bilibili-audio-skill

Project overview

ai-video takes a request from first-frame generation and prompt writing through rendering, clip review, voiceover, assembly, and upscaling. It routes a shared request format to six supported video models and records lessons from each quality-control pass. You need API keys only for the services you call, plus ffmpeg and ffprobe locally.

Project overview

watch-video uses yt-dlp to fetch videos or accept local files, takes captions when available, falls back to local whisper.cpp transcription, and extracts adaptive video frames with ffmpeg. The agent receives metadata, a transcript, and a frame index so it can inspect only the visuals needed for an answer, with fast, balanced, and accurate modes controlling cost. No API key or third-party transcription service is required, but local tools and an optional Whisper model are needed; Claude Desktop is not supported.