Uploaded December 2025 | Updated November 2026, 9 hours ago
In this video, you’ll learn how to install the Chatterbox text-to-speech engine from resemble.ai on macOS and run it completely locally.
Instructions and sample code link:
whatmakeart.com/sound/text-to-speech-tts
Chatterbox GitHub repo:
github.com/resemble-ai/chatterbox
Install Homebrew
youtu.be/fQpcJc-kyVI
We’ll walk through the setup step-by-step (including Homebrew and FFmpeg), create a clean Python 3.11 virtual environment, install chatterbox-tts, and launch the included GUI demo so you can generate speech and clone a voice from an audio sample.
You’ll also see how to switch from the basic demo to a multilingual version with extra controls (like language and emotion options), then test a quick voice clone end-to-end on your Mac.
Chapters
00:00 What Chatterbox TTS is and what we’re building (local install + voice clone)
00:19 Chatterbox model overview and why running locally matters
00:35 Install Homebrew (prereq)
00:46 Install FFmpeg (prereq)
00:59 Create the project folder and move into it
01:12 Create a Python 3.11 virtual environment
01:40 Activate venv and upgrade tooling
01:57 Install chatterbox-tts with pip
02:14 Create the first GUI script file (demo app)
02:54 Run the script and open the local URL
03:24 Stop the server and prep for multilingual + emotion controls
03:39 Create the multilingual script file
04:08 Run the multilingual version (downloads additional models)
04:30 Multilingual Chatterbox GUI is ready locally
04:49 Upload an audio sample for voice cloning
05:05 Generate and play the cloned voice output
05:16 Final notes on quality and next steps
In this video, you’ll learn how to install the Chatterbox text-to-speech engine from resemble.ai on macOS and run it completely locally.
Instructions and sample code link:
whatmakeart.com/sound/text-to-speech-tts
Chatterbox GitHub repo:
github.com/resemble-ai/chatterbox
Install Homebrew
youtu.be/fQpcJc-kyVI
We’ll walk through the setup step-by-step (including Homebrew and FFmpeg), create a clean Python 3.11 virtual environment, install chatterbox-tts, and launch the included GUI demo so you can generate speech and clone a voice from an audio sample.
You’ll also see how to switch from the basic demo to a multilingual version with extra controls (like language and emotion options), then test a quick voice clone end-to-end on your Mac.
Chapters
00:00 What Chatterbox TTS is and what we’re building (local install + voice clone)
00:19 Chatterbox model overview and why running locally matters
00:35 Install Homebrew (prereq)
00:46 Install FFmpeg (prereq)
00:59 Create the project folder and move into it
01:12 Create a Python 3.11 virtual environment
01:40 Activate venv and upgrade tooling
01:57 Install chatterbox-tts with pip
02:14 Create the first GUI script file (demo app)
02:54 Run the script and open the local URL
03:24 Stop the server and prep for multilingual + emotion controls
03:39 Create the multilingual script file
04:08 Run the multilingual version (downloads additional models)
04:30 Multilingual Chatterbox GUI is ready locally
04:49 Upload an audio sample for voice cloning
05:05 Generate and play the cloned voice output
05:16 Final notes on quality and next steps










