When working with voice applications, there’s quite a few situations where the basic, default Speech Synthesis engine doesn’t really do the trick. Maybe your app communicates with people in the U.K. and they’d rather hear an accent to match; maybe you need to sloooow down the recital of your text to make it easier to understand; maybe you need the speech engine to recite a number as individual digits instead of a whole number (1234 as ‘one, two, three, four‘ instead of ‘one-thousand two-hundred thirty-four‘).
We gotcha covered, and then some.
Check out the Speaking & Playing chapter of the Scripting Guide. Inside, you’ll find detailed descriptions (and examples) covering the use of alternate voices (including male and female voices for two different English dialects, two different Spanish dialects, French, German, Italian, Polish and Dutch), how to use various SSML elements (like prosody for speed and say-as for text interpretation), and how to use pre-recorded audio instead of speech synthesis all together.
Sort out any cool ways to manipulate your audio output? Let us know in the comments or send us an e-mail to email@example.com!