|
|
|
|
|
Type of feature
Text-to-Speech (TTS) is a licensed feature. You must have RTU licenses to use this feature.
About Text-to-Speech
With TTS, you can include speech in an application using ASCII text as input. The text is converted to synthesized speech through the third-party Text-to-Speech engine. TTS can be used for text that is retrieved from a database or a host or for prompts. Text can be spoken in an application with synthesized speech. Application development is supported through the IVR Designer software package.
TTS is an alternative to using prerecorded phrases for voice response. TTS can be essential in those applications that must speak dynamic text (for example, names and addresses) or that have large amounts of speakable text (for example, electronic news). Without TTS, these types of applications can require many hours of recording and much disk space. These applications can also use TTS for consistency in static text.
The TTS technology can distinguish between different classes of text, such as zip codes and telephone numbers, and pronounces the text string in the appropriate spoken format. When constructing speech, parameters such as pitch and duration are adjusted to make the outcome sound more natural. In addition, the ASCII text is preprocessed to expand abbreviations. For example, "Dr." is expanded to "doctor" or "drive," depending on the context.
Speech processing is done using one or more auxiliary computers connected to the Avaya IR system in a client server configuration. This capability is called Proxy Text-to-Speech (PTTS).
Hardware requirements
The Avaya IR system must be part of a LAN connected to a Text-to-Speech server.
Software requirements
The following software is required for the PTTS feature:
Setup considerations
You need to be aware of the capacity of your speech servers before connecting to the Avaya IR system. See the third-party TTS vendor documentation for more information.
Using this feature
Administer TTS using the Speech Administration > TTS Configuration screen in Web Administration.
For more information
For more information on Text-to-Speech, see:
