Rendered at 04:44:52 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
markmatsushima 3 hours ago [-]
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?
loveparade 23 hours ago [-]
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.
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...