Generate videos from text & images
You can obtain your API key from the TTAPI Dashboard.
Note: The synchronous response from the Sora video generation interface is not the final result of the task. The final result needs to be received via asynchronous notification using the hookUrl parameter, or by querying through the Sora fetch task result interface.
sora-2 normal mode sora-2-pro HD mode
sora-2, sora-2-pro "sora-2"
Video description
Reference image array, cannot pass real images with avatars or any existing US product logos. As per OpenAI regulations, non-compliant images will cause task failure. Currently only the first URL is used
[
"https://cdn.ttapi.io/demo/2025-03-30/5d17dd5207daeeac86bcecd2d6405a0.jpg"
]Video orientation. In sora-2 mode, portrait video resolution is approximately 720 * 1280, landscape is similar ratio. In sora-2-pro mode, portrait video resolution is approximately 1024 * 1792, landscape is similar ratio
portrait, landscape Video duration in seconds. 25s only works in sora-2-pro model
Supported values: 10, 15, 25
Default is 10s for sora-2 model, 15s for sora-2-pro model
Video quality setting. Only supported in sora-2-pro mode. For 25s duration, only standard quality is available
small, large Video URL for character creation
Important: The video must not contain any real people, otherwise the task will fail
Time range in seconds for character appearance in video, format: {start},{end}. Note: The range of end-start must be between 1 to 3 seconds
"1,3"
Privacy setting for generated video. true - Private access, false - Public access
Callback notification URL. When task completes or fails, this URL will be notified. Notification data structure is consistent with fetch structure. If not set, you need to request the fetch interface for query