AuK-Flash: Fast 4-Step Speech Generation and Editing

News

• [2026/09/09] 🎉 AuK is now open-source. Code and model weights are publicly available. Try it on the 🤗 Demo Space or the 🤖 ModelScope Space!

Contents

• News
• Introduction
• Performance
• Model Architecture
• Supported Tasks
• Download the weights
• Citation
• License

Introduction

AuK is a 1.5B foundation model for speech generation and editing. Trained on millions of hours of diverse audio data, AuK supports zero-shot and instruction-based TTS, content and acoustic editing, paralinguistic editing, speech enhancement, and source separation through a unified natural-language instruction interface. AuK has two variants:

This repository contains the official weights for AuK-Flash, the distilled variant with fast 4-step inference.

Performance

Model Architecture

Supported Tasks

AuK exposes every task through the same natural-language instruction interface. The table below groups the supported tasks by category, with a short description and a link to its section in the Cookbook, which provides instruction templates plus CLI and Python examples.

Download the weights

🤗 HuggingFace

pip install -U "huggingface_hub[cli]"

# AuK-Base
hf download tencent/AuK --local-dir ./ckpts/AuK

# AuK-Flash (4-step distilled) 
hf download tencent/AuK-Flash --local-dir ./ckpts/AuK-Flash

# MLLM Encoder
hf download Qwen/Qwen2.5-Omni-3B  --local-dir ./ckpts/Qwen2.5-Omni-3B

🤖 ModelScope

pip install -U modelscope

# AuK-Base
modelscope download --model Tencent-Hunyuan/AuK --local_dir ./ckpts/AuK

# AuK-Flash (4-step distilled)
modelscope download --model Tencent-Hunyuan/AuK-Flash  --local_dir ./ckpts/AuK-Flash

# MLLM Encoder
modelscope download --model Qwen/Qwen2.5-Omni-3B --local_dir ./ckpts/Qwen2.5-Omni-3B

The expected directory structure is:

ckpts/
├── AuK/
├── AuK-Flash/          # optional
└── Qwen2.5-Omni-3B/

The model checkpoint contains the diffusion transformer and layer-fusion weights. The MLLM encoder and VAE are loaded from separate files at runtime, so missing text_encoder.* keys during checkpoint loading are expected.

For installation, inference, Gradio, ComfyUI, and fine-tuning, see the GitHub README and Cookbook.

Citation

Research using AuK can cite the following entry:

@misc{ma2026auktechnicalreportopensource,
  title={AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing},
  author={Ziyang Ma and Zhikang Niu and Wenming Tu and Tianrui Wang and Ruiqi Yan and Junxi Liu and Yanru Huo and Nickk Huang and Yang Liu and Qicong Xie and Zeyu Xie and Hui Wang and Haitao Li and Zixuan Jiang and Yalin Li and Jie Fang and Yifan Duan and Zeyue Tian and Guangzheng Li and Haina Zhu and Shuyi Wang and Jinwen Wang and Mingyu Cui and Tian Tan and Auden and Sen Liang and Steve Yves and Shan Yang and Liefeng Bo and Zilong Zheng and Kai Yu and Eng-Siong Chng and Xie Chen},
  year={2026},
  eprint={2609.08936},
  archivePrefix={arXiv},
  primaryClass={cs.SD},
  url={https://arxiv.org/abs/2609.08936},
}

License

AuK is released under the MIT License. See LICENSE for the full terms.