TED very often has a transcript on their page, but it involves some clicking and then some copy-pasting, and the text result is often broken mid-clause after about 10-15 characters.
I'm wondering if there's any useful userscripts, userstyles, or other methods that handle this. (I think TED often sues people who try to make transcripts easily available on a separate site. I may be mistaken, and TED, please don't sue me, it's just a general feeling.)
The same request would apply to YouTube and/or other popular video sites, but I run into this issue most often with TED.
My thanks in advance to anyone who can help me on this!
How about an AI agent could consume the video through the normal playback experience, including ads, and produce a transcript afterward?
I download the raw audio track with yt-dlp, give it to qwen asr for raw transcription, then DeepSeek flash for transcription cleanup, formatting, corrections with web search enabled, etc. I use openrouter to call the models. It's a few cents per video (mostly the asr model at ~12 cents per hour) and quality is great. You could probably use a local asr model if you want to save money, I just don't bother because it's so cheap already.
That only makes sense for videos that don't have official (not auto-generated) transcripts of course. If there are official transcripts that are good you can just get them directly with yt-dlp.
https://news.ycombinator.com/item?id=44381640
[TedTalk] Extracting URL: [1]
[TedTalk] luvvie_ajayi_jones_how_to_be_a_professional_troublemaker: Downloading webpage
ERROR: the JSON object must be str, bytes or bytearray, not NoneType
exit 1
[1] - full URL is: https://www.ted.com/talks/luvvie_ajayi_jones_how_to_be_a_pro...