Video Extraction Plus

A video transcription server that extracts text from video platforms and audio files using multiple ASR (Automatic Speech Recognition) services including OpenAI Whisper, Bilibili's Bcut ASR, and ByteDance's JianYing ASR. Built by Seazhang, it supports downloading content from YouTube, Bilibili, TikTok, and other platforms via yt-dlp, then processes the audio through configurable transcription backends with features like word-level timestamps, caching, and rate limiting. The implementation provides a unified interface for different ASR providers while handling platform-specific authentication and upload workflows, making it useful for content analysis, subtitle generation, and automated transcription of educational or business video content.