Skip to content

A feature request for future versions #194

Description

@FloatySpaghetti

Hello, is it possible for the feature where the model able to copy the intonation of a speaking voice of one reference audio , and and use that intonation for other reference voice to generate the actual output?
kinda like what Index-tts2 has, cause right now, the model is just a bit too random and with out any emotion control that actually land.
thanks for the awesome work that you guys are providing btw!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions