Building an AI Assistant with Voice Control using Python

In this tutorial, we will learn how to build an AI assistant with voice control using Python. The assistant will be able to perform various tasks such as searching the web, opening applications, playing music, sending emails, providing information from Wikipedia, setting reminders, and more. We will be using several Python libraries such as pyttsx3, speech_recognition, datetime, wikipedia, webbrowser, os, smtplib, urllib.parse, subprocess, time, and requests.

Prerequisites

To follow along with this tutorial, you will need:

Python installed on your system (version 3.6 or higher).
The following Python libraries: pyttsx3, speech_recognition, wikipedia, webbrowser, os, smtplib, urllib.parse, subprocess, time, and requests. You can install them using pip:
```
pip install pyttsx3 speechrecognition wikipedia requests
```

Understanding the Code

Let's go through the code step by step and understand each component:

Importing the necessary libraries:

python
import pyttsx3
import speech_recognition as sr
import datetime
import wikipedia
import webbrowser
import os
import smtplib
import urllib.parse
import subprocess
import time
import requests

Initializing the pyttsx3 engine:

python
engine = pyttsx3.init()
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[0].id)

Defining a function to convert text to speech:

python
def speak(audio):
    engine.say(audio)
    engine.runAndWait()

Creating a function to greet the user based on the current time:

python
def wishMe():
    hour = datetime.datetime.now().hour
    if 0 <= hour < 12:
        greeting = "Good Morning!"
    elif 12 <= hour < 18:
        greeting = "Good Afternoon!"
    else:
        greeting = "Good Evening!"
    speak(f"{greeting} Hello, I am your AI assistant. How may I assist you?")

Implementing a function to listen to the user's voice command:

python
def takeCommand():
    r = sr.Recognizer()
    with sr.Microphone() as source:
        print("Listening...")
        r.pause_threshold = 1
        audio = r.listen(source)

    try:
        print("Recognizing...")
        query = r.recognize_google(audio, language='en-in')
        print(f"User said: {query}\n")
        return query
    except Exception as e:
        print("Say that again, please...")
        return "None"

Creating a function to search YouTube based on a query:

python
def searchYouTube(query):
    base_url = 'https://www.youtube.com/results?search_query='
    query = urllib.parse.quote_plus(query)
    webbrowser.open(base_url + query)

Defining a function to open Google Chrome:

python
def openChrome():
    codePath = r"C:\Program Files\Google\Chrome\Application\chrome.exe"
    webbrowser.get(codePath).open("google.com")

Creating a function to search Google based on a query:

python
def searchGoogle(query):
    base_url = 'https://www.google.com/search?q='
    query = urllib.parse.quote_plus(query)
    webbrowser.open(base_url + query)

Implementing a function to send emails:

python
def sendEmail(to, content):
    server = smtplib.SMTP('smtp.gmail.com', 587)
    server.ehlo()
    server.starttls()
    server.login('youremail@gmail.com', 'your-password')
    server.sendmail('youremail@gmail.com', to, content)
    server.close()

Defining a function to perform calculations:

python
def calculate(expression):
    try:
        result = eval(expression)
        speak(f"The result is {result}")
    except Exception as e:
        speak("Sorry, I couldn't perform the calculation.")

Creating a function to set reminders:

python
def setReminder():
    speak("What should I remind you about?")
    reminder = takeCommand()
    speak("When should I remind you?")
    reminder_time = takeCommand()

    # Extract hours and minutes from the reminder time
    hours, minutes = map(int, reminder_time.split(':'))

    # Get the current date and time
    now = datetime.datetime.now()

    # Set the reminder time with the current date and specified hours and minutes
    reminder_time = now.replace(hour=hours, minute=minutes, second=0, microsecond=0)

    # Calculate the time difference between now and the reminder time
    time_difference = (reminder_time - now).total_seconds()

    if time_difference <= 0:
        speak("The reminder time has already passed.")
    else:
        speak(f"Reminder set for {reminder_time.strftime('%H:%M')}.")
        time.sleep(time_difference)
        speak(f"Reminder: {reminder}")

Implementing a function to process user commands:

python
def processCommand(command):
    if 'wikipedia' in command:
        speak('Searching Wikipedia...')
        query = command.replace("wikipedia", "")
        results = wikipedia.summary(query, sentences=2)
        speak("According to Wikipedia")
        print(results)
        speak(results)

    elif 'open youtube' in command:
        webbrowser.open("https://www.youtube.com")

    elif 'open chat' in command:
        webbrowser.open("https://chat.openai.com")

    elif 'open google' in command:
        webbrowser.open("https://www.google.com")

    # ... more commands ...

Defining a function to get the weather information:

python
def getWeather():
    api_key = "65d2b3204db54b0696140719232506"  # Replace with your actual API key
    base_url = f"http://api.weatherapi.com/v1/current.json?key={api_key}&q=current"
    response = requests.get(base_url)
    data = response.json()

    if 'error' in data:
        speak("Sorry, I couldn't retrieve the weather information.")
    else:
        location = data['location']['name']
        temperature = data['current']['temp_c']
        condition = data['current']['condition']['text']
        speak(f"The current temperature in {location} is {temperature} degrees Celsius with {condition}.")

The main part of the code:

python
if __name__ == "__main__":
    wishMe()
    while True:
        command = takeCommand().lower()

        if 'exit' in command:
            break

        processCommand(command)

Running the Code

To run the AI assistant program, follow these steps:

Save the code in a Python file with a .py extension (e.g., ai_assistant.py).
Open a terminal or command prompt and navigate to the directory where the Python file is located.
Run the code using the following command:
```
python ai_assistant.py
```
Once the program starts running, the AI assistant will greet you and wait for your voice command.
You can give voice commands to the assistant, such as "What's the time?", "Open YouTube", "Search Wikipedia for Python", "Send an email", and more. The assistant will process your command and perform the corresponding task.
To exit the program, say "Exit" or press Ctrl+C in the terminal.

Download link- https://drive.google.com/file/d/1RwEbntXbPOHMYBTAwAYApnjrEpazZ2Tn/view?usp=sharing

Conclusion

Congratulations! You have successfully built an AI assistant with voice control using Python. This assistant can perform various tasks based on your voice commands, such as searching the web, opening applications, playing music, sending emails, providing information from Wikipedia, setting reminders, and retrieving weather information. Feel free to customize and enhance the assistant's functionalities according to your needs. Happy coding!

ZestBook

Search This Blog