The city of free, open AI tools My Stack
ForkopolisThe free store and magazine for open AI

Free Market / Voice

Voice3.6

Kokoro iconKokoro

The score measures project health and popularity. It is not a hands-on review. How it works

A very small text-to-speech model that sounds far better than its size suggests.

  • Some setup
  • Works on Windows, Mac, Linux

The openness label

Code
Open source, Apache-2.0
Models
Open weights
Runs
On your computer
Real cost
Free

What you need to run it

About 4 GB of memory. No graphics card needed.

These are our estimates for comfortable use. Enter your computer's specs to see a verdict on every tool.

  • 10,056 stars on GitHub
  • Last updated 2025-08-06

Quick answers

Is Kokoro free?

Yes. Kokoro is free and open source, released under the Apache-2.0 license. There is nothing to buy and no subscription.

Does Kokoro run on my own computer?

Yes. Kokoro runs entirely on your own computer, so your files and prompts stay with you.

What do I need to run Kokoro?

About 4 GB of memory. No graphics card needed. It works on Windows, Mac, and Linux.

Is Kokoro still maintained?

Kokoro was last updated on 2025-08-06, so development has slowed, but the tool still works.

What paid tools can Kokoro replace?

People use Kokoro as a free alternative to HeyGen, Synthesia, Colossyan, Pictory, and InVideo AI.

Checked by Forkopolis on November 11, 2026.

More in Voice

Whisper screenshot
Voice4.7

Whisper iconWhisper

Turns speech into text. Transcribes and translates recordings, interviews, and video audio.

  • Some setup
  • Windows · Mac · Linux
Code
Open source, MIT
Models
Open weights
Runs
On your computer
Real cost
Free
Get it
whisper.cpp screenshot
Voice4.5

whisper.cpp iconwhisper.cpp

A lightweight version of Whisper that transcribes quickly on ordinary laptops with no graphics card.

  • Some setup
  • Windows · Mac · Linux
Code
Open source, MIT
Models
Open weights
Runs
On your computer
Real cost
Free
Get it
RVC WebUI screenshot
Voice4.4

RVC WebUI iconRVC WebUI

Converts one voice into another, for dubbing and singing voice work.

  • Some setup
  • Windows · Linux
Code
Open source, MIT
Models
Open weights
Runs
On your computer
Real cost
Free
Get it