Convert text into natural-sounding speech with Kokoro v1.0, an open 82M-parameter TTS model, or instantly via the Web Speech API.
Your text never leaves your device. Audio generation happens locally.
Runs entirely in your browser. Your data never leaves your device.
No. Your text never leaves your device. Audio generation happens locally using Kokoro v1.0 via WebAssembly, or the browser's built-in Web Speech API as a zero-download fallback.
If the Kokoro ONNX model cannot load, the tool automatically falls back to your browser's built-in speechSynthesis API. This requires ZERO model download and works immediately on Chrome, Edge, Safari, and Firefox.
Kokoro v1.0 is an English-only model: US voices af_heart (female) and am_michael (male), UK voices bf_emma (female) and bm_lewis (male). Spanish, Portuguese and Indonesian text is spoken by the browser's built-in Web Speech API, using whichever voices your operating system provides.
Yes. Kokoro-generated audio can be downloaded as WAV. When using the Web Speech API fallback, audio capture is limited by the browser — playback works but direct file export may not be available.
If you just finished with AI Text to Speech, the natural next steps are AI Speech to Text, AI Text Summarizer, AI Translator, or browse every tool in Local AI Tools.