Tag Archives: Artificial Intelligenge

In this video lesson you will learn how to train the Raspberry Pi to take voice commands from you. We do this through the Fusion AI+ hat’s microphone, and a Speech to Text (STT) model. Our goal is to develop the ability to interact with our projects through spoken words. We give commands to the project, and then it responds intelligently with words.

Remember these lessons depend on you using the AI Educational OS, a special version of bookworm that has all the libraries, modules, and models already installed for you. See LESSON #2 in this class for instructions on flashing that OS.

Below is the simple demonstration code we developed to give simple voice commands:

from fusion_hat.stt import STT

stt = STT(language="en-us")

while True:
    print("Say Something: ")
    command = stt.listen(stream=False)
    print(command)

from fusion_hat.stt import STT

stt = STT(language="en-us")

while True:

print("Say Something: ")

command = stt.listen(stream=False)

print(command)

Similar to our Speech to Text example, the first time you run this program you will get a permissions error. You need to open a terminal, and put these commands in one at a time to enable permissions. This only has to be done once, and after that this and all STT programs should run properly.

sudo mkdir -p /opt/vosk_models
sudo chown -R pi:pi /opt/vosk_models
sudo chmod -R 755 /opt/vosk_models

sudo mkdir -p /opt/vosk_models

sudo chown -R pi:pi /opt/vosk_models

sudo chmod -R 755 /opt/vosk_models

AI On the Edge, Tutorial

AI on the Edge LESSON 8: Text to Speech (TTS) on the Raspberry Pi

April 24, 2026 admin

In this video lesson I will show you how to get the Raspberry Pi to speak to you in plain English. This is our first dabbling with AI. In earlier lessons we have discussed that one of our first objectives will be to begin to audibly interact with our project through speech. The first step will be to get the Pi to talk to us. Then in future lessons we will show how to get the Pi to listen to us.

In this lesson we demonstrated simple Text to Speech (TTS) with this code.

Remember this program requires use of the AI Educational OS we flashed in LESSON #2.

from fusion_hat.tts import Piper
tts = Piper()
tts.set_model('en_US-amy-low')
msg = "Hi, I'm piper TTS. Are you Ready to Rumble? I am here to pump you up!"
tts.say(msg, stream=False)

from fusion_hat.tts import Piper

tts = Piper()

tts.set_model('en_US-amy-low')

msg = "Hi, I'm piper TTS. Are you Ready to Rumble? I am here to pump you up!"

tts.say(msg, stream=False)

As we say in the video, the first time you run the program you will get a permission error. This is because the model folders are inside a system folder and must be created as a ‘superuser’ using ‘sudo’. As shown in the video, you need to open a terminal window, and type in these commands at the command prompt (Put them in one at a time):

sudo mkdir -p /opt/piper_models
sudo chown -R pi:pi /opt/piper_models
sudo chmod -R 755 /opt/piper_models

sudo mkdir -p /opt/piper_models

sudo chown -R pi:pi /opt/piper_models

sudo chmod -R 755 /opt/piper_models

You only need to do that one time. Next time you run the program, all will work properly.

Then, in order to hear all the different voice models Piper offers, you can run this program, and each voice will introduce itself to you.

from fusion_hat.tts import Piper
from time import sleep  # Optional: for pauses between voices
tts = Piper()
# Get the dictionary of available en_US models
voiceDict = tts.available_models('en_US')
print(voiceDict)
# Flatten into a single list of full model names
allVoices = []
for voice in voiceDict.values():
    for var in voice:
        allVoices.append(var)
print(allVoices) 

msg = "Hello World. This is a test message."
for voice in allVoices:
    tts.set_model(voice)  # Auto-downloads on first use
    # Create a readable voice name (remove 'en_US-' and replace '_' with space)
    speakableName = voice.replace('en_US-', '').replace('_', ' ')
    print("Switching to: " + speakableName)
    print(voice)
    sleep(5)
    # Introduction in that voice
    intro = "This is the voice " + speakableName + "."
    tts.say("Hello There" + intro)
    #tts.say(msg, stream=False)
    sleep(.1)
print("All voices demonstrated!")
for voice in allVoices:
    print(voice)

from fusion_hat.tts import Piper

from time import sleep # Optional: for pauses between voices

tts = Piper()

# Get the dictionary of available en_US models

voiceDict = tts.available_models('en_US')

print(voiceDict)

# Flatten into a single list of full model names

allVoices = []

for voice in voiceDict.values():

for var in voice:

allVoices.append(var)

print(allVoices)

msg = "Hello World. This is a test message."

for voice in allVoices:

tts.set_model(voice) # Auto-downloads on first use

# Create a readable voice name (remove 'en_US-' and replace '_' with space)

speakableName = voice.replace('en_US-', '').replace('_', ' ')

print("Switching to: " + speakableName)

print(voice)

sleep(5)

# Introduction in that voice

intro = "This is the voice " + speakableName + "."

tts.say("Hello There" + intro)

#tts.say(msg, stream=False)

sleep(.1)

print("All voices demonstrated!")

for voice in allVoices:

print(voice)

Remember in these early lessons we are using this circuit to demo our programs. Please leave this circuit put together.

