{"skill":{"slug":"web-video-transcribe-docx","displayName":"Web Video Transcribe DOCX","summary":"Offline-first workflow for turning Chinese web page video or audio into text and Word deliverables. Use when Codex needs to (1) extract playable media stream...","tags":{"latest":"1.0.2"},"stats":{"comments":0,"downloads":68,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1776439518058,"updatedAt":1776441706687},"latestVersion":{"version":"1.0.2","createdAt":1776439518058,"changelog":"Initial release of web-video-transcribe-docx.\n\n- Provides an offline-first workflow for converting Chinese web page video/audio into text and Word documents.\n- Supports extraction of media streams (video/audio) from web pages, including MP4, M3U8, MPD, and split audio streams.\n- Includes pipelines and scripts for media extraction, download (with custom headers), offline transcription using SenseVoice ASR, and rendering to TXT/DOCX.\n- Special handling for Toutiao pages alongside generic web sources.\n- Raw and refined transcripts are managed separately for accuracy and auditability.\n- Stays within ethical and legal boundaries (no DRM bypass, no credential handling, no unauthorized downloads).","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"c-narcissus","userId":"s177jw27anm32qt3dm1c7dq0jh851mjz","displayName":"c-narcissus","image":"https://avatars.githubusercontent.com/u/168325551?v=4"},"moderation":null}