UNIVERSITY INSTITUTE OF TECHNOLOGY

BARKATULLAH UNIVERSITY, BHOPAL

Department of Computer Science & Engineering
A
MINOR PROJECT
ON
VOICE ASSISTANT USING PYTHON
Submitted for the partial fulfillment of the Requirement for the

Award of Degree of Bachelor of Engineering (B.Tech.) year

2025

Barkatullah University, Bhopal

SUBMITTED BY

Nikhil Waghade

Under the Guidance

Of

Ms. Jagriti Chand Dr. Kamini Maheshwar

Co-Guide Guide
CSE,UIT-BU, BHOPAL CSE,UIT-BU, BHOPAL

Dr. Divakar Singh Prof. N.K. Gaur

HOD Director
CSE,UIT-BU, BHOPAL UIT-BU, BHOPAL
 UNIVERSITY INSTITUTE OF TECHNOLOGY
BARKATULLAH UNIVERSITY, BHOPAL
Department of Computer Science & Engineering

MINOR PROJECT

ON

VOICE ASSISTANT USING PYTHON

Submitted for the partial fulfillment of the Requirement for the

Award of Degree of

Bachelor of Engineering

(B.Tech.) Year 2025

Barkatullah university, Bhopal

By
Uttam Singh Nikhil Waghade Amit Hariyale

Under the Guidance of

Ms. Jagriti Chand Dr. Kamini Maheshwar

Co-Guide Guide
CSE,UIT-BU, BHOPAL CSE,UIT-BU, BHOPAL

Dr. Divakar Singh Prof. N.K. Gaur

HOD Director
CSE, UIT-BU, BHOPAL UIT-BU, BHOPAL
I
 CONTENTS
ABSTRACT....................................................................................................... I

List of Figures....................................................................................................II
List of Abbreviations.........................................................................................III

CHAPTER 1: INTRODUCTION................................................................... 01

Purpose / Objective..........................................................................................................03
Existing System 04
Scope and Applicability..................................................................................................07
Feasibility Report............................................................................................................08

CHAPTER 2: SOFTWARE SPECIFICATION............................................ 09

Python 10
Dbpedia 12
Quepy 12
Pyttsx 13
Speech Recognition.......................................................................................................14

CHAPTER 3: REQUIREMENT AND ANALYSIS....................................... 15

Problem Definition............................................................................................................16
Requirement Specification................................................................................................16
Software and Hardware Requirement...............................................................................17

CHAPTER 4: PROJECT DESCRIPTION..................................................... 18

Data Flow Diagram..........................................................................................................19

ER Diagram 20
Flow Chart 21
Sequence Diagram............................................................................................................22

CHAPTER 5: CODING.................................................................................... 24

Main Source Code : Voice-Controlled AI assistant...........................................................25

Code For Send a WhatsApp message................................................................................40

III
CHAPTER 6: TESTING................................................................................... 44

Automation Testing..........................................................................................................45
Usability Testing 46
Load Testing 47
Cross-platform Testing......................................................................................................48
Conformation Testing........................................................................................................49
Quality Assurance Testing.................................................................................................50

CHAPTER 7: OUTPUT DESCRIPTION........................................................ 51

Fig 7.1 : Query : Write Anything.......................................................................................52
Fig 7.2 : Query : Youtube Search......................................................................................53
Fig 7.3 : Query : Activation...............................................................................................54
Fig 7.4 : Query : Open Notepad.........................................................................................55
Fig 7.5 : Query : Youtube Search.......................................................................................56
Fig 7.6 : Query : Take A Screenshot..................................................................................57
Fig 7.7 : Query : Google Map On Set................................................................................58
Fig 7.8 : Query : Find My Location...................................................................................59
Fig 7.9 : Query : Google Search Wikipedia.......................................................................60
Fig 7.10 : Query : Send Whatsapp Message.......................................................................61

CHAPTER 8: SPECIFICATIONS.................................................................... 62
Advantages 63
Disadvantages 63
Future Scope 63
Conclusion 64REFERENCES...................................................................................65
 CHAPTER 1
INTRODUCTION

1
INTRODUCTION

2
3
having to do the research ourselves. Moreover, personal assistants can remind us of important dates such as test
dates, birthdates or anniversaries, making sure that we are well-prepared in advance. Voice searches are also
known to be four times faster than written searches. This means that we can speak around 150 words per mi-
nute, while we can only write about 40 words per minute. Therefore, the ability of personal assistants to accu-
rately recognize spoken words is crucial for them to be adopted by consumers.
One of the most popular personal assistants available today is Siri, which is available on
Apple devices. Siri is a voice-activated assistant that can perform a range of tasks such as calling someone from
your contact list, launching an application on your iPhone, sending a text message to someone, setting up a
meeting on your calendar, setting an alarm, playing a specific song in your iTunes library, and entering a new
note. However, one of the drawbacks of Siri is that it does not maintain a knowledge database of its own and
understanding comes from the information captured in domain models and data models.
In conclusion, personal assistant software is a valuable tool that can help us save time
and increase efficiency in our daily lives. By using semantic data sources available on the web and user-
generated content, personal assistants can provide quick and accurate answers to our queries.

EXISTING SYSTEM
There already exists a number of desktop virtual assistants. A few examples of current virtual assistants availa-
ble in market are discussed in the section along with the tasks they can provide and their drawbacks.

SIRI FROM APPLE

SIRI is personal assistant software that interfaces with the user through voice interface, recognizes commands
and acts on them. It learns to adapt to user’s speech and thus improves voice recognition over time. It also tries
to converse with the user when it does not identify the user request.
It integrates with calendar, contacts and music library applications on the device and also integrates
with GPS and camera on the device. It uses location, temporal, social and task based contexts, to personalize the
agent behavior specifically to the user at a given point of time

SUPPORTED TASKS

 Call someone from my contacts list.

 Launch an application on my IPhone.
 Send a text message to someone.
 Set up a meeting on my calendar for 9AM tomorrow.
 Set an alarm for 5AM tomorrow morning.
 Play a specific song in my iTunes Library.

4
DRAWBACKS
SIRI does not maintain a knowledge database of its own and understanding comes from the information cap-
tured in domain models and data models.

ALEXA FROM AMAZON

Alexa is a virtual assistant developed by Amazon for its line of Echo devices. It can also be accessed through
the Alexa app on mobile devices. Alexa uses natural language processing to understand and respond to user re-
quests. It can provide a wide range of services, such as setting reminders, playing music, and providing news
and weather updates.

SUPPORTED TASKS
 Play a specific song or playlist on Spotify or Amazon Music.
 Tell a joke or provide a trivia question.
 Order items from Amazon or other online retailers.
 Control smart home devices, such as lights and thermostats.
 Set reminders and alarms.
 Answer general knowledge questions.
 Provide news and weather updates.

DRAWBACKS
Alexa has been criticized for privacy concerns, as it is always listening for its wake word and may record and
store user conversations. It also has limitations in its ability to handle complex tasks and may sometimes misin-
terpret user requests.

GOOGLE ASSISTANT
Google Assistant is a virtual assistant developed by Google and is available on mobile devices and smart home
devices. It uses natural language processing to understand and respond to user requests. It also integrates with
other Google services, such as Google Calendar and Google Maps.

SUPPORTED TASKS

 Play music or video from a variety of streaming services.

 Answer general knowledge questions.
 Set reminders and alarms.
 Provide news and weather updates.
 Make phone calls and send text messages.

5
DRAWBACKS

Google Assistant may struggle with understanding regional accents and dialects. It also has limitations in its
ability to handle complex tasks and may sometimes provide incorrect or irrelevant information.

