VoiceStudio: a free ElevenLabs alternative on your laptop

The free, open-source desktop app from the reel. Clone a voice from a short clean recording, design new voices from a description, dub videos and turn text into audiobooks, all on your own computer.

CostFree and open source (AGPL-3.0). Optional Pro version: $99 a year or $299 once.

DoesVoice cloning, voice design, video dubbing, audiobooks, dictation and transcription

Runs onWindows, Mac (Apple Silicon) and Linux. Older Intel Macs: app screen only, no local voice engine.

Proof76k stars on GitHub

Checked on 19 Oct 2026. Tools change fast, so the official page always wins if it says something different.

What you need first

1A decent computerAn NVIDIA graphics card (Windows/Linux) or an Apple Silicon Mac makes it fast. No graphics card works too, just slower. The site says about 8 GB of RAM is enough to start.

2Free disk spaceThe voice models download the first time you use them. The small CPU setup alone needs about 5 GB free.

3A clean recordingA short, clear recording of the voice you want to clone, with no music or background noise. Only use your own voice or one you have permission to use.

Step by step

Download the app

Go to the GitHub Releases page (link below) and pick your file: Windows .exe installer, Mac Apple Silicon .dmg, or Linux .AppImage / .deb.

Tip: The installers aren't signed by Apple or Microsoft yet, so your computer may show a warning the first time you open it. Only download from the official GitHub page or website.

Install the voice engine

Open the app. On first launch it sets up its local engine and asks before downloading a model. Let it finish, this can take a while on a slow connection.

Clone your voice

Open Voice cloning, choose a voice or add a clean reference recording of your own voice.

Type and generate

Type or paste your text and press Synthesize audio. Make a couple of takes and keep the best one.

Try the other workspaces

Dubbing: upload a video, pick the language to dub into, and it translates and re-voices it. Design: describe a voice ("warm British storyteller, slightly raspy") and it creates one. Stories: turn a script or book chapter into an audiobook.

Learn this with me

LIVE · THU 15 OCT

Live AI Masterclass

8 ways I make money with AI, built live step by step. Zero experience, no code, any age.

Thu 15 Oct · 6pm UK · 1pm ET
New date coming soon. See what you'll learn and the next date →
2 hours live + the replay
$150 one time · only 10 seats

Join the masterclass →

MEMBERS

The Unnerd AI Club

Not a course. A step-by-step system to make money with AI: pick one money path and follow every step.

52 live classes a year
Q&A 7 days a week + 1:1 calls with me
$100/month · cancel any time

Join the club →

The catch

Your computer does the work. Without a good graphics card or Apple Silicon Mac it's slow, and the models take up several GB of space.
Older Intel Macs aren't really supported. The app opens, but the voice engine has to run on another computer.
Only clone voices you have permission to use. The app's own rules say so, and cloning someone without consent can be illegal.
Commercial use has fine print. The app is AGPL-3.0, but each voice model has its own licence. Check the model's terms before using voices in paid work.

Official links

VoiceStudio on GitHub ↗Downloads (GitHub Releases) ↗Website ↗

Want to go further?

I show a new AI tool every week, and how to make money or save hours with it. No tech background needed.

Join the live masterclass Join the club

More free tools →

Unnerd AI · I'm not linked to VoiceStudio, I just think it's useful.