Setup and Run your first code
When we access the AI Voicebox terminal for first time, we will notice that the setup has to be done to make it speak.
As described in the Introduciton to Software module, various services are running in multiple layers to perform tasks like Speech to Text, Text to Speech, Wake Word Command, etc.
To get started, enable the following services and click "Save Settings":
- Audio Recording (PyAudio)
- Speech to Text (Kadli)
- Intent Recognition (Fsticuffs)
- Text to Speech (NanoTTS)
- Audio Playing (aplay)
- Dialogue Management (Rhasspy)
Once Rhasspy restarts, you will see a notification at top that tells you Rhasspy needs to download some files before continuing.
Click the "Download" button to begin downloading the necessary speech models, etc. from GitHub. You will see a dialogue box with the download progress of each file.
Once all files have finished downloading, Rhasspy will automatically restart.
We need to setup respeaker as the output device for audio, to setup up the speaker. Follow the steps given below.
Audio Playing Setup
Audio Recording Setup
Once the setup is done, navigate to the home page and click on "Wake Up" button to test, also write down the content to be spoken in "Speak" form to make it speak
Congratulations, your setup initial setup is done for AI Voice Box and is ready to speak