Face Value – A YouTube de-clickbaiter with transcript context

A developer has launched Face Value, a browser extension that rewrites YouTube video titles based on transcript content, replaces thumbnails with real video frames, and hides Shorts by default. The tool aims to combat clickbait and restore user control over attention, funded entirely by donations.

browser extension Take YouTube at face value. Every title on YouTube is written to grab your attention, and every thumbnail is engineered for clicks. Face Value rewrites titles from the video’s actual transcript , replaces thumbnails with a real frame from the video, and hides all Shorts by default. You decide what deserves your attention. what they publish what you see SpaceX Ship 40 Prepares for Flight 13 Static Fire What about it ? Artemis 3 HLS Starship Based on Version 3 What about it ? David Dobrik Stays at French Villa, Meets Multiple Women David Dobrik Rick Astley - Never Gonna Give You Up 4K Remaster Rick Astley Hot Dog Package Quantity Mismatch Explained BlackLabelExpat Why Income and Spending Matter More Than Investment Choices The Iced Coffee Hour This is about our attention, not just bad-faith thumbnails. The classic clickbait shock face, the red arrows, capital letters, and now AI on top of all that. At this point, even honest creators present their videos like this. I built Face Value when I hit my own limit: I couldn’t even browse podcasts anymore without having to do a deep dive on the video and the creator just to see if it was worth my time. Platforms have been encouraging this deceptive shock face style for years, and solutions like DeArrow don’t cover enough content to be worthwhile. Face Value brings back my ability to accurately judge which videos I'd like to watch. It also makes the homepage a bit easier to look at in a way - you don't notice how much the chaos makes it ugly until you've seen the cleaned version. I hope you feel similarly if you use Face Value, and please feel more than welcome to reach out about improvements or bugs. Clean titles Face Value's edge is in the way titles are formed - reading the actual video transcript gives the AI a very accurate picture of the content, rather than working with only the title. Clean thumbnails A thumbnail caching process preserves a crisp looking homepage while fully addressing the fundamental issue. Hide Shorts One toggle removes Shorts shelves, reels, and the sidebar button everywhere. Nobody asked for YouTube to become Instagram Reels or TikTok. Channel exceptions Trust a creator? Pause Face Value on their channel and see them exactly as they publish. How it works We read the transcript When a video first appears in anyone’s feed, our server fetches its public transcript. The title is rewritten A language model rewrites the title to plainly state the contents of the video. A real frame replaces the thumbnail We pull a sharp, representative frame from the video stream itself and display that instead of the thumbnail. Results are cached and shared. The first person to see a video pays a few seconds of processing, everyone after gets it instantly. The extension never blocks your browsing; cards fill in as answers arrive. Live streams and search results are intentionally left untouched. See the source here https://github.com/Bivtor/yt-clickbait-remover Free, and funded by donations. The transcript API, thumbnail proxy data, LLM requests, as well as general hosting cost me every month. To me, this is a small price to pay for winning back the freedom to choose, but Face Value does not make money and donations are much appreciated. Consider donating https://github.com/sponsors/Bivtor