Skip to content

Latest commit

 

History

4 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🎙️ NOVA – Bilingual AI Voice Assistant for Accessibility (Sinhala & English)

Project Overview

NOVA is a Python-based AI voice assistant designed to support Sinhala and English language interactions, with a strong focus on accessibility for visually impaired and motor-disabled users in Sri Lanka.

The system enables users to perform everyday digital tasks through voice commands, reducing reliance on keyboards and screens while promoting an inclusive computing experience.


Key Features

  • Speech-to-text voice command recognition
  • Text-to-speech responses (online & offline)
  • Sinhala ↔ English language translation
  • AI-powered responses and summarization
  • YouTube search and playback via voice
  • Open desktop applications and folders
  • Conversational AI interaction
  • Accessibility-focused hands-free control

Problem Statement

Most existing voice assistants have limitations such as:

  • Lack of Sinhala language support
  • Limited customization for local users
  • Dependence on closed ecosystems
  • Minimal accessibility support

NOVA addresses these gaps by providing a customizable, bilingual, and accessibility-oriented solution tailored for Sri Lankan users.


Proposed Solution

A modular AI-powered desktop voice assistant that integrates multiple APIs and tools to deliver intelligent, voice-driven functionality.


Tech Stack

  • Programming Language: Python

  • APIs & Libraries: Google Speech Recognition | Gemini API | Google Translate API | gTTS (Google Text-to-Speech) | pyttsx3 | PyWhatKit

  • UI & Tools: CustomTkinter | Figma

  • Other Modules: OS Module | PIL

System Architecture

  • Input Module: Speech recognition (voice → text)
  • Processing Module: Command handling + AI (Gemini API)
  • Output Module: Text-to-speech (gTTS / pyttsx3)
  • Task Modules: YouTube, translation, file control

Key Contributions

  • Built bilingual voice interaction (Sinhala & English)
  • Integrated AI-based summarization and responses
  • Implemented voice-controlled YouTube and system operations
  • Developed translation functionality
  • Enhanced accessibility through voice-driven interaction

Outcomes

  • Accurate bilingual voice recognition
  • Real-time AI responses and summaries
  • Seamless execution of tasks via voice
  • Improved accessibility for differently-abled users

Limitations

  • Requires internet for AI and translation features
  • Sinhala recognition accuracy may vary
  • Basic GUI due to project scope
  • No mobile version
  • Hardware integration not implemented

Future Enhancements

  • Arduino + Bluetooth integration
  • Mobile application development
  • Advanced accessibility features
  • Improved Sinhala NLP accuracy
  • Offline AI support

Licence:

This project is licensed under the MIT License.

About

Bilingual AI voice assistant enabling Sinhala and English interaction, designed to improve accessibility and hands-free computing for differently-abled users.

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages