Input an image to generate a leg split video.
The text language and the voice model language must match, e.g., English text with an English voice model.
Select Voice Model:
'A' => American English
“B” => British English
'j' => Japanese
'Z' => Chinese
Suffix "f" for female voice, suffix "m" for male voice, e.g., ZF_xiaoxiao (female), ZM_yunxi (male).