🗣️ Voice2Machine: Local Voice Dictation

🎯 Purpose

The goal is simple:

Be able to dictate text anywhere in your operating system.

The idea is to transcribe audio using your local GPU for maximum speed and accuracy, regardless of the application you're using (code editor, browser, chat, etc.).

This project transforms a simple script into a robust modular application based on a Backend Daemon (Python), designed with Hexagonal Architecture to ensure maintainability, scalability, and absolute privacy.

---

📚 Documentation

The documentation is organized to serve different needs:

🚀 Exploration

• Quick Start: Start dictating in minutes.
• Glossary: Defines key terms like Daemon, Whisper, and REST API.

🛠️ Procedures

• Installation: Step-by-step guide for Ubuntu/Debian.
• Contributing: How to collaborate on the project.

⚙️ Reference

• Configuration: Adjust models, devices, and behaviors.
• Keyboard Shortcuts: Reference for global commands.
• REST API: HTTP endpoints documentation.
• Python API: Backend classes and methods reference.

🧠 Concepts

• Architecture: Hexagonal Design and system components.
• Decisions (ADR): Record of important technical decisions.

🔧 Maintenance

• Troubleshooting: Diagnosis and fixing common errors.
• Changelog: Project change history.