DEV Community: Sarthak Wakade

[Boost]

Sarthak Wakade — Sun, 02 Nov 2025 16:12:39 +0000

How I Built My Own AI Voice Assistant — “Nova”

Sarthak Wakade ・ Nov 2

How I Built My Own AI Voice Assistant — “Nova”

Sarthak Wakade — Sun, 02 Nov 2025 15:40:39 +0000

A fun learning project inspired by Iron Man

Ever since I watched Iron Man, I dreamed of having my own AI voice assistant — something like Jarvis that could respond to me, talk back, and perform tasks.

So instead of downloading one from the Play Store, I decided to build my own assistant as a fun Python learning project.

I named it “NOVA”, which means a bright new star.

Getting Started

I wanted Nova to handle small but fun tasks — things like:

Reading the latest news
Opening apps like Instagram or LinkedIn
Playing my favorite music

To do that, I used Python and a few useful libraries, along with the Gemini API for AI responses.

Libraries I Used

import speech_recognition as sr
import webbrowser
import pyttsx3
import musicLibrary
import requests
import google.generativeai as genai
import threading

Here’s what each one does:

Library	Purpose
speech_recognition	Converts your voice into text (Speech → Text)
webbrowser	Opens websites or apps directly from Python
pyttsx3	Converts text back into voice (Text → Speech)
musicLibrary	A custom module to store and play songs
requests	Fetches real-time data like news articles
google.generativeai	Connects to Gemini API for AI responses
threading	Runs multiple tasks at the same time

How the Code Works

One of the coolest parts was making Nova respond only when I said “NOVA” — just like Jarvis wakes up when Tony Stark calls.

Here’s a simplified version of that logic:

if __name__ == "__main__":
    speak("Initializing NOVA ...") 
    while True:
        r = sr.Recognizer()
        print("Recognizing ...")
        try:
            with sr.Microphone() as source:
                print("Listening for wake word ...")
                audio = r.listen(source, timeout=4, phrase_time_limit=3)

            word = r.recognize_google(audio)
            if "nova" in word.lower():
                speak("Yes Sir, how may I help you?")
                print("Yes Sir, how may I help you?")

                # Listen for the actual command
                with sr.Microphone() as source:
                    print("Nova Active...")
                    audio = r.listen(source)
                    command = r.recognize_google(audio)

                    processCommand(command)

        except Exception as e:
            print("Error: {0}".format(e))

Explanation (in simple words)

The program first says “Initializing NOVA…” — to let you know it’s ready.
It keeps listening for your wake word → “Nova”
Once it hears it, Nova replies:

“Yes Sir, how may I help you?”

Then it listens for your actual command — like: Play music Open Instagram

Those commands are then processed using processCommand()

Any errors are handled so the program doesn’t crash

Challenges & Mistakes (and What I Learned)

This project was full of learning moments!

Problem	What Happened	Solution
Gemini API not working	Wrong model name and expired key	Reconfigured and generated a new API key
No voice response	Forgot `engine = pyttsx3.init()`	Added engine initialization
Wake word not detected	“Nova” wasn’t recognized clearly	Adjusted `timeout` & `phrase_time_limit`
Continuous news reading	It kept reading all articles endlessly	Limited to top 5
Unhandled errors	App crashed on bad input	Added polite fallback responses

And yes — ChatGPT helped me debug a few issues faster!

The Best Part

After countless test runs, hearing:

“Initializing NOVA…”

from my laptop for the first time was an unforgettable feeling.

It felt like I had built my own mini Jarvis — one that could talk, listen, and perform real tasks.

This project taught me about:

APIs
Speech recognition
Threading
Real debugging
Patience while coding!

Final Thoughts

If you’re learning Python or AI —
I highly recommend trying a voice assistant project.

It’s simple to start, super fun to build,
and you’ll learn a LOT in the process.

Keep building cool stuff —
your own Nova might be the first step toward your next big AI idea.

Written by Sarthak Wakade — a creative developer exploring AI, frontend, and fun projects.

How Social Media Subconsciously Controls Your Mind: An Academic Review on Dopamine, FOMO & Algorithms

Sarthak Wakade — Sun, 20 Jul 2025 14:12:30 +0000

Disclaimer: This article is a personal summary and opinion piece based on a literature review conducted as part of a curiosity-driven project. It is not peer-reviewed academic research, but an effort to simplify and share insights on how social media might influence the human mind subconsciously.
Research assistance: Perplexity AI, ChatGPT

Introduction

In today’s hyper-connected world, social media is more than just a communication tool — it’s a psychological ecosystem that can subtly shape our habits, decisions, and emotions. From TikTok to Instagram, platforms are engineered not only to serve content but also to keep users engaged and returning for more.

This article breaks down academic research on how social media subconsciously influences users. It dives into dopamine loops, algorithmic feeds, fear of missing out (FOMO), and highlights why adolescents are particularly vulnerable to these effects.

Abstract (Summary)

Drawing from five peer-reviewed studies, this article outlines the subtle mechanisms through which social media platforms influence user behavior. These include:

AI algorithms designed to predict and modify behavior
Dopamine-driven feedback loops from likes and notifications
Amplification of FOMO and social comparison in teens

These influences often operate below the level of conscious thought, leading to behavioral changes such as addiction, reduced attention span, and emotional dependency. While not universally harmful, the risks are higher among vulnerable groups, especially adolescents.

Thematic Breakdown of the Research

1. Social Media Algorithms

Modern platforms use artificial intelligence to personalize content with the goal of maximizing time spent online. These algorithmic feeds are predictive, not random, and are designed to deliver content that reinforces a user’s existing interests and beliefs.

“Platforms tailor content to reduce cognitive surprise, reinforcing belief systems and behavior loops.”

