online now

We have 64 guests and no members online




Voice mode configures the system for producing synthetic speech. In voice mode all hardware is dedicated to producing allophones, which are smoothly blended configurations for each of the 64 available phonemes. The interface allows the construction of phrases that contain the phonemes as well as in-stream inflections or produce dynamic speech. In addition to playing back phrases, you can also send commands on the fly and control voice pitch, rate, and blending to add for realtime dynamics to the voice. The pitch of the voice can be defined both in frequency and in musical note, allowing the voice to sing as well as talk.

The following code example will allow the device to speak "hello world" with inflection:


GSAllophone  hello[] = { _HE , _PITCHUP , _E , _LO ,_PITCHDN ,  _OE , _PA1 , _ENDPHRASE }; 
GSAllophone  world[] = { _W , _BENDUP , _ER , _LE , _ED , _PA1 , _ENDPHRASE };

GinSingVoice *voice = GS.getVoice();                           // get the voice mode interface
voice->begin(); // enter voice mode

voice->speak ( hello );                                        // speak hello
delay ( voice->getMillis( hello ) );                           // wait for it to finish

voice->speak ( world );                                        // speak world
delay ( voice->getMillis( world ) );                           // wait for it to finish