Text to Speech
Type or paste any text, choose a voice, adjust speed and pitch, then listen instantly. Everything runs in your browser with your system voices — nothing is uploaded. Sentence-by-sentence mode highlights each sentence as it is read and lets you skip ahead.
Voice quality: depends on voices installed in your browser/system. Built-in Chinese voices are often robotic; for higher-quality neural Chinese voices see the note below after pressing Speak.
Ready.
About Chinese voice quality: this page uses voices already installed in your browser or operating system (e.g. Windows "Huihui / Yaoyao / Kangkang", macOS "Ting-Ting"). Most are traditional single-speaker voices. If you need more natural neural Chinese voices, the site roadmap includes an optional cloud voice tier. For now, try switching voices, lowering the speed to about 0.8–0.9, or read shorter sentences.
How does browser text-to-speech work?
The page drives the speech synthesis engine built into your browser, which in turn uses the voices installed on your operating system — that is why the voice list differs from machine to machine, and why a voice you pick may not exist on another reader’s device. Speed, pitch and volume are playback parameters the engine applies as it speaks; sentence-by-sentence mode splits the input at sentence boundaries so each sentence is highlighted as it is read and can be skipped.
Output quality is a property of the installed voices, not of the page — installing better system voices improves it, and neither your text nor the audio is uploaded anywhere.
