F.R.I.D.A.

Y
Voice Assistant integrated with chatbot

Presented by:
C K Ananya
Chandana A S
Jeevitha K V
Sinchana C D
ABSTRACT
Voice assistants are software agents that can interpret human speech and respond via
synthesized voices. Apple’s Siri, Amazon’s Alexa, Microsoft’s Cortana, and Google’s
Assistant are the most popular voice assistants and are embedded in smartphones or
dedicated home speakers. 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, and calendars with verbal commands. This column will explore the basic workings and
common features of today’s voice assistants. It will also discuss some of the privacy and
security issues inherent to voice assistants and some potential future uses for these devices.
As voice assistants become more widely used, librarians will want to be familiar with their
operation and perhaps consider them as a means to deliver library services and materials
Introduction
AI-Powered Virtual Assistant : A virtual assistant is a software
application powered by artificial intelligence that can understand
voice commands, process language, and provide helpful
responses through audio output. Advanced Technologies : The
virtual assistant combines several cutting-edge technologies,
including voice recognition, natural language processing, and
text-to speech, to create an intelligent and interactive user
experience. Developed in Python: This virtual assistant is
entirely developed using the powerful and versatile Python
programming language, leveraging its robust libraries and tools
for artificial intelligence and natural language processing.
 VIRTUAL CONTROL REQUIREMENTS

• Speech recognition: Utilize the Speech Recognition library to enable voice input and
commands from the user.($pip install SpeechRecognition, $pip install PyAudio )
• Text-to-Speech: Leverage the Pyttsx3 library to provide audible responses and feedback to
the user.($pip install pyttsx3)
• Knowledge Retrieval: Integrate the Wikipedia library to allow the assistant to access
information and answer user queries.($pip install Wikipedia)
• Web Scraping: Employ the Requests library to enable web scraping capabilities for
gathering additional information.($pip install requests)
 IMPLEMENTATION
• Online Speech Recognition : The application is able to recognize the voice from the user end
with internet connection. The verbal commands are converted to text and the operations take
place.
• Content Opener : The application is able to open files, folders, drives, documents present in
the system.
• Search : The application is able to search YouTube videos, songs, Wikipedia, google for any
information in the internet.
• Update: The application gives updates regarding the date, time, day, weather, humidity,

temperature.
FlowChart
Advantages:
• Easily configured to perform many of regular tasks by simply giving voice commands
• Voice based search that is a boon for many like senios citizens who are not comfortable using the
keypad.
• Able to write the text through both keyboard and voice input.
• Requires less consumption of time in writing text.
• Open different windows softwares , based on voice input
Disadvantages:
• Noisy Environments: The personal assistant may not perform well in noisy surroundings, as it can
struggle to accurately pick up and interpret the user's voice commands.
• Precise Speech Required: Users may need to speak louder and more slowly than normal for the system
to properly understand their instructions, which can be inconvenient.
• Low Accuracy: The personal assistant's speech recognition capabilities may not be 100% accurate,
leading to misinterpreted commands and frustrating the user experience.
REFERENCE:

• https://youtu.be/NpPBBKXraP0?si=fgb36_ELst7oO5Xx
• https://github.com/Dhruv58/Jarvis-AI
• https://youtu.be/c1EeSl2i5mg?si=TfjbYL1VAfJXwvf5