CORTANA FROM MICROSOFT

Cortana is a virtual assistant developed by Microsoft and is available on Windows 10 devices and mobile devic-
es. It uses natural language processing to understand and respond to user requests. It can also integrate with oth-
er Microsoft services, such as Microsoft Office and Microsoft Edge.

SUPPORTED TASKS

 Open an application on Windows 10.

 Set reminders and alarms.
 Answer general knowledge questions.
 Provide news and weather updates.
 Control smart home devices.
 Make phone calls and send text messages.

DRAWBACKS
Cortana has been criticized for its limited functionality compared to other virtual assistants. It also struggles
with understanding certain accents and dialects. Additionally, Microsoft has announced that it will be ending
support for Cortana on mobile devices in early 2021.

REQALL
ReQall is Personal assistant software that runs on smartphones running apple iOS or Google Android operating
system. It helps user to recall notes as well as tasks within a location and time context. It records user inputs and
converts them into commands, and monitors current stack of user tasks to proactively suggest actions while
considering any changes in the environment. It also performs information based on the context of the user, as
well as filter information to the user based on its learned understanding of the priority of that information.

6
SUPPORTED TASKS

 . Reminders
 . Email
 . Calendar, Google Calendar
 . Outlook
 . Notepad
 . Facebook , Linkedin
 . News Feeds
 . Music play
 . YouTube video controller

DRAWBACK
Will take some time to put all of the to-do-items in – you could spend more time putting the entries in than ac-
tually doing the revision.

SCOPE AND APPLICABILITY

SCOPE
Voice assistants will continue to offer more individualized experiences as they get better at differentiating be-
tween voices. However, it’s not just developers that need to address the complexity of developing for voice as
brands also need to understand the capabilities of each device and integration if it makes sense for their specific
brand. They will also need to focus on maintaining a user experience that is consistent within the coming years
as complexity becomes more of a concern. This is because the visual interface with voice assistants is missing.
Users simply cannot see or touch a voice interface.

APPLICABILITY
The mass adoption of artificial intelligence in users’ everyday lives is also fueling the shift towards voice. The
number of IoT devices such as smart thermostats and speakers are giving voice assistants more utility in a con-
nected user’s life. Smart speakers are the number one way we are seeing voice being used. Many industry ex-
perts will integrate voice technology in some way in the next 5 years.
The use of virtua

7
 assistants can also enhance the system of IoT(Internet of Things). Twenty years from now, Microsoft
and its competitors will be offering digital assistants that will offer the services of a full- time employee usually
reserved for the rich and famous.

8
 FEASIBILITY STUDY
Feasibility study can help you determine whether or not you should proceed with your project. It is essential to
evaluate cost and benefit. It is essential to evaluate cost and benefit of the proposed system. Five types of feasi-
bility study are taken into consideration.

1. Technical feasibility: It includes finding out technologies for the project, both hardware and soft-
ware. For virtual assistant, user must have microphone to convey their message and speaker to listen
when system speaks. Besides, system needs internet connection. While using hii, make sure you have a
steady internet connection. It is also not an issue in this era where almost every home or office has Wi-
Fi.

2. Operational Feasibility: It is the ease and simplicity of operation of proposed system. System do
not require any special skill for users to operate it. In fact, it is designed to be used by almost everyone.
Kids who still don’t know how to write can read out problems for systems and get answers.

3. Economical Feasibility: Here, we find the total cost and benefit of the proposed system over cur-
rent system. For this project, the main cost is documentation cost. User also would have to pay for mi-
crophone and speakers. Again, they are cheap and available. As far as maintenance is concerned, hii
won’t cost too much.

4. Organizational Feasibility: This shows the management and organizational structure of the pro-
ject. This project is not built by a team. The management tasks are all to be carried out by a single per-
son. They won’t create any management issues and will increase the feasibility of the project.

5. Cultural feasibility: It deals with compatibility of the project with cultural environment. Virtual as-
sistant is built in accordance with the general culture. The project is named JIA so as to represent Indian
culture without undermining local beliefs. This project is technically feasible with no external hardware
requirements. Also it is simple in operation and does not cost training or repairs. Overall feasibility
study of the project reveals that the goals of the proposed system are achievable. Decision is taken to
proceed with the project.

9
 CHAPTER- 2

SOFTWARE SPECIFICATION

1
0
 PYTHON

Python is a OOPs(Object Oriented Programming) Based, high level, interpreted programming language. It is a
robust, highly useful language focused on rapid application development. Python helps in easy writing and exe-
cution of codes. Python can implement the same logic with as much as 1/5 th code as compared to other OOPs
languages.
Python is an interpreted, object-oriented, high-level programming language with dynamic semantics.
Its high-level built in data structures, combined with dynamic typing and dynamic binding, make it very attrac-
tive for Rapid Application Development, as well as for use as a scripting or glue language to connect existing
components together. Python's simple, easy to learn syntax emphasizes readability and therefore reduces the
cost of program maintenance. Python supports modules and packages, which encourages program modularity
and code reuse. The Python interpreter and the extensive standard library are available in source or binary form
without charge for all major platforms, and can be freely distributed.
Often, programmers fall in love with Python because of the increased productivity it provides. Since
there is no compilation step, the edit-test-debug cycle is incredibly fast. Debugging Python programs is easy: a
bug or bad input will never cause a segmentation fault. Instead, when the interpreter discovers an error, it raises
an exception. When the program doesn't catch the exception, the interpreter prints a stack trace. A source level
debugger allows inspection of local and global variables, evaluation of arbitrary expressions, setting break-
points, stepping through the code a line at a time, and so on. The debugger is written in Python itself, testifying
to Python's introspective power. On the other hand, often the quickest way to debug a program is to add a few
print statements to the source: the fast edit-test-debug cycle makes this simple approach very effective.
Python is a highly versatile language, and can be used in a variety of applications. It is commonly
used in scientific computing, data analysis, artificial intelligence, and web development. Python is known for its
simplicity, which allows developers to focus on solving problems rather than getting bogged down in the com-
plexities of language syntax. This ease of use has made Python a popular choice for beginner programmers, as
well as for seasoned developers looking to quickly develop applications.
One of the key advantages of Python is its extensive standard library, which includes modules for a wide range
of tasks, such as network programming, file I/O, and regular expressions. This makes it possible to develop

11
complex applications with a minimal amount of code, and enables developers to quickly prototype and test new
ideas.
Python is also highly portable, and can run on a variety of platforms, including Windows, Linux, and
MacOS. This makes it an ideal choice for developing cross-platform applications that can run on a variety of
devices.
Another advantage of Python is its strong community support. There are numerous online resources
available for learning and troubleshooting Python, including documentation, forums, and user groups. Addition-
ally, there are many third-party libraries available that can extend the functionality of Python and make it even
more useful for specific applications.

Here are some additional points about Python:

1. Cross-Platform Compatibility: Python is a cross-platform language, which means that you can write code
on one platform, such as Windows, and run it on another, such as Linux, without having to make any changes to
the code. This makes Python an ideal choice for developing applications that need to run on multiple platforms.

2. Large and Active Community: Python has a large and active community of developers and users, who con-
tribute to the development of the language and the creation of libraries and frameworks. This means that there is
a wealth of resources available for developers who are using Python, including documentation, tutorials, and
support forums.

3. Scalability: Python is a highly scalable language, which means that it can be used to develop applications of
any size, from small scripts to large enterprise-level applications. Python's scalability is due in part to its support
for concurrency, which allows multiple threads of execution to run concurrently within a single process.

4. Libraries and Frameworks: Python has a rich collection of libraries and frameworks that make it easy to
perform complex tasks such as web development, scientific computing, and data analysis. Some popular Python
libraries and frameworks include Django, Flask, NumPy, and Pandas.

