Add captions to a video from its transcript
Burn captions into a video from its transcript, in a caption style: plain subtitles, large captions, or words that light up as they are said
Takes timed words (the speech-to-text tool's output, or a list of {text, start, end}) and burns captions into the whole video in the style you name (see style), words gathered into short lines the way that style reads best. Saves the new video in your files.
What it asks for
- video (Needed, file): The video's identity in your files (1f: then 64 hex), as find_file or list_files returns it
- transcript (Needed, value): Timed words: {words:[{text,start,end}]}, {segments:[{words}]} or a list of words
- transcript_from (Optional, number): Where in the video the transcript's zero is (default 0)
- style (Optional, value): The caption style (default subtitles): subtitles (Subtitles); emphasis (Large captions); spoken-words (Highlight spoken words); serif-spoken-words (Serif spoken words); white-words-light-up (White words light up). Or an object with id set to one of them and any of font, size, bold, italic, outline, shadow, colours, position, reveal, grouping changed.
Use it from your AI
Connect the AI you already use to Trillion once. Then ask in your own words; your AI finds this tool by what it does and runs it.
Say to your AI: “Use Trillion to burn captions into a video from its transcript, in a caption style: plain subtitles, large captions, or words that light up as they are said”
What your AI calls: run_tool {"tool_id":"tool:add-captions"}