"Common Lisp" matching MCP servers:

Enables MCP-aware agents to fetch direct captions or download audio and transcribe with local Whisper from common video platforms like YouTube, Vimeo, and Twitch.

Enables agents to inspect local audio files' metadata, convert between common formats, trim segments, and normalize loudness through ffmpeg/ffprobe, plus transcribe audio via a user-configured local transcription command. All processing runs on local binaries, returning real tool output or errors rather than fabricated results.