5. Easy to Learn and Use: Python has a simple and easy-to-learn syntax that makes it an ideal language for
beginners. The language is designed to be intuitive and easy to use, which means that developers can quickly
start writing useful code without having to spend a lot of time learning the language.

10
 DBPEDIA
Knowledge bases are playing an increasingly important role in enhancing the intelligence of Web and enterprise
search and in supporting information integration. The DBpedia leverages the gigantic source of knowledge by
extracting structured information from Wikipedia and by making the information accessible on the web. The
DBpedia knowledge has its several advantages over existing knowledge base; it covers many domains; it repre-
sents real community agreement; it automatically evolves as Wikipedia changes, and it is truly multilingual.
The DBpedia knowledge base allows you to ask quite surprising queries against Wikipedia for instance
“Give me all cities in New Jersey with more than 10,000 inhabitants” or “Give me all Italian musicians from the
18th century”.

QUEPY
Python has a large and active user community, which has developed a wide range of libraries and tools that ex-
tend the language's functionality. This makes Python a versatile language that can be used for various tasks such
as web development, scientific computing, data analysis, artificial intelligence, and more.
Python's syntax is designed to be simple and readable, which makes it easy for beginners to learn. The lan-
guage's minimalistic approach to coding makes it an ideal choice for prototyping and rapid application devel-
opment.
Another significant advantage of Python is its cross-platform compatibility. Python code can run on
various platforms such as Windows, macOS, Linux, and Unix, making it a popular choice for developers who
need to create applications that work on multiple operating systems.
Python's dynamic typing feature allows developers to write code quickly and efficiently, without wor-
rying about variable types. This makes the language very flexible and easy to use. Additionally, Python's built-
in garbage collection feature frees developers from managing memory, which reduces the risk of memory leaks
and other related issues.
Python also supports multiple programming paradigms, including object-oriented, functional, and pro-
cedural programming. This makes it a versatile language that can be used for various programming styles and
purposes.
In summary, Python is a versatile, easy-to-learn, and widely-used programming language that can be
used for various applications. Its simplicity, readability, and cross-platform compatibility make it an ideal
choice for beginners and experienced developers alike. Additionally, its large and active user community has
developed a vast range of libraries and tools that can extend its functionality, making Python an excellent
choice for many programming projects.

12
 PYTTSX
Pyttsx is a cross-platform, open-source text-to-speech library for Python programming language. It allows de-
velopers to easily integrate speech synthesis capabilities into their Python applications. Pyttsx is built on top of
the platform-specific speech synthesis engines, which are commonly found in modern operating systems such
as Windows, Mac, and Linux.
One of the key features of Pyttsx is its ability to work with a variety of speech synthesis engines.
This allows developers to choose the best engine for their specific needs, whether it be Microsoft Speech API,
Apple Speech Synthesis, or the built-in text-to-speech engine that comes with Linux. By abstracting away the
differences between these engines, Pyttsx makes it easy for developers to write cross-platform text-to-speech
applications.
Pyttsx is also very easy to use. It provides a simple, high-level API for synthesizing speech from
text. Developers can simply create a pyttsx object, set the desired properties such as the voice and rate, and then
call the say() method to synthesize speech. This simplicity makes it easy for even novice Python developers to
quickly add speech synthesis capabilities to their applications.
Another advantage of Pyttsx is its support for events. Developers can register event
handlers for various events such as the start of speech synthesis, the completion of speech synthesis, and errors
that may occur during synthesis. This allows developers to create more responsive and interactive applications
that can react to changes in the speech synthesis process.
Pyttsx is a powerful and easy-to-use text-to-speech library for Python. Its support
for multiple speech synthesis engines and events makes it a versatile tool for developers looking to add speech
synthesis capabilities to their applications. With its open-source license and active development community,
Pyttsx is sure to remain a popular choice for text-to-speech applications in the years to come.

13
 SPEECH RECOGNITION
Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that de-
velops methodologies and technologies that enable the recognition and translation of spoken language into text
by computers with the main benefit of search ability. It is also known as automatic speech recognition (ASR),
computer speech recognition or speech to text (STT). It incorporates knowledge and research in the computer
science, linguistics and computer engineering fields. The reverse process is speech synthesis.

Some speech recognition systems require "training" (also called "enrollment") where an
individual speaker reads text or isolated vocabulary into the system. The system analyzes the person's specific
voice and uses it to fine-tune the recognition of that person's speech, resulting in increased accuracy. Systems
that do not use training are called "speaker-independent" systems. Systems that use training are called "speaker
depend- ent".
Speech recognition applications include voice user interfaces such as voice dialing (e.g. "call home"),
call routing (e.g. "I would like to make a collect call"), domotic appliance control, search key words (e.g. find a
podcast where particular words were spoken), simple data entry (e.g., entering a credit card number), prepara-
tion of structured documents (e.g. a radiology report), determining speaker characteristics, speech-to-text pro-
cessing (e.g., word processors or emails), and aircraft (usually termed direct voice input).

The term voice recognition or speaker identification refers to identifying the speaker, rather than
what they are saying. Recognizing the speaker can simplify the task of translating speech in systems that have
been trained on a specific person's voice or it can be used to authenticate or verify the identity of a speaker as
part of a security process. This is a library for performing speech recognition, with support for several engines
and APIs, online and offline. It supports APIs like Google Cloud Speech API, IBM Speech to Text, Microsoft
Voice Bing Voice Recognition etc.

14
 CHAPTER- 3

REQUIREMENT AND ANALYSIS

15
System Analysis is about complete understanding of existing systems and finding where the existing system
fails. The solution is determined to resolve issues in the proposed system. It defines the system. The system is
divided into smaller parts. Their functions and inter relations of these modules are studied in system analysis.
The complete analysis is followed below:

PROBLEM DEFINITION
Usually, user needs to manually manage multiple sets of applications to complete one task. For example, a user
trying to make a travel plan needs to check for airport codes for nearby airports and then check travel sites for
tickets between combinations of airports to reach the destination. There is a need of a system that can manage
tasks effortlessly.

We already have multiple virtual assistants. But we hardly use it. There are number of people who
have issues in voice recognition. These systems can understand English phrases but they fail to recognize in our
accent. Our way of pronunciation is way distinct from theirs. Also, they are easy to use on mobile devices than
desktop systems. There is need of a virtual assistant that can understand English in Indian accent and work on
desktop system. When a virtual assistant is not able to answer questions accurately, it’s because it lacks the
proper context or doesn’t understand the intent of the question. Its ability to answer questions relevantly only
happens with rigorous optimization, involving both humans and machine learning. Continuously ensuring solid
quality control strategies will also help manage the risk of the virtual assistant learning undesired bad behaviors.
They require large amount of information to be fed in order for it to work efficiently. Virtual assistant should be
able to model complex task dependencies and use these models to recommend optimized plans for the user. It
needs to be tested for finding optimum paths when a task has multiple sub-tasks and each sub-task can have its
own sub-tasks. In such a case there can be multiple solutions to paths, and the it should be able to consider user
preferences, other active tasks, priorities in order to recommend a particular plan.

REQUIREMENT SPECIFICATION
Personal assistant software is required to act as an interface into the digital world by understanding user re-
quests or commands and then training into actions or recommendations based on agent’s understanding of the
world.
JIA focuses on relieving the user of entering text input and using voice as primary means of user input.
Agent then applies voice recognition algorithms to this input and records the input. It then use this input to call
one of the personal information management applications such as task list or calendar to record a new entry or
to search about it on search engines like Google, Bing or Yahoo etc. Focus is on capturing the user input
through voice, recognizing the input and then executing the tasks if the agent understands the task. Software
takes this input in natural language, and so makes it easier for the user to input what he or she desires to be
done.
16
Voice recognition software enables hands free use of the applications, lets users to query or command the agent
through voice interface. This helps users to have access to the agent while performing other tasks and thus en-
hances value of the system itself. JIA also have ubiquitous connectivity through Wi-Fi or LAN connection, ena-
bling distributed applications that can leverage other APIs exposed on the web without a need to store them lo-
cally.

