Skip to content

RohanBanerjee88/Aria

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

6 Commits
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Aria - Augmented Vision Assistant πŸ‘οΈ

AI-powered accessibility app for blind and visually impaired users. Navigate environments, read text, and get directionsβ€”all hands-free.

Swift iOS

Built at Hack Harvard 2025 πŸ†


✨ What It Does

Aria transforms your iPhone camera into an intelligent assistant with three gesture-controlled modes:

  • βœ‹ Environment Mode - Detects obstacles, describes surroundings, guides safe paths
  • ✌️ Communication Mode - Reads text from signs, menus, labels, documents
  • πŸ—ΊοΈ Navigation Mode - Turn-by-turn walking directions with voice guidance

All controlled hands-free with simple gestures. Show a fist (✊) to stop.


πŸ› οΈ Tech Stack

  • Gemini 2.0 Flash - Scene understanding & OCR
  • ElevenLabs - Natural text-to-speech
  • Google Maps API - Turn-by-turn navigation
  • iOS Vision - Hand gesture recognition
  • Swift/SwiftUI - Native iOS app

πŸš€ Quick Start

  1. Clone the repo
git clone https://github.com/yourusername/aria.git
  1. Get API keys from:

  2. Add keys to Utilities/Constants.swift:

static let geminiAPIKey = "YOUR_KEY"
static let elevenLabsAPIKey = "YOUR_KEY"
static let googleMapsAPIKey = "YOUR_KEY"
  1. Run on iPhone (requires physical device for camera/GPS)

πŸ“± Usage

Environment Mode: Show open palm βœ‹ β†’ Move camera around β†’ Hear obstacle descriptions

Reading Mode: Show peace sign ✌️ β†’ Point at text β†’ Hear it read aloud

Navigation: Tap Navigate button β†’ Enter destination β†’ Follow voice directions

Stop anytime: Show fist ✊

About

Realtime vison assistant

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages