🎤 Voice Cloner - AI Voice Synthesis

🚀 Advanced AI Voice Cloning & Text-to-Speech

Transform any text into natural speech using your own voice or any reference audio

---

✨ Features

• 🎯 Zero-shot Voice Cloning - Clone any voice with just seconds of reference audio
• 🎭 Emotion Control - Adjust emotional intensity and expression
• ⚡ Real-Time Processing - Optimized for fast generation
• 🔊 HD Audio Output - Crystal clear, natural-sounding speech
• 🎨 Premium UI - Modern, beautiful interface

🚀 Quick Start

1. Install Dependencies

pip install -r requirements.txt

2. Run the App

streamlit run streamlit_app.py

3. Open in Browser

Navigate to http://localhost:8501

💻 Usage

Web Interface (Recommended)

streamlit run streamlit_app.py

Python API

from src.bhavesh_ai_voice_cloner.tts import BhaveshTTS
import torchaudio as ta

# Initialize the model
model = BhaveshTTS.from_pretrained(device="cuda")

# Generate speech with default voice
text = "Hello! This is AI speaking."
wav = model.generate(text)
ta.save("output.wav", wav, model.sr)

# Clone a specific voice
wav = model.generate(text, audio_prompt_path="reference.wav")
ta.save("cloned_voice.wav", wav, model.sr)

🎛️ Parameters

Parameter	Range	Default	Description
exaggeration	0.25-2.0	0.5	Emotion intensity
cfg_weight	0.0-1.0	0.5	Speech clarity
temperature	0.1-2.0	0.8	Generation randomness

📁 Project Structure

voice-cloner/
├── streamlit_app.py          # Premium web UI
├── launch.py                  # Quick launcher
├── requirements.txt           # Dependencies
├── src/
│   └── bhavesh_ai_voice_cloner/
│       ├── tts.py            # Text-to-Speech
│       ├── vc.py             # Voice Conversion
│       └── models/           # AI Models
└── README.md

📄 License

MIT License - see LICENSE for details.

---

Made with ❤️ by Bhavesh AI