The Mary Text-to-Speech (TTS) service is a pure Java implementation of a TTS service, which uses the MaryTTS project of DFKI.
While it provides good quality results, it must be noted that it is too heavy-weight for most embedded hardware like Raspberry Pis. When using this service, you should be running openHAB on some real server instead.
There is no need to configure anything for this service.
MaryTTS comes with three packages voices, one for American English, two for German:
> voice voices marytts:cmuslthsmm cmu-slt-hsmm (en_US) marytts:bits3hsmm bits3-hsmm (de) marytts:bits1hsmm bits1-hsmm (de)
Supported Audio Formats
The MaryTTS service produces audio streams using WAV containers and PCM (signed) codec with 16bit depth. The sample frequency depends on the chosen voice and ranges from 16kHz to 48kHz.