Virtual assistants can provide a wide variety of services. These include

 .Providing information such as weather, facts from e.g. Wikipedia etc.

 Set an alarm or make to-do lists and shopping lists.
 Play music from streaming services such as Saavn and Gaana.
 Play videos, TV shows or movies or televisions, streaming from e.g. Netflix of Hotstar.
 Play videos, TV shows or movies on televisions, streaming from e.g. Netflix or Hotstar
 Book tickets for shows, travel and movies

HARDWARE AND SOFTWARE REQUIREMENTS

The software is designed to be light-weighted so that it doesn’t be a burden on the machine running it. This sys-
tem is being build keeping in mind the generally available hardware and software compatibility. Here are the
minimum hardware and software requirements for virtual assistant.

HARDWARE :

 Pentium-pro processor or later.

 RAM 512MB or more.

SOFTWARE :

 Windows 7(32-bit) or above.

 Python 2.7 or later.
 .Chrome Driver
 .Selenium Web Automation

17
 CHAPTER- 4

PROJECT DESCRIPTION

18
 DATA FLOW DIAGRAM

Fig 4.1.1

DESCRIPTION : The proposed model of the voice assistant is as shown in the above figure 1. The model con-
sists of user input through microphone to accept commands from the user. These commands are then go through
Speech Recognition, it is the ability of a machine or program to identify words and phrases in spoken languages
and convert them to a machine-readable format. On these input Natural Language Processing is applied, it is a
field which is created by amalgamating computer science and artificial intelligence. Using NLP, we are con-
cerned with interactions between computers and human natural languages. Then the voice assistant check
whether it is a question or an action, if it is a action than the action is performed by the voice assistant and ac-
knowledgment is given to the user via a synthesis voice or if it is a question than it is search in dialog box or
knowledge base and then response via a synthesis voice to the user. Our Voice assistant uses google text-to-
speech API to understand all the words spoken by the user, and based on certain conditions that satisfy being a
command the voice assistant sends responses to the user.

19
 ER DIAGRAM

Fig 4.2.1

DESCRIPTION : The above diagram shows entities and their relationship for the virtual assistant system. We
have a user system who can have their keys and values. It can used to store any information about the user. Say
for key “name” value can be “uttam”. For some key’s user might like to keep secure. There he can enable lock
set a password (voice clip). Single user can ask multiple questions. Each question will be given ID to get recog-
nized along with the query and its corresponding answer. User can also be having n number of task. These
should have their own unique id and status i.e. their current state. A task should also have a priority value and
its category whether it is a parent task or child task of an older task.

20
 FLOW CHART

Fig 4.3.1
DESCRIPTION : Flow chart is the graphical representation of algorithms. Different symbols are used to repre-
sent flow chart. As the system is started, it first authenticate the authorized user, then voice assistant is on run-
ning in the background listening for available voice commands; once the user gives a command, based on the
conditions provided to the voice assistant, the voice assistant gives the necessary output. This output is sent to
the Speech Recognition which is convert the speech into machine-readable form. Based on the input received
the personal voice assistant then performs the desired task.
In this article, we’re going to cover the topic from the very basics: from what voice assistants are,
how they work and how they can be used.
Now that the machine knows what was said and (presumably) what your intention was, it can
search for a valid answer, and respond accordingly. The response is converted from written to spoken form us-
ing a text-to-speech (TTS) technology, and voila: your voice assistant speaks. All done in a matter of seconds.
Voice assistants can thus perform a variety of tasks including answering questions, making calls and sending
messages, playing your favourite music, setting up alarms and creating to-do lists, and much, much more.
Communicating with a voice assistant is so simple it almost makes us forget how impressive the technology be-
hind it actually is.

21
 SEQUENCE DIAGRAM

Fig 4.4.1

DESCRIPTION : A sequence diagram is a visual representation of the interactions between different compo-
nents or objects in a system. In the case of a voice assistant, a sequence diagram can illustrate the flow of events
and messages between the user, the voice assistant, and any other relevant entities. Here is a description of a
typical sequence diagram for a voice assistant:

1. User Interaction:
 The user initiates a voice command by speaking to the voice assistant.
 The voice command is captured by the device's microphone and passed to the voice assistant.
2. Speech-to-Text Conversion:
 The voice assistant utilizes a speech recognition component to convert the user's spoken command into
text.
 The speech recognition component processes the audio input and produces the corresponding text repre-
sentation of the command.
3. Natural Language Processing (NLP):
 The text command is sent to the NLP module, which interprets the user's intent and extracts relevant in-
formation from the command.

22
  The NLP module may use various techniques such as language models, entity recognition, and intent
classification to understand the user's request.
4. Action Determination:
 Based on the interpreted command and extracted information, the voice assistant determines the appro-
priate action or response.
 This could involve querying a database, accessing external APIs, or executing predefined functions.
5. Response Generation:
 The voice assistant generates a response or performs the requested action.
 This could involve retrieving information, providing an answer, performing a task, or interacting with
other services.
6. Text-to-Speech Conversion:
 If the response needs to be spoken, the text response is passed to a text-to-speech component.
 The text-to-speech component converts the response into an audio format.
7. Audio Output:
 The generated audio response is played back to the user through the device's speakers or other audio
output mechanism.
Throughout this sequence, there can be additional steps or interactions depending on the
specific functionality of the voice assistant. For example, authentication and user context management can be
incorporated to personalize responses and access user-specific data. Similarly, error handling and fallback
mechanisms may be included to handle cases where the command or request cannot be understood or fulfilled
properly. Please note that this description provides a high-level overview, and the actual sequence diagram can
vary depending on the implementation details and specific features of the voice assistant system.

23
CHAPTER- 5

CODING

24
25
 elif hour >= 12 and hour<18:
Speak("Good Afternoon!")

else:
Speak("Good Evening!")

def takecommand():
r = sr.Recognizer()
with sr.Microphone() as
source: print(" ")
print("Listening...")
r.pause_threshold = 1
audio = r.listen(source)

try:
print("Recognizing...")
query = r.recognize_google(audio, language='en-in')
print(f"Your Command : {query}\n")

except:
return "Uttam"

return query.lower()

def TaskExe():
Wishme()
Speak(" Please tell me your name
") name = takecommand()
Speak(f"Hello {name} ")
Speak("How May I Help You?")

26
def Music():
Speak("Tell Me The Name oF The
Song!") musicName = takecommand()
pywhatkit.playonyt(musicName)

27
28
 elif 'youtube' in query:
webbrowser.open('https://www.youtube.com')

Speak("Your Command Has Been Completed Sir!")

def CloseAPPS():
Speak(f"Ok {name} , Wait a second!")

if 'youtube' in query:
os.system("TASKKILL /F /im Chrome.exe")

elif 'chrome' in query:

os.system("TASKKILL /f /im Chrome.exe")

elif 'telegram' in query:

keyboard.press_and_release('alt+F4')

elif 'vs code' in query:

os.system("TASKKILL /F /im code.exe")

elif 'notepad' in query:

keyboard.press_and_release('alt+F4')

elif 'instagram' in query:

os.system("TASKKILL /F /im chrome.exe")

Speak("Your Command Has Been Succesfully Completed!")

def YoutubeAuto():
Speak("Whats Your Command ?")

