🐢 Tortoise TTS Fast 🚀

Tortoise TTS Fast is a high-performance Text-to-Speech (TTS) application that generates realistic human-like speech using state-of-the-art deep learning models.

🌟 Features

• 🎙️ High-quality speech synthesis
• ⚡ Fast inference
• 📲 Streamlit-based user interface for easy interaction
• 🐳 Docker container for simple deployment
• 🧪 Tested with NVIDIA GPUs

📚 Dependencies

• Python 3.8
• PyTorch 1.13.1
• torchvision 0.14.1
• torchaudio 0.13.1
• Streamlit
• NVIDIA CUDA 11.7.0 (for GPU support)
• Miniconda (for managing Python environments)

🚀 Getting Started

Clone the Repository

git clone https://github.com/louispaulet/tortoise-tts-docker.git
cd tortoise-tts-docker

Build and Run the Docker Container

docker-compose up --build

Access the Streamlit App

Open your web browser and visit http://localhost:8501 to start using the Tortoise TTS Fast application.

📖 Usage

1. Enter your text in the input field.
2. Select the desired voice and audio settings.
3. Click the "Generate" button to synthesize speech.
4. Listen to the generated audio or download it as a file.

📜 License

This project is licensed under the MIT License.