Subtitles Skill

Video in → the same video with burned-in captions out. Everything about caption timing, wording, sizing and look lives here, so workflows call this skill instead of re-implementing captions.

Work Mode routes

Choose the first applicable route:

1. Faceless-channel assembly: when the caller still has completed per-block video and narration result URLs, pass --subs clean|paper|bold to ${HF_WORKFLOWS}/faceless-channel-video/scripts/finish_video.sh inside sandbox_exec. It transcribes and burns while finishing the sandbox cut.
2. Finished sandbox video: use the preinstalled Whisper and burner pipeline below.
3. Finished remote video: download it inside sandbox_exec, then use route 2.

Do not call legacy AskUserQuestion. If the look is missing, apply the defaults in “Picking the look”; ask in normal chat only when the caller explicitly wants a choice.