Welcome to the TTS Studio documentation. This guide will help you get started with voice cloning and text-to-speech synthesis.
Start here if you're new to TTS Studio.
- Installation - Install TTS Studio
- Quick Start - Get up and running in 5 minutes
- Configuration - Configure TTS Studio
Understand the fundamentals.
- Architecture - Hexagonal architecture overview
- Audio Specifications - Audio format requirements
Step-by-step guides for common tasks.
- Recording Samples - Record quality audio samples
- Creating Profiles - Create voice profiles
- Generating Audio - Generate speech from text
Complete API documentation.
- Python API - Main API reference
For contributors and developers.
- Setup - Development environment setup
Git workflow and best practices.
- Pre-commit Hooks - Pre-commit setup
- Git Cheatsheet - Useful Git commands
Advanced topics and optimization.
- Qwen3 Setup - Qwen3-TTS specific setup
- Model Comparison - Qwen3 vs XTTS
- Quality Improvement - Improve voice quality
- Text Formatting - Format text for TTS
- Testing Prompts - Test prompts and examples
Migration guides.
- Migration Guide - Migrate from v0.x to v1.0
Deprecated documentation (for reference only).
- Installation: 01-getting-started/01-installation.md
- Quick Start: 01-getting-started/02-quick-start.md
- API Reference: 04-api-reference/01-python-api.md
- Architecture: 02-core-concepts/01-architecture.md
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Repository: GitHub
See 05-development/01-setup.md for development setup and contribution guidelines.