg, png, gif, or webp. |
generate_audio | boolean | No | true | Generate audio with the video. |
aspect_ratio | string | No | "16:9" | 9:1616:9 |
duration | integer | No | 8 | Range: 4 – 8 |
resolution | string | No | "1080p" | 1080p720p |