Skip to content

Bhasker811/visualaid

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 

Repository files navigation

VISUAL AID

🚀 Visual Aid: Voice Assistant for the Visually Impaired

📌 Problem Statement

Problem Statement 1 –Weave AI magic with Groq

🎯 Objective

The Visual Aid project aims to provide a voice-controlled web application that helps visually impaired individuals perform common tasks like:

  • Making WhatsApp calls, sending messages, and video calling
  • Getting email summaries
  • Describing live images
  • Controlling system functions (volume, Wi-Fi, Bluetooth)
  • Getting directions to specific places
  • Summarizing news articles

The application serves the visually impaired community by giving them independence and making digital interactions accessible.

🧠 Team & Approach

Team Name: Sushanth

Team Members:

  • Nerella Sushanth (Team Lead)
  • Avusali Bhasker
  • Simhadri Pranathi
  • D Shanmukhaditya

Your Approach:

We chose this problem because of the increasing need for accessible technologies that help people with disabilities, especially the visually impaired. The project focuses on voice control to enable users to perform key tasks without the need for physical interaction with a screen. We faced challenges with integrating multiple APIs, speech recognition, and ensuring seamless interactions, but overcame them with effective brainstorming and technical pivots.

🛠 Tech Stack

Core Technologies Used:

  • Frontend: Streamlit
  • Backend: Python
  • Database: None (static data used)
  • APIs: Groq (Speech-to-Text, Text Summarization, etc.), Geolocation API, OpenCV (for image recognition)
  • Hosting: Not yet hosted (local deployment)

Sponsor Technologies Used:

  • Groq: Used for integrating speech-to-text, audio-to-text, and summarization models

✨ Key Features

  • WhatsApp Messaging – Send and receive WhatsApp messages, make calls and video calls
  • Email Summaries – Summarize emails received for the user
  • Live Image Description – Describe real-time images or camera captures for the user
  • System Controls – Adjust system volume, brightness,Wi-Fi, Bluetooth settings
  • Navigation Directions – Provide directions to specific places using voice commands
  • News Summaries – Summarize the latest news articles for the user

📽 Demo & Deliverables

✅ Tasks & Bonus Checklist

  • ✅ All members of the team completed the mandatory task
  • ✅ All members of the team completed Bonus Task 1 – Sharing of Badges
  • ✅ All members of the team completed Bonus Task 2 – Signing up for Sprint.dev

🧪 How to Run the Project

Requirements:

  • Python 3.x
  • Necessary libraries installed using pip install -r requirements.txt

Local Setup:

  1. Clone the repo:
    git clone https://github.com/Bhasker811/visualaid

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages