Transcribe an audio or video file
Transcribe an audio or video file in this person's Trillion files into timed words, for captions, search and picking a stretch by what is said
Hears the file by its identity inside the account with Whisper and keeps its transcript beside the file: the text, and each passage with its start and end and every word with its own start and end in seconds, which captions, search and the editor read. A video is heard through its sound alone (taken out once by tool:extract-sound), so videos up to about 50 minutes fit. Repeating the same identity returns the saved transcript.
What it asks for
- identity (Needed, words):
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 transcribe an audio or video file in this person's Trillion files into timed words, for captions, search and picking a stretch by what is said”
What your AI calls: run_tool {"tool_id":"tool:transcribe-file"}