Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- For single videos I use the bookmarklet from here https://ytbulktranscript.app/bookmarkletby david51232
- It looks to eventually charge, and my one attempt didn't seem to be able to choose the language.
- One issue with downloadable transcripts is that they can completely bypass the publisher’s monetization.
How about an AI agent could consume the video through the normal playback experience, including ads, and produce a transcript afterward?
- by toomuchtodo
- yt-dlp --skip-download --write-sub --write-auto-sub --sub-lang en --sub-format json2 "[1]"
[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...
- I built my own pipeline for this because in my experience the YouTube auto transcripts are quite bad.
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.
by loveparade - Would you mind sharing your code?by toomuchtodo