Directed speech generation
Turns scripts into expressive speech with natural-language control over emotion and pacing.
Loading page…
Audio and video / product dossier
Generate expressive speech in 83 languages with natural-language control of emotion, pacing, and delivery.
Product brief
Drama 3 is Fish Audio's latest AI voice model, built for performances you can direct. Turn scripts into expressive speech with natural-language control over emotion, pacing, whispers, laughter, and pauses — even within a single sentence. Create multi-character scenes, audiobooks, game dialogue, and narration across 83 languages. Available on the web, mobile, and API, with open weights for self-hosting under Fish Audio's community license.
Why we selected it
Fine-grained, natural-language direction of emotion, pacing, and delivery makes this useful beyond basic text-to-speech. Support for 83 languages, API access, and self-hostable weights under a community license broaden
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
Turns scripts into expressive speech with natural-language control over emotion and pacing.
Supports direction of whispers, laughter, and pauses, including changes within a single sentence.
Creates speech performances for scenes with multiple characters.
Supports speech creation across 83 languages.
Offers web, mobile, and API access, plus open weights for self-hosting under Fish Audio’s community license.
Best-fit use cases
FAQ
Use natural-language instructions to control emotion, pacing, whispers, laughter, and pauses, including within a single sentence.
Drama 3 supports multi-character scenes, audiobooks, game dialogue, and narration.
Drama 3 supports speech creation across 83 languages.
Drama 3 is available on the web, mobile, and through an API. Open weights are available for self-hosting under Fish Audio’s community license.