Audio Transcriber & Meeting Summarizer
Transforms audio recordings into professional Markdown documentation with intelligent summaries and speaker identification.
This skill automates the conversion of raw audio files into structured, actionable documentation within your workspace. It intelligently detects and utilizes local transcription engines like Faster-Whisper or OpenAI Whisper to generate high-accuracy text without requiring manual configuration. Beyond simple speech-to-text, it extracts technical metadata, performs speaker diarization, and leverages LLM integration to generate executive summaries, categorized topics, and action items. Whether you are documenting meetings, interviews, or lectures, this skill provides a zero-config solution for turning sound into searchable, professional Markdown reports.