inspect media
Look at media, or ask a model about it: a library item, or a picture or video at a web address (urls) read without keeping it. An image returns the picture with its size in pixels. A video returns frames: overview (default: one storyboard grid, frames spread evenly), window (a grid of one span), frame (one moment), strip (one span as frames with the waveform and words under them), or shot_log (every segment in order with its span, frame, spoken lines and a written line each; cloud only, one video). A file with a transcript also returns spoken: the sentences in the span, the opening lines for a whole file (transcribe_media reads the rest). cuts: true adds every shot change and shot length once the video is indexed. Audio returns spoken alone. prompt, on one video or audio file, has a model watch or listen and answer the question, with the moments the answer rests on as seconds; a long read returns a job; cloud only, not for images. Up to 12 refs or urls a call, in order, each item listing its pictures by position. Results are cached. inspect_timeline reads the composite. Free to look; cuts on an unindexed video, shot_log and prompt use cloud processing.
Authorizations
Headers
Body
A question for a model to answer about one video or audio file: motion, sound, timing, how type enters, when a thing happens. Answered in the call, moments as seconds, or past about 20 seconds as a job_id for get_jobs; no answer, no charge. One ref or url.
1 - 4000