29
 comm = takecommand()

if 'pause' in comm:
keyboard.press_and_release('space bar')

elif 'play' in comm:

keyboard.press_and_release('space bar')

elif 'next' in comm:

keyboard.press_and_release('shift+n')

elif 'mute' in comm:

keyboard.press_and_release('m')

elif 'forward' in comm:

keyboard.press_and_release('l')

elif 'back' in comm:

keyboard.press_and_release('j')

elif 'full screen' in comm:

keyboard.press_and_release('f')

elif 'film mode' in comm:

keyboard.press_and_release('t')

Speak(f"Done {name} ")

def ChromeAuto():
Speak("Chrome Automation started!")

30
 command = takecommand()

if 'close this tab' in command:

keyboard.press_and_release('ctrl + w')

elif 'open new tab' in command:

keyboard.press_and_release('ctrl + t')

elif 'open new window' in command:

keyboard.press_and_release('ctrl + n')

def screenshot():
Speak(f"Ok {name} , What Should I Name That File ?")
path = takecommand()
path1name = path + ".png"
path1 = "D:\\nothing\\screenshot\\"+ path1name
kk = pyautogui.screenshot()
kk.save(path1) os.startfile("D:\\nothing\\
screenshot\\") Speak("Here Is Your
ScreenShot")

while True:

query = takecommand()

if 'hello' in query:
Speak(f"Hello {name} , I Am Your Personal AI Assistant!")

elif 'how are you' in query:

31
 Speak(f"I Am Fine {name}
!") Speak("Whats About
YOU?")

elif 'switch off' in query:

Speak(f"Ok {name} , You Can Call Me Anytime !")

hour =int(datetime.datetime.now().hour)
if hour >= 0 and hour<12:
Speak("Good day sir!")

elif hour >= 12 and

hour<18: Speak("Good
day sir!")

else:
Speak("Good night sir !")

break

elif 'youtube tool' in

query: YoutubeAuto()

elif 'youtube search' in query:

Speak(f"OK {name} , This Is What I found For Your
Search!") query = query.replace("nothing","")
query = query.replace("youtube search","")
web = 'https://www.youtube.com/results?search_query=' + query
pywhatkit.playonyt(query)

32
elif 'launch' in query:
Speak("Tell Me The Name Of The Website!")

33
 site = takecommand()
web = 'https://www.' + site + '.com'
webbrowser.open(web)
Speak("Done Sir!")

elif 'wikipedia' in query:

Speak("Searching Wikipedia....")
query = query.replace("nothing","")
query = query.replace("wikipedia","")
wiki = wikipedia.summary(query,2)
Speak(f"According To Wikipedia : {wiki}")

elif 'screenshot' in
query: screenshot()

elif 'open jamboard' in

query: OpenApps()

elif 'open photos' in

query: OpenApps()

elif 'open classroom' in query:

OpenApps()

elif 'open drive' in

query: OpenApps()

elif 'open calendar' in query:

OpenApps()

34
elif 'open gmail' in
query: OpenApps()

elif 'meeting' in
query: OpenApps()

elif 'open translator' in query:

OpenApps()

elif 'open facebook' in

query: OpenApps()

elif 'open instagram' in query:

OpenApps()

elif 'open maps' in query:

OpenApps()

elif 'open vs code' in query:

OpenApps()

elif 'open notepad'in

query: OpenApps()

elif 'open madeeasy'in

query: OpenApps()

elif 'open youtube' in

query: OpenApps()

35
elif 'open telegram' in
query: OpenApps()

elif 'open chrome' in query:

OpenApps()

elif 'close chrome' in

query: CloseAPPS()

elif 'music' in
query: Music()

elif 'close telegram' in

query: CloseAPPS()

elif 'close instagram' in

query: CloseAPPS()

elif 'close vs code' in

query: CloseAPPS()

elif 'close notepad' in

query: CloseAPPS()

elif 'undo' in query:

keyboard.press_and_release('ctrl+ z')

elif 'select all' in query:

keyboard.press_and_release('ctrl+ a')

36
elif 'control' in query:
keyboard.press_and_release('ctrl+ v')

elif 'cut' in query:

keyboard.press_and_release('ctrl+ x')

elif 'copy' in query:

keyboard.press_and_release('ctrl+ c')
Speak("copied sir")

elif 'pause' in query:

keyboard.press_and_release('k')

elif 'play' in query:

keyboard.press_and_release('k')

elif 'next' in query:

keyboard.press_and_release('shift+n')

elif 'mute' in query:

keyboard.press_and_release('m')

elif 'restart' in query:

keyboard.press_and_release('0')

elif 'forward' in query:

keyboard.press_and_release('l')

elif 'back' in query:

keyboard.press_and_release('j')

37
elif 'full screen' in query:
keyboard.press_and_release('f')

elif 'new tab' in query:

keyboard.press_and_release('ctrl+ n')

elif 'film mode' in query:

keyboard.press_and_release('t')

elif 'close tab' in query:

keyboard.press_and_release('ctrl + w')

elif 'open new tab' in query:

keyboard.press_and_release('ctrl + t')

elif 'open new window' in query:

keyboard.press_and_release('ctrl + n')

elif 'chrome automation' in

query: ChromeAuto()

elif 'youtube automation' in

query: YoutubeAuto()

elif 'repeat my word' in query:

Speak("Speak Sir!")
jj = takecommand()
Speak(f"You Said : {jj}")

38
 elif ' location' in query:
Speak("Ok Sir , Wait A Second!")
webbrowser.open('https://www.google.com/maps/place/A-
Sec-
tor,+Gopal+Nagar,+Bhopal,+Madhya+Pradesh+462022/@23.2458573,77.4907322,17z/data=!3m1!4b1!4m5!3 m4!
1s0x397c41e828fb430d:0xa54fc1eccd8662f2!8m2!3d23.2459388!4d77.4927793')

elif 'alarm' in query:

Speak("Enter The Time !")
time = input(": Enter The Time :")

while True:
Time_Ac = datetime.datetime.now()
now = Time_Ac.strftime("%H:%M:%S")

if now == time:
Speak("Time To Wake Up
Sir!") Speak("Alarm Closed!")

elif now>time:
break

elif 'google search' in query:

import wikipedia as
googleScrap
query = query.replace("nothing","")
query = query.replace("google search","")
query = query.replace("google","")
Speak("This Is What I Found On The Web!")
pywhatkit.search(query)

39
try:

31
0
 result = googleScrap.summary(query,2)
Speak(result)

except:
Speak("No Speakable Data Available!")

elif 'time' in query:

strTime = datetime.datetime.now().strftime("%H:%M:%S")
Speak(f"sir , the time is {strTime}")

elif 'close it' in query:

keyboard.press_and_release('alt+F4')

elif 'home' in query: os.startfile('D:\\nothing\\

nothing.py')

elif 'type' in query:

query = query.replace("nothing","")
query = query.replace("please","")
query = query.replace("type","")
keyboard.write(query)

elif 'line' in query:

keyboard.press_and_release('enter')

elif 'save' in query:

keyboard.press_and_release('ctrl + s')

elif 'exit' in query:

keyboard.press_and_release('enter')

31
1
40
 com/send?phone=" + numb + "&text="+mess web.open(openChat)
time.sleep(10)
keyboard.write(mess)
time.sleep(1)
keyboard.press('enter')

def whatsapp_Grp(group_id,message):
openChat = "https://web.whatsapp.com/accept?code=" +
group_id web.open(openChat)

41
time.sleep(15)
keyboard.write(message)
time.sleep(10)
keyboard.press('enter')
le True:

query = takecommand()

if 'hello' in query:
Speak("hello sir ")

elif 'whatsapp message' in query:

query=query.replace("nothing","")
query=query.replace("send","")
query=query.replace("whatsapp message","")
query=query.replace("to","")

if 'Tushar' in
query:"9340033477"
Speak(f"what's the message for{query}")
mess = takecommand()
whatsapp(numb,mess)

elif 'Surendra' in query:

