What it does
Kokoro-FastAPI packages the Kokoro text-to-speech model, which turns written text into spoken audio, as a ready-to-run service. Its makers say it can generate hours of speech in minutes.
It works the same way as OpenAI's speech service, so apps built for that can use it instead. It speaks several languages, can mix voices, add word-by-word caption timings and handle long read-along text.
It runs in Docker on ordinary computers or with a graphics card for more speed, and many community apps, such as audiobook makers and Home Assistant add-ons, can use it.
Who it's for
Tinkerers and developers who want free, self-hosted text-to-speech for their apps.
Can I use it without coding?
With some setup. It runs with a single Docker command and has an optional web interface. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Windows, Linux, Server
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Install Docker on your computer.
- Start the ready-made Kokoro-FastAPI image, choosing the version for your hardware.
- Open the local web page or point your app at it to turn text into speech.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe