Yes. Providing more audio of the target speaker will enhance the voice model. While the minimum length is 15 minutes, members of the community have ad great success with up to 2 hours of audio.
Yes. Providing more audio of the target speaker will enhance the voice model. While the minimum length is 15 minutes, members of the community have ad great success with up to 2 hours of audio.
Comments
2 comments
Nice
I love
Please sign in to leave a comment.