Fish Audio Drama 3: open-weight TTS that voices up to 16 characters in one script
What is it?
A text-to-speech model that handles up to 16 speakers in one script. Write stage directions in square brackets, like [whispering] or [laughing], and the delivery changes from that point on. It covers 83 languages and is a 35B mixture-of-experts model with about 3B active per token. Weights are on Hugging Face, code is in fishaudio/fish-speech on GitHub, and it's also in the fish.audio app and API (model: drama-3).
Why does it matter?
If you make audiobooks, game dialogue or ad mockups with several characters, you can now rough out the voice track without booking actors. Fish Audio says it scored 93.2% on Artificial Analysis' pronunciation robustness test, up from 88.1% for S2.1 ProVendor claim, and that exact strings like codes, paths and emails improved from 79.4% to 86.3%Vendor claim.
Maturity
GAWeights, app and API are all out. Companies with $500K or more in annual revenue, or anyone reselling it as a TTS service, need a separate license, and cloning a real person's voice without consent is prohibited.
How to track it
- Pricing: the API launch price ($10 per million characters) ends Nov 12; check the pricing page to see whether the $50 list price kicks in.
- Independent ranking: look for Drama 3 on the Artificial Analysis TTS leaderboard.
- Serving: follow the SGLang-Omni cookbook and fish-speech GitHub releases for wider local inference support.