We’re pleased to announce that the rSpeak Technologies development team has rolled out an updated version of the rSpeak SDK/Engine, supporting the latest version of SAPI and providing some exciting new features with rSpeak’s state of the art TTS voices.
The SAPI application programming interface (API) dramatically reduces the code overhead required for an application to use speech recognition and text-to-speech, making speech technology more accessible and robust for a wide range of applications.
Among these new features, rSpeak TTS voices now also support viseme callbacks. Visemes are the gestures we make with our mouths as we generate phonemes. The former do not share a one-to-one correspondence and in many cases, several phonemes make up a single viseme, and different phonemes actually look the same on our face when we pronounce them.
The cool feature in the new version of rSpeak’s high-quality text to speech software is that the TTS engine detects viseme boundaries and generates a speaking action that is in sync with the facial movements of avatars and robots, making them appear and sound increasingly lifelike and natural.
Another useful feature in the new release is the Non-interactive installer (also known as the “silent installer”), which proves extremely useful in all situations where the Text to Speech installation needs to be done from a script or via CLI (Command Line Interface).
Check out the complete range of rSpeak voices, now available in the latest version of the rSpeak SDK/Engine. Would you like to test the power of rSpeak in your business or with your avatars and robots? Click here to get in touch.