Skip to content

visualsandbox/visual-sandbox

v0.2.71SEE LICENSE IN LICENSE

Generate images, video, audio, 3D and vector with Visual Sandbox, with the skills that teach an agent to prompt every model well. Pay per generation.

vsb-subtitles

Add TikTok/CapCut-style word-by-word captions to any video with vsb video subtitles — transcribes via Visual Sandbox's audio/scribe (ElevenLabs Scribe, word-level timestamps), builds .ass subtitles in one of five caption styles (TikTok word-by-word, MrBeast, highlight, Hormozi, or a rounded box), and burns them in with local ffmpeg. Trigger when the user says "add subtitles", "add captions", "caption this video", "burn subs", asks for a caption style, or wants a transcript of a video with timestamps. Accepts a local file or a TikTok/Instagram/YouTube URL.

License
Proprietary. See LICENSE for the terms.
Read SKILL.md at the source

Pinned to revision 10f8142b8f82, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.