VoiceOS is a modern, interactive AI-powered web application that enables real-time Speech-to-Text (STT) and Text-to-Speech (TTS) directly in the browser. Built with clean UI/UX and seamless user interaction, it leverages Web Speech API with optional Azure Speech integration.
-
🎤 Speech-to-Text (STT)
- Real-time voice recognition
- Instant transcript generation
- Copy and clear transcript functionality
-
🔊 Text-to-Speech (TTS)
- Convert text into natural speech
- Voice selection (multiple voices)
- Adjustable speed and pitch
-
🎨 Modern UI/UX
- Responsive design (mobile + desktop)
- Dark/Light mode toggle
- Smooth animations and feedback
-
🔐 Credential Support
- Azure Speech API key & endpoint input
- Input validation and error handling
-
⚡ Smart Fallback
- Automatically uses browser Web Speech API if Azure is not connected
- HTML5
- CSS3 (Modern UI Design)
- JavaScript (Vanilla JS)
- Web Speech API
- Azure Cognitive Services (Optional)
voiceOS/
│── index.html
│── style.css
│── script.js
│── README.md
👉 https://Savinay99.github.io/voiceOS/
- Clone the repository:
git clone https://github.com/Savinay99/voiceOS.git
-
Open in browser using Live Server (recommended)
-
Allow microphone permission when prompted
To enable Azure Speech Services:
- Go to Azure Portal
- Get your API Key and Endpoint
- Enter credentials in the app
- Speech recognition works best on Chrome / Edge
- Requires HTTPS or localhost
- Microphone permission is mandatory
- Full Azure Speech SDK integration
- Audio file download support
- Multi-language auto detection
- Voice cloning support
Savinay GitHub: https://github.com/Savinay99
If you like this project, consider giving it a ⭐ on GitHub!