The conversation

Building & toolsEditorial digest

Some people want the transcript, not the video

MollyRealized finds text easier to absorb than audio or video, but copying readable transcripts is cumbersome. They ask for tools that remove the extra clicks and broken line wrapping. A concrete accessibility and reading-workflow problem from an actual user.

Original excerpt

“I really absorb text a great deal better than listening to audio or watching video. I've heard others say the same and attribute to”

Read the full original
Original discussionAsk HN: Anyone set up ways to easily obtain and read transcripts from Ted, YT?
2

Community replies 0

No community replies yet. Add your perspective.

Replies from the source 2

Direct replies available in this import. Original-language excerpts.

LO

I have 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) and quality is great.

Full original
TO

https://github.com/yt-dlp/yt-dlp https://news.ycombinator.com/item?id=44381640

Full original
Continue on Hacker News

Respect different perspectives. Share concrete experiences.

Sign in to post, reply, repost, and quote.