# Fish Audio's Drama 3 brings MoE to open TTS

> The open-source speech model pairs a 35B mixture-of-experts backbone with voice cloning and directed performance control.

Published by The Open Weights on Oct 1, 2026. Canonical: https://theopenweights.com/news/fish-audio-drama-3-5yhd

## Key facts

- Company: Fishaudio
- Model: Fish Audio Drama 3
- Version: 3
- Category: Text → Speech
- Modalities: Text → Speech
- License: Other (Open weights, commercial use allowed)
- Parameters: 35B (mixture of experts)
- Active parameters: 3B
- Architecture: FishOmniModel
- Precision: FP8
- Weights size: 39.6 GB
- Languages: zh, en, ja +
- Significance: notable
- Published: 2026-10-01
- Last verified: 2026-10-14
- Hugging Face: https://huggingface.co/fishaudio/drama-3
- Canonical URL: https://theopenweights.com/news/fish-audio-drama-3-5yhd

Fish Audio has released [Drama 3](https://huggingface.co/fishaudio/drama-3), an open-source text-to-speech model built on a mixture-of-experts architecture. The model carries 35 billion parameters in total but activates roughly 3 billion per inference pass, a design that aims to deliver the quality of a large model while keeping the compute cost of generation closer to that of a much smaller one.

Beyond raw synthesis, Drama 3 is pitched around two capabilities that matter for expressive speech: voice cloning and directed performance. The latter suggests finer control over how a line is delivered — tone, emotion, and pacing — rather than just converting text to flat narration. That makes it a candidate for use cases like audiobooks, dubbing, and interactive characters, where delivery is as important as intelligibility.

## Why it matters

Mixture-of-experts has reshaped open large language models over the past two years, but it remains relatively uncommon in speech generation. Applying the approach to TTS is a notable bet that the same efficiency gains can carry over to audio.

- **Multilingual:** the model lists Chinese, English, and Japanese among supported languages, with more indicated.
- **Efficient by design:** only about 3B of 35B parameters are active per pass.
- **Open weights:** the model is published on Hugging Face, though under a custom "other" license worth reviewing before commercial use.

As with any open release, the practical question is how Drama 3 holds up against both proprietary speech APIs and other open TTS efforts. For teams already building on open audio stacks, an efficient MoE model with explicit performance controls is a meaningful new option to evaluate.

## Get the model

- [Hugging Face](https://huggingface.co/fishaudio/drama-3)

## Sources

- [fishaudio/drama-3](https://huggingface.co/fishaudio/drama-3) — Hugging Face, Oct 1, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Fish Audio's Drama 3 brings MoE to open TTS", The Open Weights, Oct 1, 2026, https://theopenweights.com/news/fish-audio-drama-3-5yhd