Voice Bridge

Break Barriers, Build Bridges — Instantly. Voice Bridge is a fast, web-based translator using Groq AI for real-time text, voice, and photo translation,making global communication seamless and instant.

📌 Problem Statement

Problem Statement 1 - Weave Al magic with Groq

The Problem It Solves

Language barriers are a major hurdle in global communication. Whether you're traveling, studying, working, or seeking help, not understanding another language can create confusion, delays, and even dangerous situations. Traditional translation tools are often slow, limited to one input type, or require switching between apps.

---

🎯 Objective

How Voice Bridge Helps

Voice Bridge makes multilingual communication instant, easy, and accessible by offering real-time translation through text, voice, and photo input — all in one place, powered by Groq AI.

Use Cases

Travel: Instantly translate signs, menus, or ask for directions using your voice or camera. Education: Break down language barriers in the classroom or while accessing international learning content. Healthcare: Communicate clearly with patients from different language backgrounds. Customer Support: Help users in their native language without needing a multilingual team. Emergency Situations: Translate critical information quickly during urgent scenarios.

Makes Life Easier By

Supporting multimodal inputs (text, audio, photo). Delivering instant translations with high accuracy. Being web-based, so no installs or downloads needed.

Providing a user-friendly experience for anyone, anywhere.

🧠 Team & Approach

Team Name:

Code Struct

Team Members:

• Satvik Mishra
• Satwik Dubey
• Satvik Kumar

Your Approach:

• Language barriers are a major hurdle in global communication. Whether you're traveling, studying, working, or seeking help, not understanding another language can create confusion, delays, and even dangerous situations. Traditional translation tools are often slow, limited to one input type, or require switching between apps.

• As it was our first hackathon and our first team project, we ran into challenges regarding team collaboration and integrating the frontend and the backend

• I explored how ngrok can be utilized to establish secure tunnels for self-hosted applications, enabling my local machine to expose services over the internet via a publicly accessible domain, as long as the machine remains online.

---

🛠️ Tech Stack

Core Technologies Used:

• Frontend: Next.js, Tailwind CSS, Shadcn, Material UI
• Backend: Spring Boot, Spring Data JPA, Spring Security, JWT Auth
• Database: MySQL
• APIs: Groq text, audio, and vision API's

Sponsor Technologies Used (if any):

• [✅] Groq: All of our work on translations happens via Groq
• 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:

• ✅ Text-to-Text Translation
• ✅ Audio-to-Text and Audio-to-Audio Translations
• ✅ Image-to-text Translation
• ✅ Secure Login using JWT

Add images, GIFs, or screenshots if helpful!

---

📽️ Demo & Deliverables

• Demo Video

---

✅ 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

Frontend

• First use npm install
• Then npm run dev

Backend

• Docker
• Docker Compose
• A .env file with necessary environment variables (see below)

---

🛠️ Environment Setup

Create a .env file in the root directory with the following contents:

API_KEY=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
API_URL_AUDIO=https://api.groq.com/openai/v1/audio/translations
API_URL_AUDIO_TRANSCRIBE=https://api.groq.com/openai/v1/audio/transcriptions
API_URL_IMAGE=https://api.groq.com/openai/v1/chat/completions
API_URL_TEXT=https://api.groq.com/openai/v1/chat/completions
API_URL_TEXT_SPEECH=https://api.groq.com/openai/v1/audio/speech

🧬 Future Scope

List of possible improvements and extensions:

📈 More integrations: API support for Sign Language Translation

🛡️ Security enhancements: Add OAuth authentication support

📎 Resources / Credits

APIs or datasets used: Groq API

🏁 Final Words

Break lingual barriers and unite the world through intelligent multilingual communication. 🌍🗣️