About OfflineTTS

OfflineTTS is a free, privacy-first text-to-speech tool that runs entirely in your browser. Powered by Kokoro TTS, an open-source model with 82 million parameters, it delivers natural-sounding speech without sending any data to a server.

Our Mission

We believe speech synthesis should be accessible to everyone — without subscription walls, API keys, or data collection. By running inference directly in the browser, we eliminate server costs and privacy concerns simultaneously.

How It Works

When you first visit the tool, it downloads the Kokoro TTS model (~90MB for Small model) and caches it in your browser. After that, all text-to-speech conversion happens on your device using WebGPU (or WebAssembly as a fallback). Your text never leaves your computer. No data is sent to any server. Ever.

Technology

  • Kokoro TTS — 82M parameter open-source TTS model (Apache 2.0)
  • ONNX Runtime Web — browser-based ML inference via WebGPU/WASM
  • Astro — fast, SEO-optimized static site framework
  • Cloudflare Pages — edge CDN for global delivery

Open Source

Kokoro TTS is open-source under the Apache 2.0 license. OfflineTTS is built with love for the open-source community and privacy-conscious users everywhere.

Try It Now

54 voices. 9 languages. 100% free. 100% private.

Open TTS Tool