Extract the sound from a video
Take the sound out of a video as a small audio file, for example to transcribe it
Saves the video's sound as a mono 16 kHz MP3 in your files (about 0.5 MB a minute), small enough for the speech-to-text tool.
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
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 take the sound out of a video as a small audio file, for example to transcribe it”
What your AI calls: run_tool {"tool_id":"tool:extract-sound"}