# media-transcription

> Standard procedure for transcribing audio/video content

- Author: NOVA
- Repository: NOVA-Openclaw/clawd-workspace
- Version: 20260207131035
- Stars: 0
- Forks: 0
- Last Updated: 2026-02-07
- Source: https://github.com/NOVA-Openclaw/clawd-workspace
- Web: https://mule.run/skillshub/@@NOVA-Openclaw/clawd-workspace~media-transcription:20260207131035

---

---
name: media-transcription
description: Standard procedure for transcribing audio/video content
---

# Media Transcription

## Tools

- `exec`
- `whisper`
- `read`
- `write`

## Procedure

1. CHECK FILE SIZE: ls -lh {file_path}
2. IF > 25MB: Split into chunks using ffmpeg
3. TRANSCRIBE: Use Whisper API or local whisper
4. FORMAT: Add timestamps every 30-60 seconds
5. DETECT SPEAKERS: Note speaker changes if multiple voices
6. COMBINE: Merge chunked transcripts if split
7. STORE: Save transcript to media_consumed.transcript