Skip to main content
POST
/
v1
/
videos
sora-2 (image to video)
curl --request POST \
  --url https://api.example.com/v1/videos
Sora is OpenAI’s newest frontier in generative media – a state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images. Built on years of research into multimodal diffusion and trained on diverse visual data, Sora brings a deep understanding of 3D space, motion, and scene continuity to text-to-video generation. 
curl --location "https://gptproto.com/v1/videos" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --form 'model="sora-2"' \
  --form 'prompt="She turns around and smiles, then slowly walks out of the frame."' \
  --form 'input_reference=@"sample_720p.jpeg"' \
  --form 'size="720x1280"' \
  --form 'seconds="4"'
Response
{
    "id": "video_xxxx",
    "object": "video",
    "status": "queued",
    "model": "sora-2",
    "progress": 0,
    "seconds": "4",
    "size": "720x1280",
    "createdAt": 1761897415
}

{
  "error": {
    "message": "Invalid signature",
    "type": "401"
  }
}

​
Parameters

ParameterTypeRequiredDefaultDescription
modelstring✅ Yessora-2The video generation model to use.
promptstring✅ Yes-Text prompt that describes the video to generate.
input_referencefile✅ Yes-Image file that guides generation. Image size 720x1280 or 1280x720.
sizestring✅ Yes720x1280Output resolution formatted as width x height. Only supports 720x1280 or 1280x720.
secondsstring❌ No4Clip duration in seconds. 4, 8, 12. Defaults to 4 seconds.