Can I use the audio in a video or a podcast?

Yes. Kokoro's model and voices are released under the Apache 2.0 licence, which allows any use, including commercial, and this page adds no conditions of its own.

Which languages does it speak?

English only for now, in American and British accents. Kokoro has voices for other languages, but each needs its own pronunciation rules.

Why is the first time slow?

The voice model, about 92 MB, is downloaded once and kept by your browser. After that it starts in a few seconds, and on most computers makes speech about as fast as it plays. Where the browser can use the graphics card (WebGPU), ticking Use the graphics card switches to the full model - a 326 MB download - which is many times faster.

Does the text I type leave my computer?

No. The model is downloaded from huggingface.co and the dictionaries from jsDelivr, and everything is spoken on your own computer.

Stays on your computer Downloads the Kokoro voice model from huggingface.co the first time (92 MB, or 326 MB to use the graphics card) and the pronunciation dictionaries (about 6 MB) from jsDelivrHow this works

Text to speech free

Natural English voices - American and British - reading any text aloud, made by an AI model in your browser. Save it as MP3 or WAV; no sign-up, no limit, nothing uploaded

Text

190 / 60,000 characters · about 13 seconds

Accent

VoiceSpeed 1.0×

The first time, the voice model (92 MB) and the pronunciation dictionary (about 6 MB) are downloaded; your browser keeps them.

Pronunciation

A name or word read wrongly can be respelled the way it sounds - "Siobhan" as "shiv awn" - and is read that way everywhere in the text.

About this text to speech

The voices are Kokoro, an open AI speech model that sounds far more natural than the robotic voices built into computers and phones, and that until now meant a paid online service with a character limit. Here it runs in your browser: type or paste any English text, pick one of 27 American and British voices, and listen or save the result as an MP3. There is no sign-up, no limit on how much you convert, and the text never leaves your computer. It is free to use, with no account and no upload limit, and it runs entirely in your browser: nothing is uploaded, and while the page stays open, a feature you have already used keeps working offline.

Before a voice can read, every word has to become sounds. This page does that itself with the same American and British pronunciation dictionaries Kokoro was trained with, over 180,000 words each. It writes out numbers, money, dates and times as they are said, spells acronyms like FBI letter by letter, and guesses the rest with a small neural model. A word read wrongly can be respelled.

What you can do

Turn text into natural speech in 27 American and British English voices
Change the speed from half to double
Listen as it is made, then save the audio as MP3 or WAV
Convert long text - up to 60,000 characters, about an hour of speech - in one go
Fix how a name or word is said with a respelling
Free, with no watermark, no limit and no upload

How to convert text to speech

Type or paste your text.
Choose American or British, a voice and a speed.
Press Play to listen, or Make audio only, then Save MP3 or Save WAV.

Questions

Can I use the audio in a video or a podcast?: Yes. Kokoro's model and voices are released under the Apache 2.0 licence, which allows any use, including commercial, and this page adds no conditions of its own.
Which languages does it speak?: English only for now, in American and British accents. Kokoro has voices for other languages, but each needs its own pronunciation rules.
Why is the first time slow?: The voice model, about 92 MB, is downloaded once and kept by your browser. After that it starts in a few seconds, and on most computers makes speech about as fast as it plays. Where the browser can use the graphics card (WebGPU), ticking Use the graphics card switches to the full model - a 326 MB download - which is many times faster.
Does the text I type leave my computer?: No. The model is downloaded from huggingface.co and the dictionaries from jsDelivr, and everything is spoken on your own computer.

Built by John McMillan, a senior full-stack engineer. Open to remote roles: hire me.

Report a problem or suggest a feature