# Fish Audio launches Drama 3, a 35B open-weight TTS model

> The new model supports 83 languages, uses a mixture-of-experts design with about 3 billion active parameters, and is released under a revenue‑capped community license.

Oossa · 2026-10-14 · https://oossa.com/en/fish-audio-launches-drama-3-a-35b-open-weight-tts-model

Fish Audio released Drama 3, a text‑to‑speech model with a total of 35 billion parameters but only about 3 billion active at any time thanks to a mixture‑of‑experts (MoE) architecture. The model can follow plain‑language prompts and can generate speech in 83 languages. Fish Audio is making the model’s weights publicly available under a community license that caps revenue for commercial use.

## The facts

- 35 billion total parameters, ~3 billion active
- Supports 83 languages

## Why it matters

Developers can now build multilingual voice applications without paying for a proprietary API, as long as they stay within the license’s revenue cap.

## Sources & references

1. [Fish Audio Releases Drama 3, a 35B Open-Weight MoE Text-to-Speech Model](https://www.marktechpost.com/2026/10/14/fish-audio-drama-3-open-weight-tts-model/) – MarkTechPost, 2026-10-14

Last updated: 2026-10-14