Pending benchmarksTracking since Oct 17, 2026
Is Drama 3 state of the art?Pending benchmarks.Announced Oct 13, 2026; no independent results yet.
Fish Audio's open-weight text-to-speech model. The lab says it gives word-level control over how words sound, with tone changes and voice shifts mid-sentence.
Announced facts
The details so far
- Lab
- Fish Audio
- Announced
- Oct 13, 2026
- API
- Live · drama-3
- Open weights
- Published
- Parameters
- 35B MoE / ~3B activeunsure
- Focus
- Text-to-speech with word-level control
- Languages
- 83unsure · Per third parties.
- Weights
- Hugging Faceunsure · Open-weight per the lab; Hugging Face hosting per third parties.
- API
- Model drama-3unsure · Per third-party posts.
- Serving
- Supported in vLLM-Omni
Tags marked unsure are not stated on the lab's own pages.
Next steps
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
Receipts
Sources
LABFish Audio announcement on Xx.com/FishAudio/status/2110038429199450126 · Oct 13, 2026Tracking continues until an independent board lists it.