audio-transcriber

To transcribe meeting audio to Markdown, the skill uses Faster-Whisper or Whisper to process formats like MP3 and WAV. It features automatic language detection and speaker diarization to generate structured Markdown reports.

Yes, you can generate meeting minutes and executive summaries from audio recordings. The skill extracts rich metadata and uses optional LLM tools to identify actions and decisions, outputting structured Markdown summaries suitable for sharing.

Yes, this transcription tool supports subtitle generation for video content by exporting SRT and VTT files. It processes audio from multiple formats and outputs structured Markdown reports alongside the subtitles.

Yes, you need Faster-Whisper or Whisper installed to transcribe audio files. These dependencies handle the core speech-to-text processing, while optional LLM tools provide intelligent processing for generating summaries and meeting minutes.

You can convert MP3, WAV, M4A, OGG, FLAC, and WEBM audio formats to structured notes. The skill processes these files to output polished Markdown reports with rich metadata, language detection, and optional summaries.