Kitta Audio Docs
Control instructionsFine-grained emotion

Kitta Audio S1

Control S1 emotion and delivery with fixed parenthesized tags.

S1 fine-grained emotion

S1 uses a fixed set of English tags in parentheses. Put emotion tags at the beginning of a sentence; tone and sound tags can be placed where they should take effect.

(happy) Great, we made it! (sad) But not everyone could be here.
(sad)(whispering) I miss you so much.

Supported categories include basic and advanced emotions, tone markers, audio effects, (break), and (long-break). Use only listed tags and do not mix S1 () with S2 [].