Add your text
Type or paste English text, or open a .txt, Word, PDF or EPUB file.
Paste text or open a document and hear it read aloud by a natural-sounding AI voice, with each sentence highlighted as it is spoken.
Pick from 16 American and British English voices, set the speed and download the speech as MP3 or WAV.
Type or paste English text, or open a .txt, Word, PDF or EPUB file.
Pick an American or British voice, listen to a sample and set the speed.
Press Play to hear it with each sentence highlighted, or download the speech as MP3 or WAV.
Create pictures and clips for your video, podcast or presentation with WaveSpeed AI.
Create pictures and graphics from a short description.
Turn an idea or a still image into a short video clip.
Turn a picture into a 3D model.
$1 in free credits for eligible new accounts. No card needed. Generators have separate account and credit requirements. The text to speech tool is free.
Yes. Listen and download as much as you like with no account and no watermark.
No. The voice runs in your browser, so your text never leaves your device. The first time, the browser downloads the voice files (about 180 MB); after that they load from its storage.
English, with American and British voices. Text in other languages is skipped or read with English pronunciation, so it won't sound right.
Yes. The speech you create is yours to use, including in commercial projects, with no attribution needed.
You can listen to long texts, even a whole book: sentences are prepared just before they are read. Downloads are limited to about an hour of speech (60,000 characters) per file, because the file is built in your browser's memory.
Once the voice is loaded, playback starts after the first sentence is ready, usually within a few seconds, and the next sentences are prepared while you listen. On a recent computer speech is created about twice as fast as it plays; older computers and phones may pause briefly between sentences. Saving a file takes roughly half its length on a recent computer (about 5 minutes for 10 minutes of speech) and longer on phones.
Yes. The speed setting changes how fast the voice speaks, not the pitch, from half speed to twice as fast.
Words are pronounced from a large dictionary; unusual names and new words are guessed from their spelling. Writing a word the way it sounds, or spelling out numbers and abbreviations, usually fixes it.
Paste text, pick a voice and press Play. Free, no sign-up.