omnibus
193 / 5,000
Speed

The voice model (about 90 MB) downloads once on first use and is then cached by your browser. Your text is never sent anywhere — the speech is made on your device.

  • 100% Free
  • No Sign-Up
  • No Credit Card
  • No Free Trial
  • No Pro Tier
  • No Watermarks

Nothing is uploaded. Just open it and start.

Turn text into natural speech

Free, no sign-up, no API key, and no limit on how much you convert. Paste your text, pick a voice, and get lifelike speech you can play here or download as an MP3. It runs on Kokoro, an open neural voice model that works entirely inside your browser — so your words never leave your device.

Natural neural voices

Kokoro's open-weight model — a long way from the robotic voice built into your browser.

Many voices

American and British, female and male, at the speed you choose.

MP3 or WAV

Download the result and use it in a video, a podcast or a slide deck.

Private & unlimited

Runs on your device — no sign-up, no key, no character cap, nothing uploaded.

Related tools

Virtual Live Band

A live band in your browser — drums, bass, keys, guitar, lead and percussion jamming in eight genres, each player switchable on the fly.

Live Focus Music

Endless generative ambient music for focus, meditation, and relaxation — five moods with several variations each, a layer mixer, and a session timer, synthesized live in your browser.

Live Psytrance

Endless psytrance generated live — Full-On, Progressive, Goa, Dark Forest and Psychill — with build-ups, drops and full-screen audio-reactive visuals.

Noise Generator

White, pink, and brown noise plus rain, ocean, and fan sounds for focus and sleep, with a sleep timer.

Frequently asked questions

Is it really free, with no limit?
Yes. The voice runs on your own device, so there is nobody paying per character and nothing to meter — no account, no API key, no watermark, and no cap on how much you convert. Most free text-to-speech sites are a front end for a paid cloud API, which is why they limit you to a few hundred characters or add a watermark.
Which voice does it use?
Kokoro, an open-weight 82-million-parameter speech model released under the Apache 2.0 licence. It is small enough to run in a browser tab yet rates well against far larger models, which is what makes free and private possible at the same time. It offers a range of American and British voices, female and male.
Is my text uploaded anywhere?
No. Your text stays in your browser and the speech is made on your device. The one thing that comes over the network is the voice model itself — about 90 MB, downloaded once from a public CDN on first use and then cached by your browser. After that the tool works offline.
Why is the first run slow?
Only the first one is. The model has to download (about 90 MB) and then warm up. Afterwards your browser has it cached, and speaking is a matter of seconds. Speed depends on your device — a recent laptop or phone renders several times faster than real time.
Can I download the speech as an MP3?
Yes — MP3 or WAV, both encoded on your device. MP3 is the small, plays-anywhere option for videos, podcasts and presentations; WAV is uncompressed if you're taking it into an editor.
Can I use the audio commercially?
The Kokoro model is Apache 2.0 licensed, which permits commercial use of what it produces, and we add no restriction of our own — the audio is yours. If it matters for your project, check Kokoro's own model card for the current terms rather than taking a web page's word for it.
How is this different from my browser's built-in speech?
The Web Speech API uses whatever voices your operating system ships, which vary by device and mostly sound robotic — and on many browsers it cannot be recorded or saved at all. Kokoro is a neural model that sounds markedly more natural, sounds the same on every device, and gives you a file you can download.
What about very long text?
The model reads a few hundred characters at a time, so longer text is split at sentence boundaries, read in passes and joined back together with a natural pause at each join. You'll see the progress as it goes, and you can stop part way.

Spotted a bug or have a suggestion?

Found something broken, have an idea, or just want to say thanks about any of our tools? Every message reaches a real person.