Kokoro TTS online, free and private in your browser

The model runs on your own computer, plays the first sentence while the rest renders, and gives you a WAV to download. When you press Start, your browser downloads the Kokoro-82M model once and keeps it in its cache. From then on everything happens in this tab. Your text is split into sentences, each sentence is turned into phonemes, and the model turns the phonemes into 24 kHz audio in the voice you picked. The first sentence starts playing as soon as it is ready, while the next ones render behind it.

English text goes through Kokoro's own English phonemizer, which also spells out numbers, prices and times. Spanish, French, Italian, Portuguese and Hindi go through eSpeak NG, the same phonemizer Kokoro uses for those languages, loaded only when you pick one of those voices. The inference runs in a background worker, so the page stays responsive.

Instead of typing, you can import a file: EPUB, PDF, Word (.docx), Markdown, HTML or plain text. The file is opened and read in this browser tab; nothing is uploaded. It opens in a full-screen reading view, with the chapters of an EPUB under Contents. Tap any sentence and the tool reads aloud from there, generating only a sentence or two ahead of what you hear, so a whole book never has to be rendered at once. The sentence being read is highlighted, and you can pause or tap another one at any time.

The same engine is set up for one job each on four other pages: read text aloud, an online EPUB reader, read a PDF aloud and hear your essay read back.

If you came looking for a text to voice or text to audio tool, this is one. Type or paste up to 1,500 characters, pick one of the 41 voices and press Generate: the text becomes speech in your browser, and Download WAV keeps it as a 24 kHz mono file that any video or audio editor opens. It is a free AI voice generator in the plain sense of the words: the voices are synthetic, there is no sign-up and no credit meter, and the Apache-2.0 license of Kokoro-82M allows commercial use. It does not clone a voice or imitate a person. For a script longer than one run, generate it in parts and join the files in your editor.

The tool picks the engine for you. There is no quality setting to get wrong: on WebGPU the tool always uses the full model, because the smaller quantized ones produce garbled speech there.

• WebGPU (graphics card): the full-precision model, a one-time 326 MB download. On a recent laptop, a 40-word paragraph takes about 3 seconds and the first sentence plays after about 1 second. Current Chrome, Edge and Safari on a computer have WebGPU.
• CPU (WebAssembly): the 8-bit model, a one-time 92 MB download, used when WebGPU is not available. It is slower than real time: expect the first sentence after 10 to 15 seconds and 20 to 40 seconds for the same paragraph, depending on your processor.
• Phones: the same 92 MB CPU model in a lighter setup that asks the browser for less memory and speaks in shorter pieces. It works on recent phones and is slower than on a computer: speech is generated more slowly than it plays, so there are pauses between sentences. If the download is interrupted, it resumes where it stopped.

Either way, the second visit skips the download: the model loads from the browser cache in a few seconds. On a computer, plan on about 1 GB of memory in the tab while it runs.

The voice decides the language. The tool offers the same 41 voices as the Sandbook app, with the app's names and descriptions:

• English: 28 voices, 20 American and 8 British, including Heart, Bella, Michael, Emma and George.
• Spanish: 3 voices (Dora, Alex, Santa).
• French: 1 voice (Siwis).
• Italian: 2 voices (Sara, Nicola).
• Brazilian Portuguese: 3 voices (Dora, Alex, Santa — distinct from the Spanish voices of the same names).
• Hindi: 4 voices (Alpha, Beta, Omega, Psi).

To audition a voice without loading anything, press the play button next to the voice picker, or listen to all the Kokoro voice samples. In this browser demo, speed runs from 0.5× to 2.0× (the app goes to 2.5×), applied inside the model, so a fast voice still sounds like a person talking quickly.

Download. Every generation of typed text can be saved as a 24 kHz mono WAV file. MP3 and M4A export are not available yet. Imported documents are read aloud in the page and have no audio download.

Usage rights. Kokoro-82M is published under the Apache-2.0 license, which allows commercial use. The audio you generate is yours; Sandbook claims nothing over it.

Limits. Typed text: up to 1,500 characters per generation, about a minute and a half of speech. Imported files: EPUB, PDF, Word (.docx), Markdown, HTML and plain text of any length; scanned PDFs (no text layer) and DRM-protected books cannot be read. The tool works best on a computer. It also works on recent phones, more slowly, and an older phone may not have the memory for it; the tool says so before downloading when that looks likely. Reading stops when the phone locks or the tab goes to the background. Closing the tab right after the first download can occasionally stop the browser from finishing its cache write, in which case the next visit downloads the model again.

Privacy. Your text and audio never leave your browser. A file you import is opened on your device and is not uploaded. The only files the tool fetches are the model, the voice you pick, for non-English voices the phonemizer, and the reader for the file type you import.

Credits. The tool is built on open-source software: Kokoro-82M (Apache-2.0), ONNX Runtime Web (MIT), Transformers.js (Apache-2.0), kokoro-js (Apache-2.0), eSpeak NG (GPL-3.0), PDF.js (Apache-2.0) and fflate (MIT).

This page is a demo of the model. Sandbook is the app: it runs the same Kokoro-82M model on iPhone, iPad and Mac through Apple MLX, fully offline, with all 41 voices and no length limit. It reads EPUB books and PDFs, web pages and (on iPhone and iPad) scanned pages aloud, highlights each word as it is spoken, and remembers where you stopped. Free, with no account and nothing to buy. It needs an iPhone 12 or later on iOS 18.2, or a Mac with Apple silicon (M1 or later) on macOS 15.2.

How the model runs on a phone is explained on the Kokoro TTS app for iPhone page. If you only need a phone to read the screen aloud, iOS already can: text to speech on iPhone with the built-in settings. And for how Sandbook compares with Speechify, NaturalReader and the other readers, see the iPhone reader alternatives.