MOSS-TTS-Nano

News

• 2026.4.10: We release MOSS-TTS-Nano. A demo Space is available at OpenMOSS-Team/MOSS-TTS-Nano. You can also view the demo and more details at openmoss.github.io/MOSS-TTS-Nano-Demo/.

Demo

• Online Demo: https://openmoss.github.io/MOSS-TTS-Nano-Demo/
• Hugging Face Space: OpenMOSS-Team/MOSS-TTS-Nano

Contents

• News
• Demo
• Introduction
  • Main Features
• Supported Languages
• Quickstart
  • Environment Setup
  • Voice Clone with infer.py
  • Local Web Demo with app.py
  • CLI Command: moss-tts-nano generate
  • CLI Command: moss-tts-nano serve
• MOSS-Audio-Tokenizer-Nano
• License
• Citation
• Star History

Introduction

MOSS-TTS-Nano focuses on the part of TTS deployment that matters most in practice: small footprint, low latency, good enough quality for realtime products, and simple local setup. It uses a pure autoregressive Audio Tokenizer + LLM pipeline and keeps the inference workflow friendly for both terminal users and web-demo users.

Main Features

• Tiny model size: only 0.1B parameters
• Native audio format: 48 kHz, 2-channel output
• Multilingual: supports Chinese, English, and more
• Pure autoregressive architecture: built on Audio Tokenizer + LLM
• Streaming inference: low realtime latency and fast first audio
• CPU friendly: streaming generation can run on a 4-core CPU
• Long-text capable: supports long input with automatic chunked voice cloning
• Open-source deployment: direct python infer.py, python app.py, and packaged CLI support

Supported Languages

MOSS-TTS-Nano currently supports 20 languages:

Quickstart

Environment Setup

We recommend a clean Python environment first, then installing the project in editable mode so the moss-tts-nano command becomes available locally. The examples below intentionally keep arguments minimal and rely on the repository defaults. By default, the code loads OpenMOSS-Team/MOSS-TTS-Nano and OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano.

Using Conda

conda create -n moss-tts-nano python=3.12 -y
conda activate moss-tts-nano

git clone https://github.com/OpenMOSS/MOSS-TTS-Nano.git
cd MOSS-TTS-Nano

pip install -r requirements.txt
pip install -e .

If WeTextProcessing fails to install from requirements.txt, try installing it manually in the same environment:

conda install -c conda-forge pynini=2.1.6.post1 -y
pip install git+https://github.com/WhizZest/WeTextProcessing.git

Voice Clone with infer.py

This repository keeps the direct Python entrypoint for local inference. The example below uses voice clone mode, which is the main recommended workflow for MOSS-TTS-Nano.

python infer.py \
  --prompt-audio-path assets/audio/zh_1.wav \
  --text "欢迎关注模思智能、上海创智学院与复旦大学自然语言处理实验室。"

This writes audio to generated_audio/infer_output.wav by default.

Local Web Demo with app.py

You can launch the local FastAPI demo for browser-based testing:

python app.py

Then open http://127.0.0.1:18083 in your browser.

CLI Command: moss-tts-nano generate

After pip install -e ., you can call the packaged CLI directly:

moss-tts-nano generate \
  --prompt-speech assets/audio/zh_1.wav \
  --text "欢迎关注模思智能、上海创智学院与复旦大学自然语言处理实验室。"

Useful notes:

• moss-tts-nano generate writes to generated_audio/moss_tts_nano_output.wav by default.
• --prompt-speech is the friendly alias for the reference audio path used by voice cloning.
• --text-file is supported for long-form synthesis.

CLI Command: moss-tts-nano serve

You can also launch the web demo through the packaged CLI:

moss-tts-nano serve

This command forwards to app.py, keeps the model loaded in memory, and serves the local browser demo plus HTTP generation endpoints.

MOSS-Audio-Tokenizer-Nano

Introduction

MOSS-Audio-Tokenizer is the unified discrete audio interface for the entire MOSS-TTS family. It is built on the Cat (Causal Audio Tokenizer with Transformer) architecture, a CNN-free audio tokenizer composed entirely of causal Transformer blocks. It serves as the shared audio backbone for MOSS-TTS, MOSS-TTS-Nano, MOSS-TTSD, MOSS-VoiceGenerator, MOSS-SoundEffect, and MOSS-TTS-Realtime, providing a consistent audio representation across the full product family.

To further improve perceptual quality while reducing inference cost, we trained **MOSS-Audio