🚀 Project Title

Real-time Multilingual AI Assistant

---

📌 Problem Statement

Problem Statement 1 – Weave AI magic with groq

---

🎯 Objective

This project breaks down language and accessibility barriers by enabling real-time, multilingual interaction with AI through text, voice, and images.

It serves users worldwide, including non-English speakers, visually impaired individuals, and anyone seeking fast, intelligent assistance — all powered by Groq’s ultra-fast AI models.

---

🧠 Team & Approach

Team Name:

Solo

Team Members:

• Aastha Bhat

Your Approach:

• I chose this problem due to the desire to break down language barriers in real-time communication and explore the potential of fast AI inference for more natural human-computer interaction drove the selection of this multilingual assistant problem.

• Key challenges addressed: Handling multilingual input and output (text and voice), integrating image understanding into a conversational flow, and ensuring a responsive user experience leveraging Groq's speed presented significant technical hurdles.

• Pivots/Breakthroughs: Initial limitations with basic voice output led to exploring more robust TTS solutions (though not yet fully integrated), and recognizing the critical role of clear UI/UX for a user-friendly multilingual interaction became a key design focus.

---

🛠️ Tech Stack

Core Technologies Used:

• Frontend: React
• Backend: Express
• Database: None
• APIs: Groq
• Hosting: Localhost

Sponsor Technologies Used (if any):

• Groq: Agnira utilizes the Groq API to power its fast and efficient large language model for generating real-time text responses.
• Monad: Your blockchain implementation
• Fluvio: Real-time data handling
• Base: AgentKit / OnchainKit / Smart Wallet usage
• Screenpipe: Screen-based analytics or workflows
• Stellar: Payments, identity, or token usage (Mark with ✅ if completed)

---

✨ Key Features

Highlight the most important features of your project:

• ✅ Voice Input Support – Speak your queries using browser's speech recognition.

• ✅ Multilingual Text-to-Speech – Input can be in English, Hindi or Kannada.

• ✅ Image Upload + AI Response – Upload images and get AI-powered insights (via Groq API).

• ✅ Dynamic Typing Effect – Real-time typewriter animation while bot replies for a more interactive feel.

---

📽️ Demo & Deliverables

• Demo Video Link: https://youtu.be/Gg0CDlx8m1g
• Pitch Deck / PPT Link: https://drive.google.com/file/d/1CwkrwgPBtYxRw11r1wgqPYfwsCbJxh8t/view?usp=drivesdk

---

✅ Tasks & Bonus Checklist

• All members of the team completed the mandatory task - Followed at least 2 of our social channels and filled the form (Details in Participant Manual)
• All members of the team completed Bonus Task 1 - Sharing of Badges and filled the form (2 points) (Details in Participant Manual)
• All members of the team completed Bonus Task 2 - Signing up for Sprint.dev and filled the form (3 points) (Details in Participant Manual)

(Mark with ✅ if completed)

---

🧪 How to Run the Project

Requirements:

• Node.js
• API Keys (Groq & OpenAI)
• .env file in the backend directory(with the API keys as : GROQ_API_KEY=Your Key, OPENAI_API_KEY=Your Key)

Local Setup:

# Clone the repo
git clone https://github.com/AasthathecoderX/Agnira-2.0

# Frontend
cd src
npm install
npm start


# Backend
cd backend
npm install multer
node index.js

-The frontend code is located in the src/ directory and runs on http://localhost:3000 by default.

-The backend code is in the backend/ folder and listens on http://localhost:4000.

-Create a .env file in the backend directory and add the following keys: GROQ_API_KEY=your-groq-api-key OPENAI_API_KEY=your-openai-api-key

• Make sure not to expose your API keys publicly in version control use .gitignore to exclude .env files.

---

🧬 Future Scope

List improvements, extensions, or follow-up features:

• 📈 More integrations (e.g., Google Vision, Hugging Face APIs)
• 🛡️ Security enhancements (e.g., rate limiting, input sanitization)
• 🌐 Localization / broader accessibility (multi-language support, screen reader optimization)
• 💾 Add database support for chat history

---

📎 Resources / Credits

• API: Groq API : For ultra-fast large language model responses Web Speech API – for speech recognition and synthesis in-browser

• React : for building the user interface

• Acknowledgements: Special thanks to Groq for providing the powerful and fast inference engine that drives Agnira's intelligence.Also I wuld like to thank the mentors of the Groq track for their valuable guidance

---

🏁 Final Words

Building this real-time chatbot with AI and the Groq API was a fun and educational first experience. Despite initial difficulties in understanding API integration and chatbot development, I thoroughly enjoyed the learning process and the progress made.

---