# MOSS-TTS Aims for More Robust Speech Synthesis

> A new text-to-speech model introduces 'delay-pattern decoding' to solve common word skipping and repetition errors in parallel generation.

Published by The Open Weights on May 25, 2026. Canonical: https://theopenweights.com/news/moss-tts-v1-5-4pw8

## Key facts

- Company: OpenMOSS
- Model: MOSS-TTS v1.5
- Version: v1.5
- Category: Text → Speech
- Modalities: Text → Speech
- License: Other (Open weights, commercial use allowed)
- Architecture: MossTTSDelayModel
- Precision: BF16
- Weights size: 17 GB
- Languages: 31 languages
- Significance: minor
- Published: 2026-05-25
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/OpenMOSS-Team/MOSS-TTS-v1.5
- Canonical URL: https://theopenweights.com/news/moss-tts-v1-5-4pw8

The OpenMOSS team has released MOSS-TTS v1.5, a new model for multilingual text-to-speech synthesis. Built on the VITS architecture, the model is designed to generate natural-sounding speech in Chinese, English, and Japanese.

Many modern TTS systems use parallel decoding to generate audio quickly, but this approach can lead to instability, causing the model to occasionally skip or repeat words. This lack of reliability is a significant hurdle for using such models in production applications.

To address this, MOSS-TTS introduces a technique its creators call "delay-pattern decoding." This novel mechanism is designed to mitigate common generation errors, significantly improving the model's robustness and making the output more consistent and reliable.

The model is available on the [Hugging Face Hub](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-v1.5) for community use. While the code is licensed under the permissive MIT license, the model weights themselves are restricted to non-commercial research purposes.

## Get the model

- [Hugging Face](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-v1.5)

## Sources

- [OpenMOSS-Team/MOSS-TTS-v1.5](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-v1.5) — Hugging Face, May 25, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "MOSS-TTS Aims for More Robust Speech Synthesis", The Open Weights, May 25, 2026, https://theopenweights.com/news/moss-tts-v1-5-4pw8