Text is read out using VOICEVOX voices such as Zundamon and Shikoku Medan.
- Since speech synthesis is performed on-device, there is no need to communicate with a server and privacy is protected.
- You can choose from 30 voices (75 types).
- You can save the generated audio files and play and share them whenever you like.
*The time it takes to synthesize speech depends on the performance of the device and the amount of text, and can take from a few seconds to several tens of seconds.
- Since speech synthesis is performed on-device, there is no need to communicate with a server and privacy is protected.
- You can choose from 30 voices (75 types).
- You can save the generated audio files and play and share them whenever you like.
*The time it takes to synthesize speech depends on the performance of the device and the amount of text, and can take from a few seconds to several tens of seconds.
Open up
