Skip to main content
🎤 Luca Berton is speaking at Red Hat Summit & KubeCon EU 2026!Learn more →
beginner

Clone your voice locally

You will record a clean reference clip and use MLX to run text-to-speech models on your Mac. You compare three local engines to find the best speed and sound quality for your needs. You check every generated take with Whisper to ensure accuracy before finalizing your audio. You combine the checked takes into a single narration track for your video.

You learn how to prepare audio using FFmpeg to remove noise and set loudness. You adjust model settings to control the delivery and emotion of the cloned voice. You apply consent and disclosure rules when using synthetic voices in your content. You finish with a narrated video that meets standard loudness levels.

6 lessons22mUpdated November 2026

What you'll learn

  • Run text-to-speech models locally using MLX on Apple Silicon
  • Prepare a clean reference clip using FFmpeg commands
  • Clone a voice with Chatterbox and adjust delivery settings
  • Compare Qwen3-TTS and VoxCPM for speed and quality
  • Check audio accuracy with Whisper and narrate a video

Who this is for

  • • Developers moving into DevOps or infrastructure roles
  • • System administrators learning modern tooling
  • • CS students building practical skills

Prerequisites

  • • Mac with Apple Silicon
  • • uv installed via Homebrew
  • • ffmpeg installed via Homebrew

Course content

2 modules, 6 lessons, 22m of video

Module 1

3 lessons, 12 min
1

4 min

The learner runs a text-to-speech model locally on an Apple Silicon Mac using MLX to generate audio. The lesson demonstrates how to measure the model's speed and memory usage while playing the generated voice.

2
Prepare a good reference clip

5 min

The learner prepares a reference clip for voice cloning, learning the requirements for a good clip and how to clean a raw clip using FFmpeg. This lesson demonstrates the difference in the resulting voice clone when using a clean reference clip versus a noisy one.

3
Clone a voice with Chatterbox

4 min

The learner clones a voice using Chatterbox, an open model, and then modifies the voice's delivery using settings like exaggeration and CFG weight. The lesson also demonstrates how the multilingual model can speak a different language, such as Italian, using an English reference clip.

Module 2

3 lessons, 11 min
4
Compare Qwen3-TTS and VoxCPM

4 min

The learner compares Chatterbox, Qwen3-TTS, and VoxCPM2 by examining their time, memory usage, and sound quality when cloning a voice. The lesson details the technical differences between the three local voice cloning engines.

5
Check every take with Whisper

4 min

The learner generates one audio take per paragraph of a script and uses a script to check each take with Whisper for accuracy. The process allows for re-generating only the takes that fail the comparison, up to three rounds.

6
Narrate a video

4 min

The learner converts checked takes into a narration track and combines it with a screen recording. The lesson also covers the rules of consent and disclosure when using a cloned voice.

Get started

Start Free Lesson

First lesson is always free — no signup required

This course includes

6 hands-on lessons
Beginner level
22m total
Final assessment

Want all courses?

See Pro plan →

Your instructor

Luca Berton

Founder and CEO, Open Empower. About the author

More in AI Homelab on a Mac mini

All courses in this track

Turn a Mac mini into a reproducible homelab server

You will turn an Apple Silicon Mac mini into an always-on home server. You start by planning hardware choices and initializing a Git repository to track your setup steps. This foundation ensures your configuration is documented and ready for automation. You then configure remote access using SSH and Tailscale for secure connectivity. You also adjust power settings to keep the machine running continuously without interruption. Next, you use Homebrew with a Brewfile to manage software packages consistently. You create a Makefile that journals every command and output for full reproducibility. Finally, you add a read-only health check to verify system status. You learn to rebuild the entire setup on a clean machine from your repository.

Beginner · 4 lessons · 15 min · Updated Nov 2026

Preview free lesson

Virtual machines on Apple Silicon

You will build a Linux virtual machine on your Apple Silicon Mac using Colima and the Virtualization framework. You will point Docker to this VM and manage it with simple commands. You will share files between your Mac and the VM using virtiofs mounts. You will run AMD64 container images efficiently using Rosetta translation instead of slow emulation. You will size your VM correctly for your specific Mac hardware to avoid resource issues. You will create a plain Ubuntu VM with Lima for lab environments. You will configure launchd to start your VM automatically when you log in. You will learn to stop and clean up these virtual machines when you are done.

Beginner · 6 lessons · 20 min · Updated Nov 2026

Preview free lesson

Kubernetes on your Mac

You will build a multi-node Kubernetes cluster on your Apple Silicon Mac using kind. You start by creating a single-node cluster and then expand it to three nodes using a configuration file. You install applications with Helm and reach them from your Mac using ingress or Gateway. You also manage persistent storage and resource limits for your pods. You finish by tearing down and rebuilding the entire environment in minutes. You use a Makefile to automate the setup and cleanup process. This ensures your cluster is reproducible and easy to manage. You gain hands-on experience with a real cluster that runs entirely on your laptop.

Beginner · 6 lessons · 23 min · Updated Nov 2026

Preview free lesson