generate video
Generate a video from a prompt (text-to-video), a start image (image-to-video; end_ref adds an end frame on models that take one), a source video (video-to-video, edit_points for local changes), or several inputs (ingredients-to-video), on the account’s default model or a named one. Settings, duration, resolution and audio are validated against list_models and set the price; a source video at or over the model’s max_input_video_duration is refused before any charge: cut shorter clips first (cut_clips, render_clips) and generate from each. Returns a job; get_jobs returns the item when it is ready. Refunded if nothing is made. Credits. Prompting: skill-ai-filmmaking; a source video changed with its performance kept: skill-transform-video.
Authorizations
Headers
Body
Change specific spots and keep the rest, on models with supports_edit_points; the first source_ref is the media. Points are fractions from inspect_media with grid: true (frame mode for video). The prompt may be empty or describe the whole edit. On an image reference_refs follow the source and a marked copy (none on GPT Image 2.6). Aspect ratio and duration are kept.
1 - 8 elements
