Text to speech

Text to speech, right in the browser

Paste your text, pick a voice and listen to it out loud. Handy for checking your own writing, for practising pronunciation, and for hearing a longer article when you cannot read. Everything is computed in your browser; the text is never sent anywhere.

Which voices there are

Amy and Ryan read in English. Both are neural voices that run inside the page: they sound the same on every computer and both can be saved as MP3. These are not the voices from Windows or from your phone, so it does not matter which of those you have.

The first time you use a voice its model downloads, about 63 MB. After that it is ready in the browser and reading starts at once, even offline.

What you can set

The voice, the reading speed, the volume and the quality of the resulting MP3. The text is read sentence by sentence, so you can see where it is and pause or resume at any point. Long text is split into shorter pieces by itself, so the reading does not stall halfway.

Frequently asked questions

Can the speech be saved as MP3?

Yes, with the Download MP3 button, for every voice on offer. The model produces the audio in the page and it is converted to MP3 straight away, so there is nothing to record and no screen to share.

Why are the Windows voices not here?

Because the browser will not let their audio out, so they could only be played, not saved. The list would then have two kinds of voices with different rules, and downloading would quietly hand you a different voice from the one you heard. We would rather offer only voices that can do both.

Is the text sent to a server?

No. Only the voice model is downloaded; the text itself stays in your browser and is spoken there.