Sora 2 · Video Generation
Sora 2 · Introduction
OpenAI Sora 2 video model: text-to-video and image-to-video. Returns a taskId; poll for the result.
How to call
- Submit:
POST /api/cqt/generator/sora2, returns a taskId. - Query:
GET /api/cqt/info/sora2?id=taskId, poll until status = succeeded.
Capability map
POSTText to Video
Generate a video from a text description.
POSTImage to Video
Turn a still image into a moving video.
Common Errors
| Code | msg | Meaning | How to fix |
|---|---|---|---|
| 451 | video_unsafe | The generated video was flagged as unsafe | Modify the prompt or change the seed and retry |
| 451 | prompt_unsafe | Prompt rejected by content safety review | Edit the prompt to remove disallowed content and retry |
| 451 | image_unsafe | Input image flagged as unsafe | Replace the input image and retry |
| 400 | Invalid model / invalid_request | Invalid parameter (model must be sora-2) or unsupported value | Check model / aspectRatio / duration against the parameter table |
| 500 | timeout | Request timed out | Retry later; contact support if it persists |
Errors are returned as upstream bizCode, e.g. upstream bizCode=451, msg=prompt_unsafe.
Tip: after saving your API Key via Authorize, every capability page supports "Try it".