Author of the blog post here. I had this idea to start a site for crowdsourced podcast transcripts (or indeed any audio content) but never did it. I’d still love to see such a site because I agree that there is so much valuable content.

But transcription is just a huge amount of work and I’m not sure how well you could automate it with the help of software.

Transcription is already down to $1/minute. If $60 for an hour-long podcast isn't worth it to the authors, I'm not sure there's much value there.

https://castingwords.com/

Google has some pretty good software for this, thought it might be internal. When they have their "Talks at Google" events, there's a screen off to the side that provides real-time translated subtitles.

There's at least one talk where the speaker addresses this system, and tries to get it to transcribe funny stuff. Can't remember which one exactly, but it might be this one with Randall Munroe (xkcd).

https://www.youtube.com/watch?v=zJOS0sV2a24&list=UUbmNph6atA...

That idea crossed my mind even seeing how many companies failed even during boom times.

Service could be powered by some speech recognition software (maybe more than one) which initially would give insane percentage of incorrectly recognized text. Community could fix those errors (weak link in my plan:)). Afterwards you feed data back to software and train it so next time it would work better.

Training would require marking which person talks when in episode to tune algorithms for each of them. Maybe group them by regional dialects.

Oh, another tiny small thingie - not clear how to monetize that.

Monetization: you could sell the service to professional podcasters as it would increase content on their site, and possibly serve as another place to put ads for their sponsors.

If you focused on a core set of popular podcasts you could package it as a monthly ebook or similar product. While overall people don't like paying for content like that I think it's possible to find a niche market that would.

Agreed about monetization. Ideally, this should be a community thing like Wikipedia but that’s probably unrealistic.

I really think it would be an amazing resource. There would be so much great content that the site would potentially rank really high on Google for a variety of search terms, too (again, like Wikipedia).

I honestly think the blog approach where you highlight sections is the best way to do it. General transcripts are indeed almost impossible to do, especially when there are weekly shows that run for over two hours each episode.

I don't, but people seem to actually use stuff like Siri, which tells me some amount of automated audio processing is currently feasible.

I just tried it, and voice dictation on the iPhone does a surprisingly good job with a well produced podcast. It's missing all punctuation of course, and tends to make a lot of mistakes on small words like prepositions. But for a first pass to edit from, it is surprisingly good.

Seems like it's time for podcast.genius.com, which would be amazing.