Suggestion for generation of long text like podcast

[ILG2021]

Checks

• This template is only for research question, not usage problems, feature requests or bug reports.
• I have thoroughly reviewed the project documentation and read the related paper(s).
• I have searched for existing issues, including closed ones, no similar questions.
• I am using English to submit this issue to facilitate community communication.

Question details

In single speaker podcast, emotions and tone of voice will constantly change, so I need to change ref audio constantly. Is there a way to solve this problem, can f5 tts generate emotions and tone depend on text?

[soc8ren]

If it doesn't need a lot of modulation, check the instructions for toml usage here.