Turn text into natural-sounding speech and clone voices on your own computer with coding needed.
AI Voice Cloner is a local text-to-speech and voice cloning app that runs entirely on your machine, giving you fast performance and full control over your data. With a simple browser-based interface, you can generate natural-sounding speech, clone voices from short samples, and manage models stored securely on your own system.
It works across Windows, macOS, and Linux, supports both CPU and NVIDIA GPU acceleration, and delivers a smooth, private experience without relying on the cloud.
- Private data
- Free to run over and over again
- Uses your local computer power
- π¬ Community
- π Newsletter
- π Shop
- π Courses
- Text-to-Speech in your browser
- Voice cloning (bring a short sample)
- Local models saved under your control
- Simple, clean UI
- Works on Windows, macOS, and Linux
- CPU or NVIDIA GPU acceleration
- Simple & easy to use web UI
- Models stored locally
-
Download Docker Desktop
-
Install Docker Desktop on your computer, and create an account (it's free)
-
Open the Docker Desktop application & login with your account credentials
-
Click here & fill out the form
-
Click "Submit" on the form to generate a
.zip
package (it will download to your computer) -
Open the
.zip
file that downloaded to your computer and put it on your Desktop -
Open the application on your computer called
Terminal
(if you use Mac) orcmd
(if you Windows) -
Copy this:
cd ~/Desktop/ai-voice-cloning-app && docker compose up
-
Paste it into your terminal application and press the Return (enter) key
-
Wait for it to boot up, then click here: http://localhost:80
- Start Docker desktop app
- Open your terminal and navigate to the
ai-voice-cloner
app's folder on your computer - Type
docker compose up
and press enter - Let the app boot up, and then visit this address in your browser:
http://localhost:80
Version: 1.0.0 Last Updated: 8/23/2025