How to use Cepstral Text-to-Speech (TTS) support on ScopTEL

In order use Text-to-Speech engine on the ScopServ Telephony Server GUI, you must install Cepstral.

We’re going to walk you through installing Cepstral with the Cepstral Allison voice. But there are numerous other voices. You can check all of them out on the Cepstral demo site. Just be sure to select only the 8kHz voices which are specifically designed to support telephony applications.

 

Installing Cepstral

Be sure you choose the correct i386-Linux version for your system. You can’t use the 32-bit version on a 64-bit CentOS system, e.g. the new 64-bit ISO of ScopServ Telephony Server. But the same license key works for both the 32-bit and 64-bit versions of the same voice.

For the 32-bit version of ScopServ Telephony Server, log into your system as root and enter the following commands:

 

[note color=#ddd]cd /root
wget http://www.cepstral.com/downloads/installers/linux32/Cepstral_Allison-8kHz_i386-linux_6.0.1.tar.gz
tar -zxvf Cepstral*
cd Cepstral_Allison-8kHz_i386-linux_6.0.1
./install.sh
[/note]

For the 64-bit version of ScopServ Telephony Server, log into your system as root and enter the following commands:

 

[note color=#ddd]cd /root
wget http://www.cepstral.com/downloads/installers/linux64/Cepstral_Allison-8kHz_x86-64-linux_6.0.1.tar.gz
tar -zxvf Cepstral*
cd Cepstral_Allison-8kHz_x86-64-linux_6.0.1
./install.sh[/note]

After you’ve read the license, type yes to install the voice on your system, Accept the default locations for the installation. When the installation completes, issue the following command:

 

[note color=#ddd]echo /opt/swift/lib > /etc/ld.so.conf.d/cepstral.conf
ldconfig[/note]

 

Configure Text-to-Speech

Once the Cepstral TTS application is installed, you can start using it right away on the ScopTEL PBX. New options to enable Text-to-Speech (TTS) are available on the following sections of the Telephony module and allow to customize the announce messages :

  • Audio -> IVR Prompts
  • Applications -> Application
  • Applications -> Auto Attendant (IVR)
  • Queue (ACD) -> ACD
  • Configuration -> Hangup Cause
Text to Speech (TTS)

Text to Speech (TTS)

 

 

Using SSML Language

Cepstral voices support the Speech Synthesis Markup Language (SSML). SSML provides a wide range of control over how input text is read by a TTS engine. For example, with SSML, one can alter prosody attributes, such as rate, pitch, and volume, insert pauses of any length, change the speaking voice while reading, and control many other aspects of how the text is read by the synthetic voice.

The Voice Browser Working Group has sought to develop standards to enable access to the Web using spoken interaction. The Speech Synthesis Markup Language Specification is one of these standards and is designed to provide a rich, XML-based markup language for assisting the generation of synthetic speech in Web and other applications.

More information can be found on on the W3’s SSML 1.0 specificiation available on http://www.w3.org/TR/speech-synthesis11/

We also recommand to read Cepstral SSML FAQ on http://www.cepstral.com/support/faq/customization/ssml.html