The quality of a voice model improves with more audio from the target speaker. To create a voice, you need at least 5 minutes of clean audio. For optimal results 15 minutes is recommended.
Please note that the maximum allowed length per voice is 15 minutes.
Comments
8 comments
Nice
I love
pop
Hi Team
I try to upload my voice but it is so long?
Is it possible to add more voice data to my existing voice so that It can train the voice better and understand the tone, style and accent more.
Tawna
Hola pablo
Cómo estás
Please sign in to leave a comment.