Self Build Voice Assistant !

Introduction

A self-build voice assistant is an AI-powered virtual assistant that you create and customize according to your requirements. Unlike commercial voice assistants, a self-built version allows you to have complete control over the functionalities, privacy settings, and data usage. By building your voice assistant, you can design it to recognize your voice more accurately and cater to your specific needs, making the user experience more tailored and enjoyable.

Prerequisite Library

1. speech_recognition
2. pywhatkit
3. os
4. pyautogui
5. time
6. pysstx3
7. datetime
8. subprocess

Speech Recognition

• Speech Recognition is an AI-driven technology that enables machines to understand and interpret human speech, converting spoken words into written text
• .Install Speech Recognition library using pip command.

pip install SpeechRecognition        

Pywhatkit

• Pywhatkit is a Python library that offers various functionalities and features to simplify tasks related to web scraping, sending WhatsApp messages, performing Google searches, and more.
• Install pywhatkit library using pip command.

pip install pywhatkit        

Os

• The "os" module in Python provides a way to interact with the operating system, allowing developers to perform various system-related tasks. Here are the key points about the "os" module
• Install os library using pip command

pip command os        

Pyautogui

• The?pyautogui?library is a Python module for automating GUI interactions, such as mouse movements, clicks, and keyboard inputs.
• Install pyautogui library using pip command

pip install pyautogui        

Time

• The?time?library is a Python standard library module for working with time-related functions and operations.
• Install time library using pip command

pip install time        

Pysttx3

• The?pyttsx3?library is a Python text-to-speech (TTS) conversion module.
• Install pysstx3 library using pip command

pip install pysstx3        

Datetime

• The?datetime?library is a Python standard library module for working with dates, times, and time intervals.
• Install datetime library using pip command

pip install DateTime        

Subprocess

• The?subprocess?library is a Python standard library module for creating and managing additional processes.
• Install subprocess library using pip command

pip install subprocess.run        

Self Build Voice Assistant Python code

import speech_recognition as s
import pywhatkit
import pyautogui
import os
import subprocess
import datetime
import time
import pyttsx3


recognizer = sr.Recognizer()
with sr.Microphone() as source:
? ? print("Adjusting noise ")
? ? recognizer.adjust_for_ambient_noise(source, duration=1)
? ? print("listening....")
? ? recorded_audio = recognizer.listen(source, timeout=5)
? ? print("Done recording")
try:
? ? print("Recognizing the text")
? ? text = recognizer.recognize_google(
? ? ? ? ? ? recorded_audio,?
? ? ? ? ? ? language="en-US"
? ? ? ? )
? ? print("Decoded Text : {}".format(text))
? ? #pint(text)
except Exception as ex:
? ? print(ex)
? ??
text = text.lower()
if 'open notepad' in text:
? ? os.system("notepad")
? ? print("Done")
? ??
elif 'open chrome' in text:
? ? os.system("chrome")
? ? print("Done")
? ??
elif 'youtube' in text:
? ? song = text.replace('song', '')
? ? pywhatkit.playonyt(song)
? ? ? ??
elif 'turn off wifi' in text:
? ? mywish=subprocess.run (['netsh', 'interface', 'set', 'interface', "Wi-Fi", "admin=disable"])
? ? mywish
? ??
elif 'time' in text:
? ? time = datetime.datetime.now().strftime('%I:%M %p')
? ? engine=pyttsx3.init()
? ? engine.say('Current time is ' + time)
? ? engine.runAndWait()
? ? ? ??
elif 'open camera' in text:
? ? os.system("start microsoft.windows.camera:")
? ??
elif 'shutdown' in text:
? ? os.system("shutdown -s")
? ??
elif 'open spotify' in text:
? ? os.system("spotify")
? ? time.sleep(2)
? ? pyautogui.hotkey('ctrl','l')
? ? pyautogui.write('ya habibi',interval=0.1)
? ? for key in ['enter','pagedown','tab','enter','enter']:
? ? ? ? time.sleep(2)
? ? ? ? pyautogui.press(key)
? ? ? ??
elif 'do whatsapp'in text:
? ? engine=pyttsx3.init()
? ? engine.say("Tell me phone No")
? ? engine.runAndWait()
? ? number=input("Number please:")
? ? engine.say("Write your Messege here:")
? ? engine.runAndWait()
? ? messege=input("Messege:")
? ? pywhatkit.sendwhatmsg_instantly(number,messege)
? ? engine.say("Done")
? ? engine.runAndWait()
? ??
elif 'make folder' in text:
? ? folder_name=input()
? ? os.mkdir(folder_name)
? ??
elif 'remove folder' in text:
? ? folder_name=input()
? ? os.rmdir(folder_name)        

Conclusion

The code showcases the potential of voice technology and automation in Python, merging?speech_recognition,?pywhatkit,?pyautogui, and other modules for voice-controlled interactions and task automation.

Thanks for reading???