Re:Deep Voice: Real-Time Neural Text-To-Speech
by skykooler on Tuesday February 28, 2017 @09:16PM
(#13760363)
Julius[1] can do this. But the accuracy depends on the language model you are using, and unfortunately the free English language model (VoxForge) is not the best.
[1] http://julius.osdn.jp/en_index.php