Fetches YouTube transcripts and metadata (title, channel, duration) for URLs, using subtitles or on-device Whisper STT when no subtitles are available, enabling chat-based YouTube video analysis.
Enables downloading videos from platforms like YouTube and converting them to text using OpenAI Whisper and ffmpeg. It supports multiple output formats including TXT, JSON, SRT, and VTT for transcriptions.
Enables high-performance, offline transcription of videos from 1000+ platforms and local files using whisper.cpp, with support for multiple model sizes, languages, and output formats over stdio or HTTP.
Enables intelligent transcription of YouTube videos with automatic optimization for any video length, using local OpenAI Whisper processing and speaker diarization.