Build a voice assistant with Python

Building a voice assistant with Python involves integrating several components like speech recognition, text-to-speech, and command handling. Here’s a step-by-step guide to create a simple yet functional voice assistant using popular Python libraries:

1. Install Required Libraries

You’ll need the following Python packages:

bash
CopyEdit
pip install SpeechRecognition pyttsx3 pyaudio

If pyaudio fails to install, on Windows use:

bash
CopyEdit
pip install pipwin
pipwin install pyaudio

2. Basic Voice Assistant Code

python
CopyEdit
import speech_recognition as sr
import pyttsx3
import datetime
import webbrowser
import os

# Initialize the text-to-speech engine
engine = pyttsx3.init()
engine.setProperty('rate', 150)  # Speed percent (can go over 100)
engine.setProperty('volume', 1)  # Max volume

# Function to convert text to speech
def speak(text):
    engine.say(text)
    engine.runAndWait()

# Function to take command from microphone
def take_command():
    recognizer = sr.Recognizer()
    with sr.Microphone() as source:
        print("Listening...")
        recognizer.pause_threshold = 1
        audio = recognizer.listen(source)

    try:
        print("Recognizing...")
        command = recognizer.recognize_google(audio, language='en-in')
        print(f"User said: {command}n")
    except Exception as e:
        print("Sorry, could not recognize. Please say that again...")
        return "None"
    return command.lower()

# Function to process the voice command
def process_command(command):
    if 'time' in command:
        str_time = datetime.datetime.now().strftime("%H:%M:%S")
        speak(f"The current time is {str_time}")
    elif 'open google' in command:
        speak("Opening Google")
        webbrowser.open("https://www.google.com")
    elif 'open youtube' in command:
        speak("Opening YouTube")
        webbrowser.open("https://www.youtube.com")
    elif 'play music' in command:
        music_dir = 'C:\Users\Public\Music'
        songs = os.listdir(music_dir)
        os.startfile(os.path.join(music_dir, songs[0]))
    elif 'your name' in command:
        speak("I am your personal assistant.")
    elif 'exit' in command or 'quit' in command:
        speak("Goodbye!")
        exit()
    else:
        speak("Sorry, I can't perform that task yet.")

# Main loop
if __name__ == "__main__":
    speak("Hello! I am your voice assistant. How can I help you today?")
    while True:
        user_command = take_command()
        if user_command != "None":
            process_command(user_command)

3. Add More Features

You can expand the assistant with:

• Weather Updates: Use an API like OpenWeatherMap.

• News Headlines: Use requests with a news API.

• Custom Commands: Add more elif conditions in process_command.

• AI Integration: Add OpenAI’s API for chatbot features.

• GUI: Use tkinter or PyQt for visual interface.

4. Tips for Improvement

• Add error handling for each functionality.

• Make it modular: split functions into separate files or classes.

• Use threading to manage long-running tasks like music without blocking the assistant.

• Implement wake word detection using libraries like snowboy or porcupine.

This voice assistant is basic but gives a solid foundation. You can progressively enhance it into a more intelligent virtual assistant by integrating NLP models and APIs.