AudioLens

Bladen Lehnberg

221146

Interactive Development 300

Audio Lens

AudioLens is an accessibility-focused mobile app designed for the visually impaired.

Explore the docs »

View Demo · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
     • Front-end Installation
3. Features
4. Contributors
5. License

About the Project

AudioLens is a mobile app that empowers visually impaired users by transforming visual text into audio in real-time. Utilizing Google Cloud Vision for Optical Character Recognition (OCR) and Google’s Text-to-Speech (TTS) API, AudioLens allows users to take a photo or select an image to detect text, which is then read aloud for an accessible experience. The app provides an intuitive and accessible interface with large, easy-to-read buttons and high-contrast colors to accommodate users with low vision. It starts with a live camera, making it quick and easy for users to capture text, whether it's on a menu, a sign, or any document. AudioLens is an essential tool for anyone seeking assistance with reading text in their daily life, providing seamless navigation, simple controls, and a commitment to accessibility.

(back to top)

Built With

Getting Started

Prerequisites

• 
• 

Installation

Frontend Installation

1. Clone the frontend repo

   https://github.com/Bladeyboy54/AudioLens.git

2. Install the node modules for React Native

   cd audiolens

   then

   npm i

3. Create a file called .env
4. In the .env file add you Google Cloud SKD API Key

   API_KEY=""

5. Start the application in your IDE Terminal

   npm start

(back to top)

Features

1. AI Intergration

• Real-time Text Recognition: Starts with a live camera feed to capture text instantly or allows users to select an image from their gallery for text recognition.
• Text-to-Speech Conversion: Recognized text is converted into audio using Google’s Text-to-Speech (TTS) API, making it accessible for visually impaired users to hear the content.
• Cloud Integration for High Accuracy: Google Cloud Vision API enables high-accuracy OCR for diverse text formats, from printed documents to handwritten notes.

2. User-Friendly UI

• Simple Navigation: Intuitive navigation flow between camera, image preview, and text recognition screens, with a back button to return and retake images as needed.
• High Accessibility Standards: Easy-to-read button text, large touch targets, and high-contrast color schemes designed with visually impaired users in mind.

3. Manual inputs

• Supported File Types: Allows image input from both live camera captures and photo gallery selections, providing flexibility in how users capture text.
• Manual Text-to-Speech Control: Users can manually convert recognized text to speech, giving control over when to hear the content aloud.

User Testing Results

Question	Average Rating	Notes
Ease of navigation	9/10	Users found the interface intuitive and easy to navigate.
Feature accessibility	5/5	All features were generally easy to locate.
Feature functionality	9/10	Minor improvements suggested for TTS screen layout.
Satisfaction with app experience	8.5/10	UI simplification and accessibility efforts were well-received.
Design (colors, font, layout)	9/10	Positive feedback on color choice for accessibility.
Accessibility for visually impaired users	8/10	Accessibility features praised, with room to enhance text conversion UI.

(back to top)

Contributors

_{Bladen Lehnberg}

(back to top)

Licence

Distributed under the MIT License. See LICENSE.txt for more information.

(back to top)