TTS introduction

TTS introduction

  • Comments 2

TTS means "Text to speech" which is  the technology to let computer speak to you.

In short, you can input the text to computer, then a computer algorithm (so called TTS engine) will analyze the text, determine the pronunciation, synthesize the sound with some mathematical models. The output of a TTS engine is usually kind of sound data like PCM wave data etc.

On Windows platform, TTS functionality can be called via Speech API. There are two Speech APIs as below:

- System.Speech: managed

- SAPI: unmanaged

To get Speech API SDK, here is the good source to start

http://blogs.msdn.com/chuckop/archive/2008/02/26/speech-content-in-the-windows-sdk.aspx

I will discuss some aspects on how to use TTS via Speech API in future posts.  

The user scenerios of TTS are mainly related to human machine interaction. Together with SR (Speech Recognition), Speech technology provides the foundmentals for next generation of natual user interface.

Dear readers,  do you use TTS in your application or scenerio? How do you think about it? I'd like to hear comments or story from you.

Leave a Comment
  • Please add 6 and 3 and type the answer here:
  • Post
Page 1 of 1 (2 items)