Hacker News Reader

I'm a big fan of the android tts. A bit robotic, with quite a few prosodic errors (which is simple to get used to), but so convenient. No need to hunt for audiobooks - actually in most languages the size of the audibook market is rather poor...

I can switch easily from audio to reading, e.g. listening while walking to the bus, and if I get a seat then switch to read, and then back to listening etc...

View on HN

With the rate speech synthesis is developing, it's probably going to be hard to distinguish between human speakers and synthetic speakers in a few years from now.

See https://google.github.io/tacotron/publications/tacotron2/ind...

And the HN discussion: https://news.ycombinator.com/item?id=15962543

I think what's missing is to understand and adapt the speech rhythm and pauses based on the language. At first sight I would say that this requires human intuition, but then again, lots of literature is repetative, so I think ML could actually work quite well well, with actual understanding of the text, given enough data.

I'm really looking forward to those actually being available to use.

I've just started to use AWS Polly in some demos, but the speech synthesis quality feels 2-3 years old at least :/

Reply on news.ycombinator.com