TTS: Local Neural Text-to-Speech

A high-fidelity, local-first Text-to-Speech application built with Python and ONNX. This system provides both high-speed standard synthesis and advanced neural output using a lightweight footprint.

Features

• AI Neural Engine: Professional-grade speech synthesis using Piper ONNX models.
• Fast Mode: Low-latency standard synthesis via pyttsx3.
• Premium UI: Modern sidebar dashboard built with CustomTkinter.
• Precise Controls: Adjustable speech rate (0.5x - 2.0x) and live volume scaling.
• Local First: Runs entirely on your hardware with no cloud dependencies.

Installation

1. Create a virtual environment: python -m venv .venv

2. Activate the environment:

   Windows

   .venv\Scripts\activate

3. Install dependencies: pip install -r requirements.txt

Usage

Run the main application: python main.py

Both main.py and advanced_main.py provide the full dashboard experience.

Technical Details

• Framework: CustomTkinter
• Neural Backend: Piper (ONNX Runtime)
• Standard Backend: pyttsx3
• Audio Playback: Pygame Mixer
• Data Extraction: Multi-property AudioChunk extraction for Piper compatibility.