Speech Diarizer

Transcribes a local audio or video file into a speaker-labeled transcript using local WhisperX + pyannote diarization, and identifies recurring people by voice via an enrolled voiceprint store. Use when the user wants to know who said what - a transcript that separates speakers and names the ones it has met before (interviews, meetings, calls, podcasts).

rami-maalouf Updated 3 repo stars

File contents

rami-maalouf/ai-agents-config commit 43fc6246fb

Frequently asked questions

npx get-skill add rami-maalouf/speech-diarizer