Video Transcription Use When - The input is a video file and the goal is speech extraction, timed transcript, caption generation, multilingual transcript, or edit-prep timestamps. - Use instead when the user needs semantic visual analysis. If a timed transcript already exists and only subtitle output is requested, skip transcription and read the local subtitle conversion reference. Do Not Use When - The task needs new creative generation or visual analysis rather than speech or subtitles. - Required inputs are missing and guessing would change the result. Execution Boundary - Hosted video tra…