Type colon (:) in the dialogue line to see the available emotion and intonation tags
Controls the maximum length of the generated audio (more tokens = longer audio).
Higher values increase adherence to the text prompt.
Lower values make the output more deterministic, higher values increase randomness.
Filters vocabulary to the most likely tokens cumulatively reaching probability P.
Top k filter for CFG guidance.
Adjusts the speed of the generated audio (1.0 = original speed).