MODEL
Tags in brackets are performed rather than spoken. You can also enter your own tags in English.
Lower values produce more emotion and variation; higher values produce a steadier, more monotone voice.
How closely the result matches the original voice.
MODEL
Tags in brackets are performed rather than spoken. You can also enter your own tags in English.
Lower values produce more emotion and variation; higher values produce a steadier, more monotone voice.
How closely the result matches the original voice.