In this project, I have used certain python libraries to create my personal voice assisant named 'AYAKA'. Ayaka can inform about its origin, reason to build. Moreover she can open google, youtube, Play music, crack jokes in real-time.
What is a Voice Assistant? A voice assistant is a digital assistant that uses speech recognition technology to interpret and respond to voice commands. Python is a popular programming language that can be used to create voice assistants.
In this article, we will discuss how to create a voice assistant using Python.
**COMPONENTS USED IN THIS PROJECT**
(A) Laptop
A laptop is a portable computer that is designed for use on the go. It typically features a thin, lightweight design and a built-in display, keyboard, and touchpad or trackpad for input. Laptops are powered by batteries and can be used for several hours without needing to be plugged into an outlet.
(B) In-built or external mic
An in-built mic, also known as an integrated microphone, is a microphone that is built into a device such as a laptop, smartphone, or tablet. In-built microphones are used for recording sound or capturing voice input without the need for an external microphone.
(C) ISE to run the Program
ISE stands for Integrated Software Environment. It refers to a software application that provides a comprehensive set of tools and functionalities for designing, developing, testing, and deploying software systems or applications.
(D) Active Internet connection
An active internet connection refers to a connection between a device and the internet that is currently operational and able to transmit and receive data. It means that the device is currently connected to the internet and can access online services such as websites, email, cloud storage, and other internet-based applications.
**DEPENDENCIES INSTALLED**
-
To Install Pip
sudo apt-get install python-pip // for python2 sudo apt-get install python3-pip // for python3 -
To Install Python3
sudo apt-get install python3 // python2 is installed Bydefault -
To Update/Upgrade packages
sudo apt-get update // upgrade the packages sudo apt-get upgrade -
To install pyttsx3
pip install pyttsx3 // conversion of text to speech in a program -
To install speech recognition
pip install SpeechRecognition // To recognizes your voice -
To install datetime
pip install DateTime // To show Date & Time -
To install wikipedia
pip install wikipedia // To perform a Wikipedia search -
To install webbrowser
python -m pip install webbrowser // To perform Web Search -
To install pyjokes
pip install pyjokes // Collection of Python Jokes over the Internet -
To install winshell
pip install winshell // for accessing special folders, etc... -
To install ecapture
pip install ecapture // To capture the Pic -
To install os
pip install os_sys // To interact with OS pip install --upgrade os_sys // OPERATING SYSTEM
The Explanation of the program is as follows:
At the beginning, we imported all the necessary python libraries used in this project. The dependencies can be installed by following the above stated Pip command. Subprocess module comes in-built with python so there is no need to be worry about its installing.
Presently we will set our program to Pyttsx3 which is utilized for text to speech in Python and sapi5 is a Microsoft discourse application platform interface that we will involve in our program. We can also change the female voice to male voice as ( voices[0].id ), but for best results follow my program...
The main function starts from here, now we will call each & every def function defined in the above code snippet in the main function as follows.
**THE FINAL PROJECT**