VOICE MODELS
Can someone please tell me what the standard file structure is for these voice models? I would like to import one from a third party but I need to describe to them what format (file type) is required.
Bitsi
0
-
If you want to create a voice using an audio file, it’s best to have 15 minutes of clean audio from a single speaker. The presence of a different speaker, music, or background noise will greatly reduce the quality of the trained voice. If you plan to upload a third-party model, make sure it is in a .zip file.
0
Please sign in to leave a comment.
Comments
1 comment