Kokoro
A small, fast, good-sounding voice model.
New to this? What open source means and how to read this page.
Want to run it? Read the voice guide: install and your first audio file.
What it is
A lightweight open text-to-speech model (82 million parameters) that runs quickly, even without a big GPU.
Good for
Quick narration on an ordinary computer.
The catch
It has fixed voices and no voice cloning, and fewer languages than ElevenLabs. The last code update was in August 2025.
Facts checked on 12 October 2026. We have not yet run a hands-on test of this tool. When we do, it gets a "Tested" mark here. Approximate US list prices for an individual plan, from third-party price trackers checked on 12 Oct 2026. Monthly billing where it exists. Regions, taxes and promotions change them. Confirm at the vendor before you decide.
More in AI voice & music
Open text-to-speech with voice cloning.
Replaces: ElevenLabs
Fast, local text-to-speech.
Replaces: ElevenLabs
Voice cloning from a short sample.
Replaces: ElevenLabs