A professional-grade voice cloning and text-to-speech application built with Python using Coqui TTS XTTS v2. Clone your voice and generate natural-sounding speech in multiple languages.

• Voice Cloning: Record or upload your voice and clone it instantly
• Multi-language Support: Auto-detects and supports 13+ languages
• Real-time Generation: Generate speech in your cloned voice in seconds
• Quality Control: Audio normalization, pitch, and volume adjustments

• Pitch Adjustment: Fine-tune voice pitch (0.5x to 2.0x)
• Volume Control: Adjust output volume (0.1x to 3.0x)
• Gender Modulation: Toggle between natural/female voice characteristics
• Device Selection: Choose specific input/output audio devices

• Dark/Light Themes: CustomTkinter-based modern interface
• Real-time Monitoring: Live audio level and duration display
• Hardware Detection: Automatic GPU/CPU detection and optimization
• Model Selection: Switch between different TTS engines

• GPU Acceleration: CUDA support for NVIDIA GPUs (GTX 1650+ optimized)
• Low VRAM Mode: Automatic optimization for 4GB VRAM systems
• Batch Processing: Handles long texts with automatic chunking
• Audio Formats: Supports WAV, MP3, FLAC, M4A

• CPU: Intel i5-3470 (4C/8T) | 3.2GHz
• RAM: 16.0GB | Used: 8.2GB (51.2%)
• GPU: NVIDIA GeForce GTX 1650 | 4.0GB VRAM | CUDA 13.1
• OS: Windows 10/11

• Python 3.10 (64-bit)
• NVIDIA GPU (GTX 1650 or better recommended)
• NVIDIA Drivers (latest)
• CUDA Toolkit 12.1 (optional, for GPU acceleration)

git clone https://github.com/SyntX34/Python-Voice-TTS.git

cd Python-Voice-TTS

python -m venv voice_tts

.\voice_tts\Scripts\activate

pip install -r requirements.txt

python app.py