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.
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.
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...
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.
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).
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.