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 media-analysis 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.