Re:Text to speech in Python
by visarga on Sunday June 25, 2017 @09:41AM
(#14629926)
I'm wondering why the Linux TTS offering is so dismal, and why the voices used by Apple, Google and MS are so old. We have seen amazing demos with WaveNet from DeepMind a year ago. Where are the new amazing voices?
[ Parent
| on HN ]
Because WaveNet is very impractical in production (per sample prediction). Tacotron may be a better fit (https://google.github.io/tacotron).