Skip to content

Image to Video

Animate static images into dynamic video sequences using the Siraya Model Router Image to Video API. This endpoint supports high-fidelity animation using leading video models.

POST https://llm.siraya.ai/v1/videos/generations
Authorization string Required
Your API Key (e.g., Bearer <API_KEY>).

Body

model string Required
The ID of the model (e.g., openai/sora-2-pro-image-to-video).
prompt string Required
Text description of the desired animation or context.
image_url string Required
The URL of the input image to use as the first frame. Supports public URLs or base64 data URIs.
seconds integer Default: 8
Video duration in seconds. Supported values depend on the model (e.g., Veo supports 4, 6, 8).
negative_prompt string
Describes what should not appear in the video. Automatically mapped to each vendor's corresponding field.
seed integer
Random seed for reproducibility. Same seed produces the same video.
extra_body object
Vendor-specific parameters. See below for details per provider.

|

curl https://llm.siraya.ai/v1/videos/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "sora-2",
    "prompt": "A cute baby sea otter swimming happily",
    "image_url": "https://example.png",
    "seconds": 8
  }'

import requests

url = "https://llm.siraya.ai/v1/videos/generations"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer <API_KEY>"
}
data = {
    "model": "openai/sora-2",
    "prompt": "A cute baby sea otter swimming happily",
    "image_url": "https://example.png",
    "seconds": 8
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Example Response

{
    "id": "video_abc123...",
    "object": "video",
    "status": "processing",
    "created_at": 1772093692,
    "seconds": 8,
    "model": "openai/sora-2-pro-image-to-video"
}

Info

The id is encrypted and contains provider and model information. Use this ID directly for subsequent queries and downloads.

Visit the Models Directory to find more supported image-to-video models.