> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ninjachat.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Video generation
> Veo, Gemini Omni Flash, Kling, and Seedance behind one endpoint. Submit, poll, get an MP4.
VeoGemini OmniKlingSeedanceRunway
Video is **async**: submit a job, then poll its status — or register a signed webhook in [Developers → Webhooks](https://www.ninjachat.ai/developers/webhooks) and skip the loop. Either way you get an MP4 URL in one to a few minutes.
```mermaid theme={null}
flowchart LR
A["POST /api/v1/videos"] --> B["video id"]
B --> C{"GET /videos/{id} every 5s — free"}
C -->|processing| C
C -->|completed| D["video_url (MP4)"]
C -->|failed| E["Auto-refund"]
```
## Create a video
```typescript TypeScript SDK theme={null}
import { NinjaChat } from "@ninjachat/sdk";
const client = new NinjaChat({ apiKey: process.env.NINJACHAT_API_KEY! });
const job = await client.videos.generate({
model: "veo-3.1-fast",
prompt: "A timelapse of a flower blooming, macro lens, soft lighting",
duration: 6,
aspect_ratio: "16:9",
});
const video = await client.videos.waitFor(job.id);
console.log(video.video_url);
```
```python Python SDK theme={null}
import os
from ninjachat import NinjaChat
client = NinjaChat(api_key=os.environ["NINJACHAT_API_KEY"])
job = client.videos.generate(
model="veo-3.1-fast",
prompt="A timelapse of a flower blooming, macro lens, soft lighting",
duration=6,
aspect_ratio="16:9",
)
video = client.videos.wait_for(job["id"])
print(video["video_url"])
```
## Parameters
| Parameter | Default | Description |
| ------------------ | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `prompt` | required | Camera movement + subject action + style + lighting. Max 4,000 chars. |
| `model` | `veo-3.1-fast` | Choose from the [model catalog](/models-overview#video-models). |
| `duration` | `8` | Integer seconds. Most models accept 4–15; `gemini-omni-flash` renders 3–10 and bills a 3-second clip as three seconds. Supported durations depend on the model. |
| `aspect_ratio` | `16:9` | `16:9` or `9:16`; `1:1` is also supported by Seedance 2 variants and Grok Imagine Video. |
| `image_url` | — | Public HTTPS image URL to animate. |
| `end_image_url` | — | Public HTTPS still to end on, for models that support first-and-last-frame generation. |
| `reference_images` | — | Up to 4 public HTTPS image URLs to guide subject/style (Seedance 2 and 2.5). |
| `reference_video` | — | Public HTTPS video URL to guide motion/POV framing (Seedance 2 and 2.5). On `seedance-2.5` this shape has its own, higher flat price — see [Pricing](/pricing). |
| `reference_audio` | — | Public HTTPS audio URL to use as background music (Seedance 2 and 2.5). |
| `generate_audio` | `false` | Generate an audio track for the video (Seedance 2, Seedance 2.5 and Kling 2.6). `gemini-omni-flash` always renders sound. |
| `negative_prompt` | — | Describe what to avoid (`kling-video` only). |
| `watermark` | `false` | Overlay a watermark on the output (Seedance 2 and 2.5). |
Polling `GET /videos/{id}` is free. Status moves `queued` → `processing` (with `progress`) → `completed` (with `video_url`) or `failed` (auto-refunded).
## Edit or extend a finished clip
Clips made with `gemini-omni-flash` stay revisable. Send the finished clip's `id` back as `video_id` and describe the change in `prompt`; the clip's length and everything you do not mention stay the same. Add `task: "extend"` with a `duration` of 3–10 to append new footage instead — you get the whole lengthened clip back, up to 40 seconds. `model` can be left out; a revision always runs on the model that made the clip.
```bash Edit theme={null}
curl https://www.ninjachat.ai/api/v1/videos \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"video_id":"vid_…","prompt":"Make the paper boat bright blue"}'
```
```bash Extend theme={null}
curl https://www.ninjachat.ai/api/v1/videos \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"video_id":"vid_…","task":"extend","duration":4,"prompt":"The boat drifts under a footbridge"}'
```
Revisions have their own flat price on the [rate sheet](/pricing): the source clip is carried as context on top of the seconds rendered. Poll the new job exactly like a fresh generation.
## Which model?
[Explore all video models and pricing →](/models-overview#video-models)
## Prompting for motion
| Weak | Strong |
| ----------- | -------------------------------------------------------------------------------------------------------------------- |
| `mountains` | `Drone shot slowly ascending over a misty mountain valley at golden hour, camera reveals a river below, cinematic` |
| `ocean` | `Underwater camera glides through a coral reef, bioluminescent creatures pulse with light, slow motion, documentary` |
The formula: **camera movement + subject action + style + lighting**.
Agents can run this whole flow conversationally — "animate the second one" — via the [MCP server](/mcp/tools).
Veo
Kling
Seedance
Runway