The Audio Transcriber skill automates the conversion of raw audio files into professional, high-quality documentation. By leveraging powerful transcription engines like Faster-Whisper and OpenAI Whisper, it handles speech-to-text with high accuracy, identifies speakers, and extracts technical metadata. Beyond simple transcription, the skill utilizes LLMs to process the text into structured meeting minutes, highlighting key decisions, action items, and executive summaries, making it an essential tool for developers and project managers who need to turn recordings into searchable, actionable knowledge.
주요 기능
01Multi-format support including MP3, WAV, M4A, OGG, and FLAC via ffmpeg
02Professional Markdown output with embedded metadata and executive summaries
0340,309 GitHub stars
04Automated meeting minutes generation with action items and decisions
05Intelligent speaker identification and diarization for multi-person audio
06High-speed local transcription using Faster-Whisper or OpenAI Whisper
사용 사례
01Creating subtitles and structured content reports for video and audio assets
02Generating searchable transcripts and summaries for technical interviews and lectures
03Converting team meeting recordings into organized documentation and task lists