Offline Voice AI on Arduino

Create voice experiences similar to Alexa with Arduino Nano 33 BLE Sense and Picovoice SDK in 15 steps

Detailed documentation: https://picovoice.ai/docs/quick-start/picovoice-arduino/

Requirements

• Arduino IDE
• Picovoice Account & AccessKey

1. Install and select desired board from Tools -> Board
2. Select the desired device Serial Port to upload package via Tools -> Port
3.Open the Library Manager in the Arduino IDE.4. Search for the Picovoice_EN package, and click on the Install button.5. Initialize audio and construct the picovoice object in the setup function:6. Get the audio frames and pass them in to pv_picovoice_process in the loop function7. Release resources explicitly when done with Picovoice8. Obtain the UUID of the chipset9. Go to Picovoice Console to create models for Porcupine Wake Word and Rhino Speech-to-Intent engines10. Select Arm Cortex-M as the platform when training the model.11. Select the appropriate board type and paste in your board UUID.12. Train your models13. Download your custom voice model(s).14. Decompress the zip file. The model file is either.ppn for Porcupine wake word or.rhn for Rhino Speech-to-Intent. Both zip archives also contain a.h header file containing the C array version of the binary model.15. Copy the contents of the arrays inside the.h header files and update the keyword_array and context_array values.