feiskyer/video-skills

Extracts transcripts or subtitles from local video files by first checking for embedded subtitles (faster and more accurate) and falling back to API-based speech recognition if none are found.

Generates professional voiceover narration for videos by analyzing scenes, writing timed scripts, generating speech via Azure TTS or Gemini 3.1 Flash TTS, and merging audio with video while maintaining precise audio-visual sync.

Downloads videos from 1000+ websites including YouTube, Bilibili, Twitter/X, TikTok, and Vimeo using yt-dlp, with support for quality selection, audio extraction, and playlist downloads.