Fusion Hat Circuit Diagram — This is the circuit we will use moving forward in the class

AI On the Edge, Tutorial

AI on the Edge LESSON 7: Homework Solution for Dimmable LED

April 18, 2026 admin

In Lesson 6, I gave you a homework challenge: build a dimmable LED using a potentiometer. In today’s Lesson 7, we go through the solution together step-by-step.

This lesson is all about taking analog input from a potentiometer and converting it into smooth PWM output to control the brightness of an LED. It’s a very practical project because it teaches you how to read real-world analog values and turn them into useful control signals — skills we’ll use again and again as we build smarter AI-powered projects.

In the video, I walk you through the complete working code. You’ll see how we read the potentiometer value (0 to 4095), convert that raw number into a proper brightness percentage using a bit of math (with a nice logarithmic curve so the brightness feels natural to the human eye), and then send that value to the LED using PWM. The result is a very smooth, responsive dimmer that feels professional.

Even though this seems like a simple project, it’s actually an important stepping stone. Understanding how to read sensors and smoothly control outputs is fundamental to building real AI on the Edge systems — whether you’re controlling motors, adjusting screen brightness, or varying the speed of a robot based on sensor input.

By the end of this lesson, you should have a solid understanding of how to combine the ADC (Analog to Digital Converter) with PWM output, and more importantly, how to think about mapping real-world inputs to useful outputs.

So if you did the homework, great job! If you got stuck, don’t worry — we go through the full solution together. And as always, I strongly encourage you to take the code and make it your own. Try changing the response curve, add multiple LEDs with different colors, or combine it with things we’ve learned in earlier lessons.

This is the kind of foundational hardware skill that will serve you well as we continue moving deeper into the AI on the Edge class. You’re doing great — keep going!

We are still using the schematic from our earlier project.

In this lesson, this is the code which we came up with:

#!/usr/bin/env python3
from fusion_hat.adc import ADC
from fusion_hat.pwm import PWM
from time import sleep
import math
potPin=0
myPot = ADC(0)
redPin=5
redLED=PWM(redPin)

while True:
    potVal = myPot.read()                     # 0 to 4095
    writeVal=100**(potVal/4095)-.005
    redLED.pulse_width_percent(int(writeVal))
    print(potVal,writeVal)
    sleep(0.1)

#!/usr/bin/env python3

from fusion_hat.adc import ADC

from fusion_hat.pwm import PWM

from time import sleep

import math

potPin=0

myPot = ADC(0)

redPin=5

redLED=PWM(redPin)

while True:

potVal = myPot.read() # 0 to 4095

writeVal=100**(potVal/4095)-.005

redLED.pulse_width_percent(int(writeVal))

print(potVal,writeVal)

sleep(0.1)

AI On the Edge

AI on the Edge LESSON 5: Understanding Fusion AI Hat+ For Raspberry Pi

April 9, 2026 admin

In today’s lesson we will become familiar with the capabilities of the Fusion AI Hat+ for the Raspberry Pi. This hat will be a core part of our class moving forward. The hat makes it easy to get data from the outside world, and to control things in the outside would. We will get an understanding of the core capabilities of the board, and your homework will be to build the first circuit with the board. This schematic shows the various parts of the board:

Fusion AI Hat for Raspberry Pi Schematic

Then for the homework, we need you to go ahead and build this circuit. This circuit will allow us to learn how to make Digital Output commands, PWM commands, and how to read analog inputs.

Artificial Intelligence, OpenCV, Raspberry Pi

Raspberry Pi LESSON 63: Object Detection on Raspberry Pi Using Tensorflow Lite

May 25, 2023 admin

In this lesson I show you how to do object detection on the Raspberry Pi using Tensorflow Lite. We will write our first program and by the end of the lesson you will have your Pi detecting objects, boxing them and labeling them in OpenCV.

The video demonstrates step-by-step how to install the tensorflow libraries.

