drama3-small demo

Voice

Preset voices only. All output is synthetic speech.

Text

0 / 400

Expression tags

Point tags anywhere in the line: [laughs] [sighs] [gasps] [pause] [hesitates] [clears throat] [coughs]

Spans: <whisper>…</whisper> <emphasis>…</emphasis> <slow>…</slow>

Style (English, at the start): [with heavy, deflated sadness] [softly, whispering as if someone might overhear] [icy calm, barely containing anger]

Director's note: Direction: calm and reassuring. Slow down at the end. then a new line Line: …

Parameters

Temperature Top-p Top-k Max pause Pause fix is always on: silence longer than this is cut short, runaways are stopped. Speed Exact, pitch-preserving time-stretch after generation. Pace Asks the model itself to speak slower or faster. Max length Seed

Voice

Text

Parameters

Recent