about this book
This book teaches you how to run a large language model (LLM) on your own computer and build a fully functional voice-enabled AI chat application, from scratch.
This is a Mac-first book. The main path uses macOS, Terminal, Homebrew, VS Code, Python, Ollama, MLX Whisper, and Streamlit. It does not use Swift or SwiftUI; Python is used because the local AI tooling ecosystem around Ollama and Streamlit is easier to reproduce for hands-on learning.
By the end of this book, you will speak naturally into your microphone, watch your words be transcribed on screen, and receive a streaming AI response—all running entirely on your Mac. No internet connection required, no subscription fees. Your voice data, your conversations, and the AI’s responses never leave your machine.
You will accomplish this using five key tools:
- Ollama—A runtime that downloads and runs open source LLMs on your machine
- MLX Whisper—Apple silicon–optimized speech recognition that transcribes your voice locally
- VS Code—The editor used to write, run, and organize the Python files
- Python—A beginner-friendly programming language
- Streamlit—A framework for building web applications with Python
Along the way, you will learn the terminal, package management, Python programming fundamentals, API interaction, and web application development. Each concept builds on the last, and every step is explained from the ground up.