42
 numb = "6266993271"
Speak(f"what's the message for{query}")
mess = takecommand()
whatsapp(numb,mess)

elif 'umesh bhai' in

query: numb =
"9981176469"
Speak(f"what's the message for{query}")
mess = takecommand()
whatsapp(numb,mess)

elif 'family' in query:="EWlAjdrLV0H972ksLSIHKs" Speak(f"what's the message for {query}") mess =

takecommand() whatsapp_Grp(gro,mess)

elif 'stop message' in

query: Speak("ok sir")
break

Task()

43
44
 Quality Assurance Testing:
Quality Assurance (QA) testing is of utmost importance in voice assistant projects to ensure the accuracy, functionality,
and user satisfaction of the voice-driven software. A voice assistant project involves the development of a software ap-
plication capable of understanding and responding tocommands, providing users with a seamless and intuitive
experience.
QA testing in voice assistant projects encompasses several key aspects:
 Accuracy of Speech Recognition:
Speech recognition is a critical component of voice assistants. QA testing focuses on assessing the accuracy of
speech recognition algorithms to ensure that the voice assistant accurately understands and interprets user com-
mands across different languages, accents, and speech patterns. Testing involves a diverse range of spoken
commands and scenarios to verify the reliability and precision of the voice recognition system.
 Natural Language Understanding:
Voice assistants must possess robust natural language understanding (NLU) capabilities to comprehend user
queries and respond appropriately. QA testing involves verifying the voice assistant's ability to interpret user
intents accurately, extract relevant information, and generate appropriate responses. NLU testing includes eval-
uating the system's performance in understanding variations in user phrasing, handling ambiguous queries, and
providing relevant and context-aware responses.
 Functional Testing:
Functional testing in voice assistant projects focuses on verifying the correct implementation of various features
and functionalities. This includes testing specific voice commands, integration with external services and APIs,
handling of multimedia content, and ensuring smooth transitions between different application states. QA test-
ers validate that the voice assistant performs as expected and delivers the intended functionality consistently.
 Usability and User Experience:
QA testing places significant emphasis on evaluating the user experience of voice assistant applications. Testers
assess factors such as ease of use, intuitiveness, and responsiveness of the voice assistant's interactions. Usabil-
ity testing involves examining the system's ability to handle different user scenarios, adapt to user preferences,
and provide clear and concise instructions or prompts.
 Performance and Load Testing:
Voice assistant projects require rigorous performance and load testing to ensure that the system performs opti-
mally under various conditions. QA testing involves simulating high loads and concurrent user interactions to
evaluate the voice assistant's response time, scalability, and stability. It also encompasses testing the system's
ability to handle simultaneous requests and maintain high performance levels without degradation.

45
 Compatibility and Device Testing:
QA testing in voice assistant projects covers compatibility and device-specific testing. It ensures that the voice
assistant functions seamlessly across different platforms, operating systems, and devices, including
smartphones, smart speakers, and other IoT devices. Compatibility testing validates the voice assistant's behav-
ior across a wide range of target devices and configurations.
By conducting comprehensive QA testing in voice assistant projects, development
teams can identify and rectify potential issues, ensuring a high-quality, reliable, and user-friendly voice
assistant application. QA testing improves accuracy, enhances user satisfaction, and contributes to the
overall success and adoption of voice assistant projects.

Conformation Testing:
Conformation testing plays a significant role in voice assistant projects, ensuring that the voice assistant con-
forms to specified requirements, guidelines, and standards. It focuses on verifying that the voice assistant accu-
rately adheres to predefined rules and behaviors, providing a consistent and reliable user experience.

 Compliance with Design Guidelines:

Conformation testing involves assessing whether the voice assistant aligns with the design guidelines and prin-
ciples set by the development team or the platform it is built upon. This includes conforming to the recom-
mended voice and tone, ensuring consistent branding, and adhering to accessibility standards. Testing ensures
that the voice assistant's responses, prompts, and interactions are in line with the desired design language and
user experience.

 Verification of Voice Assistant Scripts:

Conformation testing verifies the correctness and completeness of voice assistant scripts or dialogues. The
scripts encompass the predefined set of responses, prompts, and interactions that the voice assistant is pro-
grammed to deliver. Testers ensure that the voice assistant's responses are accurate, contextually appropriate,
grammatically correct, and consistent across different scenarios. This testing ensures that the voice assistant
consistently communicates the intended information and maintains a cohesive conversational flow.

 Conformance to Platform Guidelines:

Voice assistants often operate within specific platforms or ecosystems, such as Amazon Alexa or Google Assis-
tant. Conformation testing includes validating that the voice assistant complies with the guidelines and require-
ments of the target platform. This includes adhering to platform-specific voice command structures, fulfilling
certification criteria, and conforming to platform-specific technical limitations or capabilities. Testing ensures
that the voice assistant is compatible with the platform's expectations and functions smoothly within its ecosys-
tem.
46
 Cross-platform Testing:
Cross-platform testing is an essential aspect of voice assistant projects that ensures the seamless functionality
and performance of the voice assistant across different platforms and devices. In a rapidly evolving technologi-
cal landscape, where voice assistants are accessible through various operating systems, devices, and ecosys-
tems, it is crucial to validate the voice assistant's compatibility and consistency across these diverse platforms.

 Platform Compatibility:
Cross-platform testing focuses on verifying that the voice assistant performs optimally on different platforms,
such as mobile operating systems (iOS, Android), smart speakers (Amazon Echo, Google Home), or other In-
ternet of Things (IoT) devices. Testers evaluate the voice assistant's behavior, features, and interactions on each
platform, ensuring that it functions as intended and meets the platform-specific guidelines and requirements.
This testing guarantees that users can access the voice assistant seamlessly, regardless of the platform they
choose.
 Operating System Variations:
Different operating systems have unique features, user interfaces, and voice assistant integrations. Cross-
platform testing includes evaluating the voice assistant's compatibility and performance across multiple operat-
ing systems, verifying that it can handle variations in system resources, permissions, and user interface ele-
ments. Testers ensure that the voice assistant maintains consistent behavior and functionalities across different
operating systems, providing users with a unified experience.

 Device-Specific Testing:
Voice assistants are deployed on a wide range of devices, including smartphones, tablets, smart speakers, smart
TVs, and more. Cross-platform testing involves testing the voice assistant's compatibility and performance on
these devices, verifying that it adapts seamlessly to different screen sizes, input methods, and hardware configu-
rations. Testers validate that the voice assistant's user interface elements, visual feedback, and interactions are
optimized for each device, ensuring an optimal user experience.

 Integration with Third-Party Services:

Voice assistants often integrate with various third-party services, such as weather providers, music streaming
platforms, or home automation systems. Cross-platform testing includes verifying the voice assistant's integra-
tion capabilities and compatibility with different third-party services across platforms. Testers ensure that the
voice assistant can seamlessly access and interact with external services, providing users with a consistent and
reliable experience regardless of the platform or service being utilized.

47
 Performance and Stability:
Cross-platform testing encompasses performance and stability testing to evaluate the voice assistant's respon-
siveness, speed, and stability across different platforms and devices. Testers assess factors such as response
time, resource utilization, and overall system performance, ensuring that the voice assistant performs optimally
on each platform without degradation. This testing guarantees a smooth and consistent user experience, regard-
less of the platform or device being used.
Cross-platform testing in voice assistant projects is critical to ensuring a con-
sistent, reliable, and high-quality user experience across diverse platforms and devices. By conducting thorough
testing, development teams can identify and address platform-specific issues, optimize performance, and deliver
a voice assistant that seamlessly integrates with different ecosystems, operating systems, and hardware configu-
rations. This comprehensive testing approach enhances user satisfaction, broadens the reach of the voice assis-
tant, and contributes to the overall success of the project.

