Text to speech — natural voices, or your own

Type any text, pick a voice — or record ten seconds of your own — and get natural speech in English, French, German, Spanish, Portuguese or Italian. It all runs in your browser, so it's free and unlimited, and your files are never uploaded.

  1. Your text

    0 characters · about 0:00

    Formatting — add pauses & pronunciation

    Type these anywhere in your text. They shape the speech but aren't read aloud.

    Pause

    Insert a real silence.

    [pause] · [pause 1.5s] · [pause 800ms]

    Pronunciation

    Respell a tricky name or acronym.

    [Nguyen](win) · [GIF](jif) · [Siobhan](shivawn)

  2. Voice & speed

  3. Speech

How to turn text into speech

  1. Paste your text

    Type or paste the text you want spoken. It never leaves your browser.

  2. Pick a language and a voice

    Choose from 24 voices in each of six languages, plus 28 more in English, hear any of them first, or record ten seconds of your own voice.

  3. Generate & download

    The voice model runs on your device — the first run downloads it, then it stays on this device. Play the audio back and download it as a WAV file.

Why generate speech here

Your text is never uploaded

Speech is generated 100% in your browser — no server, no account, no upload. Ideal for scripts, drafts and anything confidential.

Natural voices, six languages

Pocket TTS by Kyutai speaks English, French, German, Spanish, Portuguese and Italian with 24 voices each, and can learn your voice. Kokoro adds 28 English voices with adjustable speed.

Free & unlimited

Because synthesis happens on your device, there's no per-character cost and no cap. Generate as much speech as you like.

Your own voice

Record ten seconds of yourself reading and every sentence after that is spoken in your voice. The model learns your voice from the recording on your device, and keeps the recording only if you ask.

Questions

Is my text uploaded to a server?
No. The voice model is downloaded to your browser and runs on your own device — your text never leaves it.
What do I get to download?
A standard 48 kHz mono WAV file, ready to play anywhere or drop into a video editor. (The voice itself renders at 24 kHz; the download is resampled to the 48 kHz video timelines use.)
Which voices and languages are supported?
Six languages — English, French, German, Spanish, Portuguese and Italian — with 24 voices each from Pocket TTS by Kyutai, plus 28 English voices from Kokoro-82M. You can also record your own voice.
Is it really free?
Yes — free and unlimited. There's no account and no metering because the model runs on your device, not our servers.
Why is the first run slower?
The first run downloads the voice model once, then it's cached in your browser, so later generations start quickly.
Does it need a fast computer?
No graphics card is needed. Pocket TTS runs on your processor through WebAssembly; Kokoro uses your GPU (via WebGPU) when it can and your processor otherwise. Phones work too, just more slowly.
How can I check that my text is not being uploaded?
Open your browser's developer tools, switch to the Network tab, and generate some speech with it open. On the first run you will see the voice model download once — about 120 MB for Pocket TTS, or from about 86 MB for Kokoro, depending on the voice you pick — and after that it is cached. What you will not see, on any run, is a request carrying your text. Then sort that list by size: the largest thing the page sends is a few kilobytes of analytics, nowhere near the length of a script. This page loads analytics and advertising like most websites do, which is why the claim is scoped precisely: your files are never uploaded.