Installing the speech synthesizer

• Two speech synthesizers are compatible with Greta so far, OpenMary and Cereproc. If you plan on using Cereproc, you need to acquire a license and place the voices and their respective license files in the bin\Common\Data\Cereproc folder. If you plan on using OpenMary, you need to have an OpenMary server running. For this tutorial we will focus on using Openmary for speech.

• Go to http://mary.dfki.de/download/index.html and install MARY TTS.

• After the installation, navigate to the folder marytts-5.2\marytts-5.2\bin and run the marytts-server.bat file to start the MaryTTS server. Once the server is up and running, you will be able to see the port number.

• You can change and verify the address and the port number of your server in the file \greta-master\greta-master\bin\vib.ini. You can also check the character files in bin\Common\Data\characters to verify which voices are needed and used.

• Now we have to add the OpenMary Client module to the agent in the configuration window. Add the module from 'TTS' category under 'ADD' tab and connect it to the TTS module.