Fish Audio Drama 3

Fish Audio Drama 3 is an AI text-to-speech model built for directed voice performances. Instead of simply generating speech, it lets you describe performances in natural language — controlling emotion, pacing, whispers, laughter, and pauses, even within a single sentence. It supports multi-character scenes, audiobooks, game dialogue, and narration across 83 languages, and is available on web, mobile, and API with open weights for self-hosting under Fish Audio's community license.