— White et al. (2024)

This results in echo chambers, reducing exposure to diverse perspectives and strengthening cognitive biases.

2. Dopamine Loops & Instant Gratification

Social media platforms are structured around dopamine-triggering feedback — such as likes, notifications, and new content — which can mimic the patterns seen in addiction.

“Notifications and likes create a dopamine cycle similar to substance addiction.”

— Zsila & Reyes (2023)

Even short periods away from social media can induce discomfort, restlessness, or anxiety, reflecting its addictive potential.

3. The Fear of Missing Out (FOMO)

FOMO is a dominant psychological factor in compulsive social media use. Adolescents, in particular, feel pressure to stay constantly connected to avoid being excluded from trends, conversations, or experiences.

“Teens with high FOMO were more likely to check their phones late at night and report poor sleep and attention.”

— Pellegrino et al. (2022)

4. Behavioral & Mental Health Impacts

Research links excessive social media use to a range of mental health challenges:

Anxiety and depression
Decreased attention span
Poor academic performance
Negative body image

However, findings vary. Some studies using objective tracking methods (like Jones et al., 2024) found only small effects, suggesting that context and usage patterns play a critical role.

5. Adolescents: The Most Vulnerable Group

Adolescents are neurologically and emotionally still developing. Influencers, trends, and curated content strongly affect their identity formation, consumer choices, and mental health.

“Attractive and relatable influencers strongly shaped teenagers’ opinions and lifestyle choices.”

— Lajnef (2023)

Discussion: Why This Matters

Social media is not just “entertainment.” Behind every swipe and scroll, AI-driven systems are shaping:

What users see
What they believe
How they feel and behave

And because this process happens subconsciously, many users feel in control — when, in fact, their experiences are being curated in real-time to maximize engagement.

What Can We Do?

Based on the research, here are a few actionable recommendations:

1. Digital Literacy

Understanding how algorithms work can help users become more mindful and critical of the content they consume.

2. Algorithmic Transparency

Researchers and users should advocate for greater transparency from tech companies on how feeds and recommendations are constructed.

3. Mindful Usage

Encourage practices like screen time limits, notification control, and intentional content consumption.

Visual Insight

A conceptual map showing how algorithms, networks, influencers, and psychological feedback loops interact on social media platforms.

References

White, B., Clark, A., & Miller, M. (2024). Digital being: Social media and the predictive mind. Neuroscience of Consciousness, 2024(1)
Jones, C. N., et al. (2024). Investigating the links between objective social media use and well-being. Social Science & Medicine, 361
Pellegrino, A., et al. (2022). Research trends in social media addiction. IJERPH, 19(23)
Zsila, Á., & Reyes, M. E. S. (2023). Impacts of social media on mental health. BMC Psychology, 11(1)
Lajnef, K. (2023). The effect of social media influencers on adolescents. Current Psychology

Conclusion

Social media isn't just shaping content — it’s shaping cognition, emotion, and behavior. While these platforms offer real benefits in communication and creativity, they also operate through subtle psychological mechanisms that warrant attention.

By promoting awareness, education, and mindful engagement, users can better navigate the digital world — rather than be controlled by it.

[Boost]

Sarthak Wakade — Wed, 16 Jul 2025 15:05:21 +0000

Getting Started With Frontend and UI/UX — A Beginner-Friendly Guide

Sarthak Wakade ・ Jul 16

#beginners #frontend #uiux #html

Getting Started With Frontend and UI/UX — A Beginner-Friendly Guide

Sarthak Wakade — Wed, 16 Jul 2025 14:52:56 +0000

Not Sure Where to Start in Tech? Try Frontend and UI/UX

If you're a student or beginner trying to figure out where you fit in tech — frontend development is a great place to start.

Why?

Because it's visual, creative, and gives you real results fast. You don’t need deep programming knowledge to build your first webpage. All you need is a browser, a text editor, and curiosity.

Start Simple: HTML + CSS

Here’s the basic stack to learn first:

HTML: Structure of the page
CSS: Styling, layout, colors, spacing
JavaScript (basics): To add simple interactions

Once you get the hang of those, you can build:

A blog layout
A landing page
A Netflix or Starbucks UI clone
A portfolio site to showcase your learning

The key is to build while you learn. No need to wait until you're “ready”.

UI/UX: The Design Side of Tech

Once you’ve built a few frontend projects, you might start asking questions like:

Is this layout easy to use?
Does this color scheme look right?
Where should this button go?

That’s the start of UI/UX thinking.

You can explore tools like:

Figma (for prototyping designs)
Dribbble / Mobbin (for design inspiration)
Frontend Mentor / DevChallenges (for real-world practice)

Try redesigning simple pages or apps. Focus on layout, user flow, and making the interface clean and usable.

A Quick Note From My Own Journey

I'm a student myself. I started learning frontend during semester breaks. I didn’t know much — just basic HTML/CSS — but I kept experimenting.

Eventually, I tried tools like Figma, rebuilt pages like Starbucks, created light/dark UIs, and even designed a fitness app layout. The more I built, the more I enjoyed it.

I'm still learning. Still improving. But I’ve found what I enjoy — and that’s a good place to start.

Tips for Students Starting Out

Don’t wait for college to teach you. Learn by doing.
YouTube + Figma + CodePen = your best friends
You don’t need to know everything — just enough to start
Explore frontend, then design, then full-stack if it interests you

Wrapping Up

If you're confused about where to begin in tech, try frontend.

Build something small. Tweak it. Break it. Fix it. Add a little design. Explore UI/UX. You’ll learn more by doing than any course can teach you.

Still unsure where to begin? Drop a comment or DM. I’m also figuring it out — and sharing as I go.