audio-transcriber

SKILL.md

Transcribe audio files to structured Markdown with intelligent meeting minutes and executive summaries.

Supports MP3, WAV, M4A, OGG, FLAC, WEBM formats with automatic format detection and conversion via ffmpeg

Auto-detects and uses Faster-Whisper (4-5x faster) or OpenAI Whisper with zero configuration; offers one-click dependency installation

Extracts rich metadata (speakers, timestamps, language, duration, file size) and generates structured meeting minutes with topics, decisions, and action items

Optionally integrates with Claude or GitHub Copilot CLI for intelligent summarization and custom prompt-based processing

Handles batch processing of multiple files and warns on large files (>25 MB) with estimated processing time

Purpose

This skill automates audio-to-text transcription with professional Markdown output, extracting rich technical metadata (speakers, timestamps, language, file size, duration) and generating structured meeting minutes and executive summaries. It uses Faster-Whisper or Whisper with zero configuration, working universally across projects without hardcoded paths or API keys.

Inspired by tools like Plaud, this skill transforms raw audio recordings into actionable documentation, making it ideal for meetings, interviews, lectures, and content analysis.

When to Use

Invoke this skill when:

User needs to transcribe audio/video files to text

User wants meeting minutes automatically generated from recordings

User requires speaker identification (diarization) in conversations

User needs subtitles/captions (SRT, VTT formats)

User wants executive summaries of long audio content

User asks variations of "transcribe this audio", "convert audio to text", "generate meeting notes from recording"

User has audio files in common formats (MP3, WAV, M4A, OGG, FLAC, WEBM)

Workflow