What is a Voice Assistant?

A voice assistant or intelligent personal assistant is a software agent that can perform tasks or services for an individual based on verbal commands i.e. by interpreting human speech and respond via synthesized voices. Users can ask their assistants’ questions, control home automation devices, and media playback via voice, and manage other basic tasks such as email, to-do lists, open or close any application etc with verbal commands.

Let me give you the example of Braina (Brain Artificial) which is an intelligent personal assistant, human language interface, automation and voice recognition software for Windows PC. Braina is a multi-functional AI software that allows you to interact with your computer using voice commands in most of the languages of the world. Braina also allows you to accurately convert speech to text in over 100 different languages of the world.

Recognize spoken voice

Speech recognition can by done using the Python SpeechRecognition module. We make use of the Google Speech API because of it’s great quality.

Answer in spoken voice (Text To Speech)

Various APIs and programs are available for text to speech applications. Espeak and pyttsx work out of the box but sound very robotic.

Dependencies and requirements :

Install all these python libraries :

pip install SpeechRecognition

pip install beautifulsoup4

pip install python-vlc

pip install youtube-dl

pip install pyowm

pip install wikipedia

Let’s start building our desktop voice assistant using python

Start by importing all the required libraries :

import speech_recognition as sr

import os

import sys

import re

import webbrowser

import smtplib

import requests

import subprocess

from pyowm import OWM

import youtube_dl

import vlc

import urllib

import urllib2

import json

from bs4 import BeautifulSoup as soup

from urllib2 import urlopen

import wikipedia

import random

from time import strftime

For our voice-assistant to perform all the above-discussed features, we have to code the logic of each of them in one method.

So our first step is to create the method which will interpret user voice response.

def myCommand():

    r = sr.Recognizer()

    with sr.Microphone() as source:

        print('Say something...')

        r.pause_threshold = 1

        r.adjust_for_ambient_noise(source, duration=1)

        audio = r.listen(source)

    try:

        command = r.recognize_google(audio).lower()

        print('You said: ' + command + '\n')

    #loop back to continue to listen for commands if unrecognizable speech is received

    except sr.UnknownValueError:

        print('....')

        command = myCommand();

    return command