# MiraTTS Brings Qwen2 to Bilingual Speech Synthesis

> A new text-to-speech model from OpenMOSS leverages the Qwen2 architecture to generate speech in both English and Chinese.

Published by The Open Weights on Dec 17, 2025. Canonical: https://theopenweights.com/news/miratts-fmsw

## Key facts

- Company: YatharthS
- Model: MiraTTS
- Version: MiraTTS
- Category: Text → Speech
- Modalities: Text → Speech
- License: CC BY-NC 4.0 (Research only)
- Architecture: Qwen2ForCausalLM
- Precision: BF16
- Weights size: 1 GB
- Languages: English, Chinese
- Significance: minor
- Published: 2025-12-17
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/YatharthS/MiraTTS
- Canonical URL: https://theopenweights.com/news/miratts-fmsw

A new open-source text-to-speech model named MiraTTS has been released by the OpenMOSS team. The model is notable for its bilingual capabilities, generating speech in both English and Chinese, and for its foundation in the powerful Qwen2 language model architecture.

MiraTTS employs a two-stage design for speech synthesis. The first stage uses the Qwen2-based model to convert input text into a spectrogram—a visual representation of sound frequencies. This spectrogram is then passed to a separate vocoder model to produce the final audio waveform.

## From Research to Application

The model's architecture offers practical advantages for developers. MiraTTS supports exporting to the ONNX format, a standard that enables efficient inference across a wide range of hardware and platforms. This focus on deployment readiness, combined with its bilingual support, makes it a useful component for various non-commercial applications.

The model is available for experimentation on its [Hugging Face repository](https://huggingface.co/YatharthS/MiraTTS), released under a Creative Commons Non-Commercial license (CC BY-NC 4.0) that encourages academic and personal use.

## Get the model

- [Hugging Face](https://huggingface.co/YatharthS/MiraTTS)

## Sources

- [YatharthS/MiraTTS](https://huggingface.co/YatharthS/MiraTTS) — Hugging Face, Dec 17, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "MiraTTS Brings Qwen2 to Bilingual Speech Synthesis", The Open Weights, Dec 17, 2025, https://theopenweights.com/news/miratts-fmsw