Configuration of Naomi
The configurations contains six sections:
- Audio - Audio is the hardest part to setup, but don't worry, if you follow theses steps, everything should be ok
- TTS - TTS, stands for Text To Speech, is software that transforms text into speech, which is how Naomi can speak to you
- STT - STT, stands for Speech to Text, is software that transforms spoken words & sentences into text, which is how Naomi can understand you
- STTTrainer - A plugin which helps you train a STT engine to recognize your voice better
- TTI - TTI stands for Text to Intent. This takes the text of your request and determines which intent(s) you were trying to activate.
- VAD - VAD, stands for Voice Activity Detection, is software that detects when you are speaking
- NPE - NPE, stands for Naomi Plugin Exchange, easily search for and install 3rd party plugins
- Profile - The backbone that give Naomi the basic information needed to run
- SpeechHandler - SpeechHandler plugins that come with Naomi as well as ones you can install
The individual articles hold all details needed to understand the concepts behind these building bricks for your vocal assistant.
Caught a mistake or want to contribute to the documentation? Edit this page on GitHub