Skip to content

ChinthanChinnappa/Voice-Assistant

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

🎤 Web Voice Assistant

A browser-based voice assistant built using HTML, CSS, and JavaScript. The application uses the Web Speech API to enable speech recognition and text-to-speech functionality, allowing users to interact with the assistant through voice commands.

This project demonstrates how modern browsers can implement voice-controlled interfaces without external frameworks or APIs.


🚀 Features

  • 🎙️ Voice command recognition
  • 🔊 Text-to-speech responses
  • 🌐 Browser-based implementation
  • ⚡ No external libraries or frameworks
  • 💬 Interactive voice responses

🛠️ Technologies Used

Frontend:

  • HTML
  • CSS
  • JavaScript

Web APIs:

  • Web Speech API

    • SpeechRecognition
    • SpeechSynthesis

🏗️ How It Works

The system follows this workflow:

User Voice Input
       │
       ▼
Speech Recognition (Web Speech API)
       │
       ▼
JavaScript Processing
       │
       ▼
Assistant Response
       │
       ▼
Speech Synthesis (Text-to-Speech)
  1. The user clicks the microphone button.
  2. The browser listens for voice commands.
  3. JavaScript processes the spoken input.
  4. The assistant generates a response.
  5. The response is spoken using text-to-speech.

📂 Project Structure

Voice-Assistant
│
├── index.html      # Main user interface
├── styles.css      # Styling for the UI
├── app.js          # Voice recognition and assistant logic
└── README.md

⚙️ How to Run the Project

1️⃣ Clone the repository

git clone https://github.com/ChinthanChinnappa/Voice-Assistant.git

2️⃣ Open the project folder

cd Voice-Assistant

3️⃣ Run the application

Simply open:

index.html

in your browser.

Recommended browsers:

  • Google Chrome
  • Microsoft Edge

💡 Example Commands

The assistant can respond to commands such as:

  • “Open Google”
  • “What is the time?”
  • “Search for something”
  • “Tell me a joke”

(Commands depend on the logic implemented in app.js.)


📚 Learning Outcomes

This project helped me understand:

  • Browser-based speech recognition
  • Text-to-speech synthesis
  • Event-driven JavaScript
  • Web APIs integration
  • Building interactive voice interfaces

📈 Possible Improvements

Future enhancements could include:

  • Integration with AI APIs
  • More advanced command processing
  • Natural language understanding
  • Voice-controlled smart assistant features
  • Better UI design

👨‍💻 Author

Chinthan Chinnappa P T

Computer Science Engineering Student

Interested in:

  • AI Systems
  • Data Engineering
  • Backend Development
  • Intelligent Interfaces

About

A simple and interactive web-based voice assistant built using HTML, CSS, and JavaScript. This project demonstrates how browser-based speech recognition and synthesis can be used to create a responsive, voice-controlled assistant directly in the browser—without any external frameworks.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors