Paste a YouTube link into ChatGPT and it reads the transcript, not the picture. crv runs locally: scene-change detection picks the frames that matter, dedup drops the repeats, Whisper transcribes the audio - then any LLM can read the folder. MIT, no ML downloads.
Open SourceDeveloper ToolsArtificial IntelligenceGitHub




Advertisement (Responsive)
💬 Comments
📋 Details
Launched
July 5, 2026
Upvotes
5
Comments
5
Source
Public data
Advertisement (Responsive)






This tool has 5 comments on Product Hunt.
View comments on Product Hunt →