OpenAI Sora 2 (reverse) Video Generation
Video
OpenAI Sora 2 (reverse) Video Generation
POST
OpenAI Sora 2 (reverse) Video Generation
Sora 2 (reverse) is a state-of-the-art video + audio generator. It improves upon the original Sora with more precise physics, clearer realism, synchronized audio, stronger controllability, and a broader range of styles.
Request Headers
Enum:
application/jsonBearer authentication format: Bearer {{API Key}}.
Request Body
Positive text prompt for video generation.
Input image supports URL format only. Supported image formats include .jpg, .jpeg, .png.
Video duration (seconds)Enum:
10,15Width x Height, specific values are ignored. Width > Height produces landscape, Width < Height produces portrait.Enum:
1280x720- Standard definition landscape (actual output resolution is approximately 480P, listed as 480P in pricing)720x1280- Standard definition portrait (actual output resolution is approximately 480P, listed as 480P in pricing)
Whether to include a watermark. Defaults to no watermark if not provided.
Video URL for creating a character. Note: the video must not contain real people, otherwise it will fail.
Time range in seconds when the character appears in the video, format: {start},{end}. Note: end-start range must be 1-3 seconds.Example:
1,3Response
The task_id of the async task. Use the task_id to call the Get Async Task Result API to retrieve the generated result.