Who is in this recording or picture
Name who speaks in a recording (each stretch of words with its speaker) or whose faces are in a picture or video, against the people this person's Mac knows
Runs on the person's Mac. Give path (on the Mac) or file (in their Trillion). A recording answers speakers: [{ start, end, who, me, text }], and for a Trillion file they are also kept as the file's speakers result; a picture (or faces true for a video) answers faces: [{ at, box, who, score }]. Anyone not enrolled is Someone (voice-N).
What it asks for
- path (Optional, words): A recording, video or picture on the Mac
- file (Optional, words): A recording, video or picture in the person's Trillion, by name or identity
- faces (Optional, yes or no): true to look for faces in a video instead of voices
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 name who speaks in a recording (each stretch of words with its speaker) or whose faces are in a picture or video, against the people this person's Mac knows”
What your AI calls: run_tool {"tool_id":"tool:who-is-in-this"}