Load Testing:
Load testing is a vital aspect of voice assistant projects that focuses on evaluating the performance and scalabil-
ity of the voice assistant under different load conditions. It involves simulating high levels of concurrent user
interactions to assess the system's response time, resource utilization, and overall stability.
 Simulating Realistic User Loads:
Load testing aims to replicate real-world scenarios by simulating the expected user loads that the voice assistant
will encounter. Testers generate a significant number of concurrent requests to assess the voice assistant's per-
formance when multiple users are interacting simultaneously. By simulating realistic user loads, load testing
ensures that the voice assistant can handle the expected volume of user interactions without experiencing per-
formance degradation or system failures.

 Performance Assessment:
Load testing provides insights into the performance of the voice assistant under different load conditions. Test-
ers measure and analyze response times, throughput, and resource utilization metrics to evaluate how the system
behaves when subjected to peak loads. This testing helps identify potential bottlenecks, performance
limitations, and areas for optimization, ensuring that the voice assistant delivers a responsive and efficient user
experience even during high-demand periods.

 Scalability Evaluation:
Load testing plays a crucial role in evaluating the scalability of the voice assistant. Testers assess how the sys-
tem scales with increasing user loads, ensuring that it can handle a growing user base without compromising
performance or stability. By testing scalability, development teams can identify any limitations in system re-

48
sources, architecture, or configuration that may hinder the voice assistant's ability to accommodate increasing
demands.
By conducting thorough load testing in voice assistant projects, development teams can ensure that the
voice assistant performs reliably, efficiently, and consistently under various load conditions. Load testing helps
identify performance bottlenecks, scalability limitations, and resource constraints, allowing for optimization and
refinement of the system to deliver a high-quality user experience. With load testing, the voice assistant can
confidently handle increasing user demands, ensuring user satisfaction and the success of the project.

Usability Testing:
Usability testing plays a crucial role in voice assistant projects, ensuring that the voice assistant delivers an intu-
itive, user-friendly, and satisfying experience. It focuses on evaluating how easily users can interact with the
voice assistant, how well it understands their commands, and how effectively it provides accurate and relevant
responses.
 User Interaction Evaluation:
Usability testing assesses the ease of use and effectiveness of user interactions with the voice assistant. Testers
observe how users interact with the voice assistant, evaluate the intuitiveness of the voice commands, and
assess how well the voice assistant understands and interprets user inputs. This testing helps identify any
usability is- sues, such as commands that are difficult to understand or inconsistencies in the voice assistant's
responses.

 Voice Assistant's Responsiveness:

Usability testing involves evaluating the voice assistant's responsiveness to user commands and queries. Testers
analyze the voice assistant's ability to provide prompt and accurate responses, ensuring that it understands and
processes user inputs effectively. This testing assesses factors such as response time, the clarity of responses,
and the voice assistant's ability to handle simultaneous interactions, ensuring a smooth and seamless user expe-
rience.

 Intuitive Prompting and Guidance:

Usability testing focuses on evaluating how well the voice assistant provides intuitive prompts and guidance to
users. Testers assess whether the voice assistant provides clear instructions, asks for necessary information in a
concise manner, and guides users through complex tasks or interactions. This testing helps ensure that users can
easily navigate through the voice assistant's capabilities and features without confusion or frustration.
Usability testing in voice assistant projects is essential for delivering a user-
centric experience, ensuring that the voice assistant is intuitive, efficient, and satisfying to use. Through usabil-
ity testing, development teams can identify usability issues, optimize user interactions, enhance error handling
mechanisms, and improve the overall user experience.
49
 Automation Testing:
Automation testing plays a crucial role in voice assistant projects, enabling efficient and reliable testing of the
voice assistant's functionalities, performance, and user experience. It involves the use of automated tools and
scripts to execute predefined test cases and validate the behavior of the voice assistant. Automation testing of-
fers several advantages in terms of speed, repeatability, accuracy, and scalability, making it an essential compo-
nent of the voice assistant development and testing process.
 Increased Testing Efficiency:
Automation testing significantly enhances testing efficiency by automating repetitive tasks and reducing manual
effort. With automation tools, test cases can be executed quickly and repeatedly, allowing for efficient testing of
various scenarios and edge cases. This rapid execution helps identify bugs, performance issues, or inconsisten-
cies in the voice assistant's behavior, enabling faster troubleshooting and bug fixing.

 Test Case Coverage:

Automation testing allows for comprehensive test case coverage, ensuring that various functionalities and user
interactions are thoroughly tested. Testers can create a wide range of test cases, covering different voice com-
mands, user inputs, and potential error scenarios. Automated tests can be executed consistently, increasing the
likelihood of identifying critical issues and ensuring that all aspects of the voice assistant are thoroughly tested.

 Regression Testing:
Voice assistant projects often undergo frequent updates and enhancements. Automation testing is valuable for
conducting regression testing to ensure that existing functionalities remain intact and unaffected by new chang-
es. By re-executing automated test scripts, testers can quickly validate that the voice assistant's previously tested
behaviors and interactions continue to function as expected, maintaining the overall quality and reliability of the
voice assistant.

Automation testing is a valuable tool in voice assistant projects, offering increased testing effi-
ciency, extensive test case coverage, and the ability to conduct regression, performance, and load testing. By
automating repetitive tasks and leveraging automated tools and scripts, development teams can ensure the relia-
bility, accuracy, and overall quality of the voice assistant, leading to an enhanced user experience and the suc-
cessful deployment of the voice assistant project.

50
 CHAPTER 7
OUTPUT
DESCRIPTION

51
 Fig 7.1 Query : Write Anything

DESCRIPTION : In Figure 7.1, the voice assistant project demonstrates a remarkable feature that allows users
to write text simply by issuing a command. The specific command used in this example is 'please type.' By em-
ploying this command, users can dictate any text they wish to write, such as a paragraph or a message, and the
voice assistant transcribes it accurately. This innovative functionality of the voice assistant offers immense con-
venience, particularly when users find themselves occupied with other tasks and need to quickly jot down their
thoughts. By utilizing the voice assistant's ability to convert spoken words into written text, users can efficiently
compose content without the need for manual typing. The command 'please type, I am Uttam Singh, a student
of Barkatullah University Institute of Technology in Bhopal' exemplifies the versatility and flexibility of the
voice assistant. Users have the freedom to articulate their intended message naturally and effortlessly, allowing
the voice assistant to accurately capture their words. This feature proves especially valuable in time-sensitive
situations where users require a convenient and hands-free method of generating written content. By harnessing
the capabilities of the voice assistant, users can save significant time and effort that would otherwise be spent on
manual typing.

52
 Fig 7.2 Query : Youtube Search

DESCRIPTION : In Figure 7.2, the voice assistant project showcases a convenient feature that allows users to
search for videos on YouTube without interrupting their current work. This functionality proves particularly
useful when encountering obstacles or needing additional information to resolve a specific problem. Instead of
manually switching tasks and navigating to YouTube, users can simply issue the command 'YouTube search'
followed by their desired search query. For instance, in the given example, the user wants to search for infor-
mation about 'binary heap.' By stating the command 'YouTube search binary heap,' the voice assistant seamless-
ly redirects the current page to YouTube and automatically plays the first video from the search results. This
integration with YouTube search demonstrates the voice assistant's versatility and ability to cater to users' in-
formation needs swiftly. By eliminating the need to manually open a new browser tab, navigate to YouTube,
and type in the search query, the voice assistant streamlines the process and enhances productivity. Users can
leverage this feature in various scenarios, such as when they are engaged in a task and encounter a roadblock
that requires visual or audio assistance to overcome. With a simple voice command, they can access relevant
YouTube content related to their query and gain the necessary insights without disrupting their workflow. The
inclusion of this feature highlights the developers' focus on enhancing the voice assistant's capabilities and
providing a seamless user experience. By incorporating YouTube search functionality, the voice assistant ena-
bles users to access a vast repository of educational, instructional, or entertainment content with ease.
Overall, Figure 7.2 depicts the voice assistant's ability to search for YouTube videos ef-
fortlessly. By issuing the command 'YouTube search' followed by a specific query, users can seamlessly transi-
tion to YouTube, access relevant video content, and address their information needs while staying focused on
their ongoing tasks.

