Text to Speech
Mode:

Language:

TTS Base Voice:

The generated audio will be applied voice conversion to the target voice.

Target:


Speed:
Change the speed of the generated audio

Pitch:
Shift the pitch of the generated audio by semitones

Output File Extension:



Input text:
Our model currently works best with spoken Cantonese. You sentence should not end with a period, and should not contain any special characters. For best results, please avoid using English words and numbers.
Your input text will be translated into Cantonese before generating the audio.


Enhance the audio quality with improved the audio clarity. It may take longer time to generate the audio.