Create a video generation task using the Sora 2 model. Supports text-to-video and image-to-video (via input_reference). The workflow is: create task -> query status -> download video.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Video generation model ID.
sora-2 "sora-2"
Natural language description of the video. Include shot type, subject, action, setting, lighting, and desired camera movement for best results. Keep it single-purpose for optimal adherence.
"A cat walking through a sunflower field at golden sunset"
Video duration in seconds.
4, 8, 12 "12"
Output resolution in width x height format.
720x1280, 1280x720, 1024x1792, 1792x1024 "1280x720"
Optional reference image used as the first frame. Accepted MIME types: image/jpeg, image/png, image/webp.
ID of a previously completed video (e.g. video_...) to reuse its structure, motion, and framing.
"video_69b131ea03548190925a6a06febf993b"