🎤 VoiceForge — Azure AI Speech Studio

A premium, modern web application built using Microsoft Azure Speech Services that enables real-time Speech-to-Text (STT) and Text-to-Speech (TTS) with a stunning UI and smooth user experience.

---

🚀 Features

🎤 Speech-to-Text (STT)

• Real-time voice recording using microphone
• Continuous speech recognition
• Live transcription (interim + final text)
• Character count tracking
• Copy and clear transcription

🔊 Text-to-Speech (TTS)

• Convert text into natural AI-generated speech

• High-quality Neural Voices

• Adjustable:

  • Speed (0.5× – 2.0×)
  • Pitch (-10Hz to +10Hz)

• Audio controls:

  • Play
  • Pause / Resume
  • Stop

• Download generated speech as .wav

🌍 Multi-Language Support

• Supports multiple languages:

  • English (US/UK)
  • Hindi
  • Spanish
  • French
  • German
  • Japanese
  • Chinese
  • Arabic
  • And more...

🎚️ Voice Customization

• Male & Female neural voices
• Dynamic voice switching based on language

🔄 Mode Switching

• Toggle between:

  • 🎤 Speech → Text
  • 🔊 Text → Speech

📋 Utility Features

• Copy to clipboard
• Clear input/output
• Character limit handling (TTS: 5000 chars)

---

🔐 Azure Integration

This app uses Microsoft Azure Cognitive Services Speech SDK.

Required Inputs:

• API Key
• Region (e.g., eastus, centralindia)

⚠️ Credentials are NOT hardcoded and must be entered by the user.

---

🎨 UI/UX Highlights

• 🌌 Futuristic bioluminescent dark theme
• 🧊 Glassmorphism UI design
• 🎤 Animated microphone with ripple effect
• 🔊 Speaker visualization animation
• 🌊 Real-time waveform bars
• ⚡ Smooth transitions & hover effects
• 🌗 Dark / Light mode toggle
• 📱 Fully responsive (mobile + desktop)

---

⚙️ Tech Stack

• HTML5

• CSS3 (Advanced UI + Animations)

• Vanilla JavaScript (ES6+)

• Azure Speech SDK

• Web APIs

  • MediaDevices (microphone access)
  • Web Audio API

---

📂 Project Structure

VoiceForge/
│
├── index.html     # Main UI structure
├── style.css      # Styling & animations
├── script.js      # Logic (STT + TTS + UI interactions)
└── README.md

---

▶️ How to Run

1. Download or clone this repository

2. Open index.html in your browser

3. Enter:

   • Azure API Key
   • Region

4. Start using:

   • 🎤 Record speech
   • 🔊 Convert text to voice

---

⚠️ Important Notes

• Requires internet connection
• Microphone permission must be enabled
• Azure account is required: 👉 https://portal.azure.com/

---

🧠 Advanced Features

• Continuous speech recognition

• Real-time interim transcription

• Audio download functionality

• Dynamic SSML generation for TTS

• Error handling:

  • Invalid API key
  • Mic permission denied
  • API failures

---

🛠️ Future Improvements

• Voice cloning support
• Emotion-based speech synthesis
• AI noise cancellation
• Speech-to-speech conversion
• User authentication & cloud storage

---

👨‍💻 Author

Krishna Gopal Rathore

---

⭐ Credits

Powered by Microsoft Azure Cognitive Services

---

📜 License

This project is open-source and free to use for learning and development purposes.

---

💡 Final Note

VoiceForge is designed to feel like a real AI product, not just a demo — combining powerful Azure Speech capabilities with a premium SaaS-level UI/UX.

---