# MOSS-TTS: A New Multilingual Text-to-Speech Model

> The new system from the OpenMOSS Team uses a novel 'delay-pattern' architecture to generate natural-sounding speech in Chinese, English, and Japanese.

Published by The Open Weights on Feb 6, 2026. Canonical: https://theopenweights.com/news/moss-tts-j0m7

## Key facts

- Company: OpenMOSS
- Model: MOSS-TTS
- Version: 1.0
- Category: Text → Speech
- Modalities: Text → Speech
- License: Other (Open weights, commercial use allowed)
- Architecture: MossTTSDelayModel
- Precision: BF16
- Weights size: 17 GB
- Languages: 20 languages
- Significance: notable
- Published: 2026-02-06
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/OpenMOSS-Team/MOSS-TTS
- Canonical URL: https://theopenweights.com/news/moss-tts-j0m7

The OpenMOSS Team has released MOSS-TTS, a new open-source model for generating high-quality speech from text. The system is multilingual, capable of producing audio in Chinese, English, and Japanese, making it a versatile tool for a range of voice applications.

The model's key innovation lies in its architecture. MOSS-TTS is a non-autoregressive system that uses a technique called a "delay-pattern." This approach allows it to model the rhythm and prosody of speech more effectively than some traditional methods, which can result in more natural-sounding intonation without generating audio one step at a time.

## A Two-Stage System

Like many modern text-to-speech systems, MOSS-TTS operates in two stages:

*   First, a text-to-spectrogram model converts the input text into a mel-spectrogram, a visual representation of the sound's frequency spectrum.
*   Second, a HiFi-GAN vocoder takes this spectrogram and synthesizes it into a final audio waveform.

The complete model, along with instructions for use, is available on the [Hugging Face Hub](https://huggingface.co/OpenMOSS-Team/MOSS-TTS). While the weights are openly accessible, they are released under a custom license that prohibits commercial use, a key consideration for developers looking to integrate the technology.

## Get the model

- [Hugging Face](https://huggingface.co/OpenMOSS-Team/MOSS-TTS)

## Sources

- [OpenMOSS-Team/MOSS-TTS](https://huggingface.co/OpenMOSS-Team/MOSS-TTS) — Hugging Face, Feb 6, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "MOSS-TTS: A New Multilingual Text-to-Speech Model", The Open Weights, Feb 6, 2026, https://theopenweights.com/news/moss-tts-j0m7