Loading page
Loading page

AI · ElevenLabs alternative
Turn text into natural speech in your browser, and give your apps an OpenAI-compatible text-to-speech API.
Kokoro Web is a free AI voice generator. You type or paste text, choose a voice and accent, and it creates natural-sounding speech. It runs on Kokoro-82M, a small open-weight text-to-speech model that the README says ranks near the top of the TTS Arena leaderboard.
The self-hosted version adds an API that matches OpenAI's text-to-speech API. Apps built for OpenAI can switch to your server by changing the base URL and key.
It suits developers who need speech in their apps, content makers who want voice-overs, and anyone who wants a private text-to-speech tool. It is useful when you want to avoid paying per character to a cloud voice service.
Cloud voice APIs bill by usage and see every line you send. With Kokoro Web on your own service, the text stays on your server and there is no per-character fee. The API key in the Environment tab keeps strangers from using it.
The trade-offs are speed and range. Speech generation on a plain CPU server is slower than on a GPU, so long texts take time. The voices and languages are limited to what the Kokoro model offers, which is a smaller set than big commercial services. You also keep the image updated.
Containers: ghcr.io/eduardolat/kokoro-web:latest
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Kokoro Web, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Kokoro Web setup screen.