Input image,to generate split video,and can be equipped with voice.~,digital people love to talk, love sports!
The language of the text and sound model must match,like英文文本配英文语音模型。
select voice model:
'A' => American English
“b” => British English
'j' => Japanese
'Z' => Chinese
“f”后缀female声,“m”后缀male声,like:ZF_xiaoxiao(female)。ZM_yunxi(male)。
Pack up