For your convenience I have included the code below we develop in this lesson

import cv2
import time
from picamera2 import Picamera2

from tflite_support.task import core
from tflite_support.task import processor
from tflite_support.task import vision
import utils

model='efficientdet_lite0.tflite'
num_threads=4

dispW=1280
dispH=720

picam2=Picamera2()
picam2.preview_configuration.main.size=(dispW,dispH)
picam2.preview_configuration.main.format='RGB888'
picam2.preview_configuration.align()
picam2.configure("preview")
picam2.start()

webCam='/dev/video2'
cam=cv2.VideoCapture(webCam)
cam.set(cv2.CAP_PROP_FRAME_WIDTH, dispW)
cam.set(cv2.CAP_PROP_FRAME_HEIGHT, dispH)
cam.set(cv2.CAP_PROP_FPS, 30)

pos=(20,60)
font=cv2.FONT_HERSHEY_SIMPLEX
height=1.5
weight=3
myColor=(255,0,0)

fps=0

base_options=core.BaseOptions(file_name=model,use_coral=False, num_threads=num_threads)
detection_options=processor.DetectionOptions(max_results=3, score_threshold=.3)
options=vision.ObjectDetectorOptions(base_options=base_options,detection_options=detection_options)
detector=vision.ObjectDetector.create_from_options(options)
tStart=time.time()
while True:
    ret, im = cam.read()
    #im=picam2.capture_array()
    #im=cv2.flip(im,-1)
    imRGB=cv2.cvtColor(im,cv2.COLOR_BGR2RGB)
    imTensor=vision.TensorImage.create_from_array(imRGB)
    detections=detector.detect(imTensor)
    image=utils.visualize(im, detections)
    cv2.putText(im,str(int(fps))+' FPS',pos,font,height,myColor,weight)
    cv2.imshow('Camera',im)
    if cv2.waitKey(1)==ord('q'):
        break
    tEnd=time.time()
    loopTime=tEnd-tStart
    fps= .9*fps +.1*1/loopTime
    tStart=time.time()
cv2.destroyAllWindows()

import cv2

import time

from picamera2 import Picamera2

from tflite_support.task import core

from tflite_support.task import processor

from tflite_support.task import vision

import utils

model='efficientdet_lite0.tflite'

num_threads=4

dispW=1280

dispH=720

picam2=Picamera2()

picam2.preview_configuration.main.size=(dispW,dispH)

picam2.preview_configuration.main.format='RGB888'

picam2.preview_configuration.align()

picam2.configure("preview")

picam2.start()

webCam='/dev/video2'

cam=cv2.VideoCapture(webCam)

cam.set(cv2.CAP_PROP_FRAME_WIDTH, dispW)

cam.set(cv2.CAP_PROP_FRAME_HEIGHT, dispH)

cam.set(cv2.CAP_PROP_FPS, 30)

pos=(20,60)

font=cv2.FONT_HERSHEY_SIMPLEX

height=1.5

weight=3

myColor=(255,0,0)

fps=0

base_options=core.BaseOptions(file_name=model,use_coral=False, num_threads=num_threads)

detection_options=processor.DetectionOptions(max_results=3, score_threshold=.3)

options=vision.ObjectDetectorOptions(base_options=base_options,detection_options=detection_options)

detector=vision.ObjectDetector.create_from_options(options)

tStart=time.time()

while True:

ret, im = cam.read()

#im=picam2.capture_array()

#im=cv2.flip(im,-1)

imRGB=cv2.cvtColor(im,cv2.COLOR_BGR2RGB)

imTensor=vision.TensorImage.create_from_array(imRGB)

detections=detector.detect(imTensor)

image=utils.visualize(im, detections)

cv2.putText(im,str(int(fps))+' FPS',pos,font,height,myColor,weight)

cv2.imshow('Camera',im)

if cv2.waitKey(1)==ord('q'):

break

tEnd=time.time()

loopTime=tEnd-tStart

fps= .9*fps +.1*1/loopTime

tStart=time.time()

cv2.destroyAllWindows()

Technology Tutorials

Tag Archives: Artificial Intelligenge

AI on the Edge LESSON 10: Make Your Raspberry Pi Listen to You with Voice Commands

AI on the Edge LESSON 8: Text to Speech (TTS) on the Raspberry Pi

AI on the Edge LESSON 7: Homework Solution for Dimmable LED

AI on the Edge LESSON 5: Understanding Fusion AI Hat+ For Raspberry Pi

Raspberry Pi LESSON 63: Object Detection on Raspberry Pi Using Tensorflow Lite

Making The World a Better Place One High Tech Project at a Time. Enjoy!