Hacker News Reader

Sorry if this is off-topic with respect to the content of the episode, but does anybody know what kind of software NPR uses to create these transcripts? There is a very specific structure to the layout and I'm wondering what the data entry UI looks like, if it's a commercial package, or if they rolled their own. Thanks.

View on HN

I don't know for sure but the transcripts are so good and for a show like TAL I imagine that they could probably have someone do them by hand.

I don't know either, but it looks like the transcripts are initially generated from speech recognition (text dump + timing meta data?) and then hand-edited/annotated by a producer.

They'd add punctuation, sound cues, fix spelling, annotate the speakers (e.g. name + host, subject, or interviewer). Then that data's got to go somewhere...

It looks pretty labor intensive. I sure hope they have great tools!

I don't know for sure but they probably use something by Nuance

Reply on news.ycombinator.com