This blog entry is the second of an 11-part series highlighting the top 11 new features in InphoniteVoice 2012.
Text-to-speech is a necessary component of any dynamic telephone-based application. A quality text-to-speech engine allows you to quickly build dynamic and interactive voice response applications. A poor quality text-to-speech engine can be difficult to understand, which will require you to record more of the speech elements in order for the message to be delivered effectively. In InphoniteVoice 2010, we shipped the product with one text-to-speech engine, US English. While this text-to-speech engine worked well for many of our customers, there was a lot of room for improvement. InphoniteVoice 2012 introduces a new speech engine that is a dramatic improvement over any previous engine we have used. In addition to the improvements, we are including over 27 text-to-speech voices at no additional cost.
While we have taken great strides to make text-to-speech as human-like as possible, it is not, unfortunately, possible for text-to-speech to ever be as good as a creating a custom voice recording. To aide in making InphoniteVoice 2012 as ‘human’ as possible, we include over 13,000 professionally recorded names. In addition, common speech elements, such as date and time information, are also included with the product. Finally, we have made numerous improvements to the InphoniteVoice client to make it as easy as possible to create custom voice recordings while you are designing your message.
Here is the complete list of the 27 new text-to-speech voices included with InphoniteVoice 2012:
InphoniteVoice 2012 takes great strides to improve the user experience by offering an improved text-to-speech engine, the ability to choose between 27 voices, and numerous improvements that eliminate the need for text-to-speech altogether. All of these new features combined make InphoniteVoice 2012 the most powerful product on the market today.
