Question 1

Will the text be uploaded to the server?

Accepted Answer

No. Reading is done locally in the browser using your device's system speech engine. The input text never leaves your device and is not uploaded to any server.

Question 2

Why are the available voices different?

Accepted Answer

Available voices are provided by your operating system and browser. Different systems (Windows / macOS / Android / iOS) have different built-in voices and languages. You can install additional voice packages in system settings.

Question 3

Can the reading be saved as an audio file like MP3?

Accepted Answer

The browser's speech synthesis interface only supports real-time reading and does not have a standard way to export audio files directly. If you need an audio file, use the 'Recording Tool' or system screen recording to capture speaker output while playing.

Question 4

Does it support Chinese and other languages?

Accepted Answer

Yes, it does. As long as the system has the corresponding language voice package installed, you can read Chinese, English, Japanese, and more; simply select the voice with the appropriate language label in the dropdown.

Text to Speech

Frequently Asked Questions