arduinoPicovoice Platform — Arduino Quick Start

Platforms

Requirements

Picovoice Account & AccessKey

  1. Login or signup for a free account on the Picovoice Console.
  2. Go to the AccessKey tab to create one or use an existing AccessKey. Be sure to keep your AccessKey secret.

Quick Start

Setup

  1. Install and select desired board from Tools -> Board.
    • Install Arduino Mbed OS Nano Boards for Arduino Nano 33 BLE Sense.
    • Install Arduino Mbed OS Portenta Boards for Arduino Portenta H7 (M7 core).
  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.

Usage

Initialize audio and construct the picovoice object in the setup function:

#include <Picovoice_EN.h>
static const char* ACCESS_KEY = "${ACCESS_KEY}";
static uint8_t memory_buffer[MEMORY_BUFFER_SIZE] __attribute__((aligned(16)));
static const uint8_t *keyword_array = ${KEYWORD_ARRAY};
const float porcupine_sensitivity = 0.5f;
static void wake_word_callback(void) {
// logic to execute upon detection of wake word
}
static const uint8_t *context_array = ${CONTEXT_ARRAY};
const float rhino_sensitivity = 0.75f;
static void inference_callback(pv_inference_t *inference) {
// `inference` exposes three immutable properties:
// (1) `IsUnderstood`
// (2) `Intent`
// (3) `Slots`
// ..
pv_inference_delete(inference);
}
pv_picovoice_t *picovoice = NULL;
void setup() {
pv_status_t status = pv_audio_init_rec();
if (status != PV_STATUS_SUCCESS) {
// error starting audio
while(1);
}
status = pv_picovoice_init(
ACCESS_KEY,
MEMORY_BUFFER_SIZE,
memory_buffer,
sizeof(keyword_array),
keyword_array,
porcupine_sensitivity,
wake_word_callback,
sizeof(context_array),
context_array,
rhino_sensitivity,
true,
inference_callback,
&picovoice);
if (status != PV_STATUS_SUCCESS) {
// error handling logic
while(1);
}
}

Get the audio frames and pass them in to pv_picovoice_process in the loop function:

void loop() {
const int16_t *buffer = pv_audio_rec_get_new_buffer();
if (buffer) {
const pv_status_t status = pv_picovoice_process(picovoice, buffer);
if (status != PV_STATUS_SUCCESS) {
// handle error logic
while(1);
}
}
}

Release resources explicitly when done with Picovoice:

pv_picovoice_delete(picovoice);

Create Custom Keywords

  1. Obtain the UUID of the chipset:
    1. Open File -> Examples -> Picovoice_EN -> GetUUID.
    2. Click Upload and check the Serial Monitor for the UUID of the board:
UUID: xx xx xx xx xx xx xx xx
  1. Go to Picovoice Console to create models for Porcupine wake word engine and Rhino Speech-to-Intent engine.
  2. Select Arm Cortex-M as the platform when training the model.
  3. Select appropriate board type and paste in your board UUID.
  4. Train your models.
  5. Download your custom voice model(s).
  6. 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.
  7. Copy the contents of the arrays inside the .h header files and update the keyword_array and context_array values.
const uint8_t *keyword_array = ${CUSTOM_KEYWORD_ARRAY};
const uint8_t *context_array = ${CUSTOM_CONTEXT_ARRAY};

Non-English Languages

Open the Library Manager in the Arduino IDE and search for Picovoice. Click Install on the language desired and add the header file to the project:

#include <Picovoice_{$LANGUAGE_CODE}>

Demo

For the Picovoice Arduino SDK, we offer demo projects for several evaluation boards to demonstrate how to use the Picovoice SDK on Arduino.

Setup

  1. Open the Library Manager in the Arduino IDE.
  2. Search for the Picovoice_EN package, and click on the Install button.

Usage

  1. Open File -> Examples -> Picovoice_EN -> PicovoiceExcample.
  2. Replace ACCESS_KEY with the AccessKey obtained from picovoice console.
  3. Press Upload and check Serial Monitor for outputs.

Resources

API

GitHub

Videos

Further Reading


Issue with this doc? Please let us know.