53
 Fig 7.3 Query : Activation

DESCRIPTION : In Figure 7.3, the voice assistant project showcases a seamless activation process with a
simple initial query, 'Good Morning, Sir.' This intuitive and user-friendly feature allows users to effortlessly en-
gage with the voice assistant. Upon uttering the wake-up command, the voice assistant springs into action,
ready to assist the user with their inquiries and tasks. The activation process exemplifies the voice assistant's
advanced speech recognition capabilities, as it accurately detects and interprets the wake-up phrase. This
prompt initiates a dynamic interaction between the user and the voice assistant, enabling a natural and conversa-
tional experience. With the activation successfully triggered, users can then proceed to communicate their re-
quests and queries to the voice assistant. Whether it's checking the weather, playing music, setting reminders, or
controlling smart home devices, the voice assistant is poised to fulfill various tasks and provide relevant infor-
mation promptly.
Overall, the activation process depicted in Figure 7.3 exemplifies the voice assistant's
ability to respond promptly and accurately to a simple initial query, 'Good Morning, Sir.' This feature
showcases the voice assistant's advanced speech recognition capabilities, user-centric design, and adaptability,
contributing to a frictionless and engaging user experience.

54
 Fig 7.4 Query : Open Notepad

DESCRIPTION : In Figure 7.4, the voice assistant project showcases its ability to open and close Notepad, a
popular text editing application, through voice commands. This feature offers users a convenient and hands-free
method of accessing and managing their textual content. By simply uttering the command 'Open Notepad,' users
can prompt the voice assistant to launch the Notepad application on their device. This functionality eliminates
the need to manually navigate through menus or search for the application icon, saving time and effort. Once
Notepad is open, users can utilize its various text editing capabilities to create, modify, or view their documents.
This feature proves particularly useful for users who may be engaged in other tasks and need quick access to a
text editor without interrupting their workflow. Furthermore, the voice assistant project provides users with the
ability to close Notepad by issuing the command 'Close Notepad.' This feature allows for seamless control over
the application, enabling users to efficiently manage their open windows and streamline their work processes.
The integration of Notepad control within the voice assistant demonstrates the project's commitment to provid-
ing a comprehensive and user-friendly experience. By incorporating these voice commands, users can leverage
the power of their voice to interact with Notepad, enhancing productivity and convenience.
Figure 7.4 represents the voice assistant's capacity to open and close Notepad
effortlessly through voice commands. With the simple prompt of 'Open Notepad,' users can quickly access the
application, while the command 'Close Notepad' allows for efficient closure. This integration exemplifies the
voice assistant's ability to streamline workflow, optimize task management, and provide a seamless user experi-
ence.

55
 Fig 7.5 Query : Youtube Search

DESCRIPTION : In Figure 7.5, the voice assistant project showcases its capability to open a specific video on
YouTube with a straightforward voice command. This feature allows users to quickly access and view a
particular video of their choice without the need for manual navigation or searching. By stating the
corresponding query, users can prompt the voice assistant to open a specific video on YouTube. For example, if
a user wants to watch a video on "how to bake a chocolate cake," they can simply issue the command
mentioning the query, such as "Open video: how to bake a chocolate cake." This functionality eliminates the
need for users to manually browse through YouTube, enter search terms, and sift through search results.
Instead, the voice assistant intuitively understands the command and takes the user directly to the desired video.
By streamlining the process of accessing specific videos, the voice assistant enhances convenience and saves
valuable time for users. Whether they are seeking educational content, tutorials, entertainment, or any other type
of video, the voice assistant provides a seamless and efficient way to access the desired content. The integration
of this feature highlights the voice assistant project's commitment to delivering an intuitive and user-centric
experience. By allowing users to open specific YouTube videos with a simple voice command, the project
empowers users to enjoy personalized and targeted video content without any hassle.
Overall, Figure 7.5 exemplifies the voice assistant's ability to open a specific video on
YouTube by responding to the corresponding query. This feature enhances user convenience, saves time, and
ensures a personalized viewing experience. By leveraging this functionality, users can effortlessly access and
enjoy their preferred video content, whether it be for educational, entertainment, or informational purposes.

56
 Fig 7.6 Query : Take A Screenshot

DESCRIPTION : In Figure 7.6, the voice assistant project showcases its ability to capture screenshots through
a simple voice command. By uttering the query, "take the screenshot," users can prompt the voice assistant to
capture an image of the current screen or specific area of interest. This feature offers a convenient and efficient
way to capture visual information without the need for manual screenshot tools or complex keyboard shortcuts.
Users can seamlessly integrate the voice assistant into their workflow and capture screenshots effortlessly.
Whether users want to capture a specific webpage, a portion of an application, or an image displayed on their
screen, the voice assistant responds to the command by capturing the desired screenshot promptly. The inclu-
sion of this feature highlights the voice assistant project's commitment to enhancing user productivity and ac-
cessibility. By simplifying the process of taking screenshots through voice commands, users can quickly
capture and save important visual information for reference, documentation, or sharing purposes. Furthermore,
the voice assistant's screenshot functionality is versatile and adaptable to various contexts and applications. It
ena- bles users to capture screenshots during online meetings, presentations, research, or any other task where
visual information is crucial. Figure 7.6 demonstrates the voice assistant's capability to capture screenshots by
issuing the command, "take the screenshot." This feature provides users with a user-friendly and efficient way
to docu- ment visual content and enhances their ability to capture and retain important information.
Overall, the voice assistant's screenshot functionality exemplifies its commitment to deliver-
ing a seamless and intuitive user experience. By enabling users to capture screenshots through a simple voice
command, the project enhances productivity, accessibility, and the ability to efficiently capture and save visual
information.

57
58
 Fig 7.8 Query : Find My Location

DESCRIPTION : In Figure 7.8, the voice assistant project showcases its capability to determine the user's live
location through the query, "Find my location." This feature enables users to retrieve their current geographical
coordinates or address effortlessly, providing them with real-time location information.
By issuing the command, "Find my location," users prompt the voice assistant to access the
necessary location services and retrieve their current coordinates or address. This functionality eliminates the
need for users to manually search for their location or rely on external navigation apps. The integration of this
feature within the voice assistant project offers users enhanced convenience, especially when they need to
quickly access their current location or share it with others. Whether users require location information for nav-
igation, meeting up with someone, or simply identifying their whereabouts, the voice assistant provides a
streamlined solution. The live location determination feature is particularly useful for users who are on the
move, in unfamiliar places, or require location-based assistance. By leveraging the voice assistant's capabilities,
users can easily obtain accurate and up-to-date location information, enhancing their overall navigation experi-
ence. The inclusion of the "Find my location" query in Figure 7.8 demonstrates the voice assistant project's ded-
ication to providing comprehensive and user-centric functionality. By empowering users to determine their live
location through a simple voice command, the project enhances accessibility, saves time, and facilitates loca-
tion-based decision making.
Overall, Figure 7.8 showcases the voice assistant's ability to determine the user's
live location by utilizing the query "Find my location." This feature offers users a convenient and efficient way
to retrieve real-time location information, enhancing their navigation experience and providing valuable loca-
tion-based assistance.
59
60
61
62
63
64
65
66