Hi all, I've read some interesting articles about the use of deep neural networks to generate more convincing human speech. For example see below: https://deepmind.com/blog/wavenet-generative-model-raw-audio/ https://cloud.google.com/text-to-speech/ So far all the products I've seen are online-only, but it seems feasible to perform the speech synthesis offline (perhaps not the training). Has anybody heard of such an API or service being available? Thanks, JT