audio-transcriber - Transcribe audio into structured Markdown
Transcribes audio or video, extracts metadata, and generates Markdown transcripts, meeting minutes, and summaries.
Tags
Updated: 2026-09-29Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Transcribe audio recordings
- Extract recording metadata
- Identify conversation speakers
- Generate meeting minutes
- Create executive summaries
- Generate SRT and VTT subtitles
- Convert unsupported audio formats
Inputs
- Audio or video file
- Audio or video URL
- Custom processing prompt
Outputs
- Markdown transcription report
- Markdown meeting minutes
- Executive summary
- SRT subtitles
- VTT subtitles
- Transcription metadata
- Converted WAV file
Requirements
- Python 3
- Faster-Whisper or Whisper
- ffmpeg for format conversion
- AI model for intelligent summaries