- Speech synthesis is performed on-device, eliminating the need for server communication and protecting privacy.
- Choose from 39 voices (113 types).
- Generated audio files can be saved and played back or shared at any time.
- Can be used as a text-to-speech engine. (Settings app > Accessibility > Text-to-speech settings > Preferred engine)

*Speech synthesis time depends on the device's performance and the amount of text, and can take anywhere from a few seconds to several tens of seconds.
*When using the generated voices, please follow the terms and conditions of each voice library.