Studio
LIVE
Synthesize speech from plain text, a .txt file, or a timestamped .srt. With SRT, each cue is fit to its subtitle window (natural pace by default, or strict frame-lock for lip-sync).
Voice
Intonation
Shape the delivery. Style takes inherit emotion from a recorded clip; pitch / whisper / accent are voice-design tags layered on top.
Markup in your text also works: **emphasis**, [pause], [pause 400ms], …
Input
0.5× slow1× normal2× fast