Dialogue Audio

This generates realistic two-speaker conversations using Dia TTS through the inference.sh CLI. You write dialogue with [S1] and [S2] speaker tags, and it assigns distinct voices automatically. The punctuation actually matters here—exclamation points add energy, ellipses create hesitation, parenthetical sounds like (laughs) work as expected. Good for podcast intros, explainer dialogues, or character conversations where you need natural back-and-forth without the complexity of ElevenLabs voice selection. The script writing tips are solid—write like people talk, not like they write, and break up monologues into actual exchanges.