X Video Transcribe

Other

Transcribe and summarize X/Twitter videos using bird CLI + Gemini audio transcription.

Install

openclaw skills install ec-x-video-transcribe

X Video Transcribe

Transcribe X/Twitter video posts to text. Downloads the video, extracts audio, and uses Gemini for accurate transcription.

When to use

  • User shares an X/Twitter URL containing a video
  • User asks to "transcribe this tweet" or "what does this video say"
  • User wants a summary of an X video

Usage

# Basic transcript
~/agent-workspace/skills/x-video-transcribe/scripts/transcribe.sh "https://x.com/user/status/123"

# With summary
~/agent-workspace/skills/x-video-transcribe/scripts/transcribe.sh "https://x.com/user/status/123" --summary

# Save to file
~/agent-workspace/skills/x-video-transcribe/scripts/transcribe.sh "https://x.com/user/status/123" --summary --output /tmp/transcript.md

Pipeline

  1. bird CLI — Fetches tweet JSON, extracts video URL
  2. curl — Downloads the video MP4
  3. ffmpeg — Extracts audio as MP3 (much smaller than video)
  4. Gemini API — Uploads audio, transcribes with gemini-2.0-flash

Requirements

  • bird CLI with auth (cookies in ~/agent-workspace/secrets/bird.env)
  • ffmpeg
  • GEMINI_API_KEY environment variable

Environment

VariableDefaultDescription
GEMINI_API_KEY(required)Google Gemini API key
BIRD_ENV~/agent-workspace/secrets/bird.envPath to bird credentials
GEMINI_MODELgemini-2.0-flashGemini model for transcription