Audio samples – speech synthesis directly from text • Hacker News Board

Audio samples – speech synthesis directly from text

#1

Post by msq » Thu, Dec 28, 2017, 12:20 PM UTC

Audio samples – speech synthesis directly from text
google.github.io

Re: Audio samples – speech synthesis directly from text

#2

Post by Erik816 » Thu, Dec 28, 2017, 7:43 PM UTC

Definitely looks promising. I'm curious if there are any user-friendly ways to use this or similar WaveNet text to speech? Last time I looked into it, it still required a fair amount of processing power and a library of speech files to generate something on your own.

Re: Audio samples – speech synthesis directly from text

#3

Post by scarface74 » Thu, Dec 28, 2017, 7:48 PM UTC

Serious question, how does this stand out from speech synthesis we have had for years? The only problem that I see that this solves is the different pronunciations of "read".

Re: Audio samples – speech synthesis directly from text

#4

Post by kleiba » Thu, Dec 28, 2017, 7:52 PM UTC

This has been posted before, maybe even more than once. Can anyone find the link to the previous discussion?

Re: Audio samples – speech synthesis directly from text

#5

Post by melling » Thu, Dec 28, 2017, 7:59 PM UTC

kleiba wrote: post #4

This has been posted before, maybe even more than once. Can anyone find the link to the previous discussion?

A lot of things get posted multiple times. Best to just include the links:

https://news.ycombinator.com/item?id=16014047

Timing has a lot to do with upvotes.