bggg-tiktok-readvideo

Extract metadata, transcripts, keyframes, and contact sheets from TikTok videos.

559|88|Updated May 2, 2026
One-click install
npx skills add https://github.com/binggandata/bggg-skills --skill bggg-tiktok-readvideo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bggg-tiktok-readvideo
Source: https://github.com/binggandata/bggg-skills/tree/main/bggg-tiktok-readvideo
Command: npx skills add https://github.com/binggandata/bggg-skills --skill bggg-tiktok-readvideo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, ffprobe, whisper-cli, whisper-cpp, tesseract, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill transforms TikTok and UGC videos into a structured format, enabling Codex to analyze, transcribe, and edit them effectively.

Core Features & Use Cases

  • Video Analysis: Break down videos into metadata, transcripts, keyframes, contact sheets, and timelines.
  • Transcription: Convert audio content into text, optionally with subtitles and JSON output.
  • Use Case: You can use this Skill to analyze a TikTok video, extract a transcript, and create an edit plan for a TikTok post.

Quick Start

Analyze a TikTok video with bggg-tiktok-readvideo analyze_video /path/to/video.mp4 --slug product_qc_ugc.

Frequently Asked Questions about bggg-tiktok-readvideo

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract transcripts and keyframes from TikTok videos for UGC analysis?

To extract transcripts and keyframes from TikTok videos, this Skill processes the video to output structured metadata, text transcripts, and visual contact sheets. It leverages whisper.cpp for audio transcription and FFmpeg for video breakdown.

What is the best way to transcribe UGC video audio into text and JSON subtitles?

Transcribing UGC video audio into text is handled by the integrated whisper.cpp engine. It processes the audio track to generate standard text transcripts, with optional outputs available in subtitle and JSON formats for further analysis.

Do I need FFmpeg and tesseract installed to analyze TikTok video metadata?

Yes, you need FFmpeg, ffprobe, whisper-cli, whisper-cpp, and tesseract installed in your environment to analyze TikTok video metadata. These dependencies handle the video processing, audio transcription, and OCR required for the workflow.

Can I generate a structured edit plan from a TikTok video timeline?

Generating a structured edit plan from a TikTok video timeline is supported by transforming the video into structured metadata, transcripts, and keyframes. This structured output is designed specifically for Codex to analyze and create an edit plan.

Does tesseract OCR work on extracting text from TikTok video keyframes?

Tesseract OCR works on extracting text directly from TikTok video keyframes. The Skill uses FFmpeg to extract the keyframes and contact sheets, then applies tesseract to capture any visual text present in the UGC video frames.