Controllable Text-to-Speech for over 7000 Languages

The biggest thank you to Hugging Face🤗 for sponsoring the GPU for this space!
To get the code, models, additional features, and more information, check out our toolkit: https://github.com/DigitalPhonetics/IMS-Toucan

Text input

Select the Language of the Text (type on your keyboard to find it quickly)

Prosody Creativity

0 0.8

Faster - Slower

0.7 1.3

Random Seed for the artificial Voice

0 10

Gender of artificial Voice

-10 10

[OPTIONAL] Voice to Clone (if left empty, will use an artificial voice instead)

Speech

Visualization