Sponsored by
APIMaster
tencent / AuK
Model's Last Updated: September 10 2026
text-to-speech
Introduction of AuK
Model Details of AuK
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:
| Model | Description | Weight |
|---|---|---|
| AuK | Base model for high-quality generation | 🤗 Hugging Face · 🤖 ModelScope |
| AuK-Flash | Distilled model for fast 4-step inference | 🤗 Hugging Face · 🤖 ModelScope |
This repository contains the official weights for the AuK base model .
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.
| Category | Task | Description | Cookbook |
|---|---|---|---|
| Speech Generation | Zero-shot TTS | Speak the target text in the voice of the reference audio. | Zero-shot TTS |
| Instruct TTS | Generate speech from a voice description alone — no reference audio. | Instruct TTS | |
| Content Editing | Speech Content Editing | Rewrite what is said — replace, insert, or remove text. | Speech Content Editing |
| Lyric Editing | Rewrite lyrics in a singing recording while preserving the melody and voice. | Lyric Editing | |
| Acoustic Editing | Pitch Editing | Raise or lower the pitch by semitones. | Pitch Editing |
| Speed Editing | Adjust the speaking rate; output length scales with the speed factor. | Speed Editing | |
| Volume Editing | Raise or lower the volume by decibels. | Volume Editing | |
| Paralinguistic Editing | Emotion | Change the emotion while preserving content and voice. | Emotion |
| Timbre | Change the timbre to a description while keeping the content unchanged. | Timbre | |
| De-accent | Remove a regional accent while preserving the speaker's voice and content. | De-accent | |
| Nonverbal Editing | Remove or add nonverbal sounds such as breaths, laughs, or coughs. | Nonverbal Editing | |
| Whisper Conversion | Convert between normal speech and whisper while preserving speaker and content. | Whisper Conversion | |
| Enhancement & Separation | Speech Enhancement | Denoise, dereverberate, or restore natural, clear speech. | Speech Enhancement |
| Speech Separation | Keep one speaker by talking order and remove the others. | Speech Separation | |
| Music Separation | Extract the singing voice from a mix, or keep all human voices. | Music Separation | |
| Target Speaker Extraction | Keep the target speaker identified by what they say . | Target Speaker Extraction |
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.
Runs of tencent AuK on huggingface.co
4.1K
Total runs
107
24-hour runs
430
3-day runs
959
7-day runs
4.1K
30-day runs
More Information About AuK huggingface.co Model
Url of AuK
AuK huggingface.co Url
Provider of AuK huggingface.co
Other API from tencent
Total runs:
356.7K
Run Growth:
209.5K
Growth Rate:
57.90%
Total runs:
108.2K
Run Growth:
-3.2K
Growth Rate:
-2.97%
Total runs:
90.7K
Run Growth:
-582.4K
Growth Rate:
-642.43%
Total runs:
58.7K
Run Growth:
6.7K
Growth Rate:
12.00%
Total runs:
54.8K
Run Growth:
-7.7K
Growth Rate:
-14.26%
Total runs:
51.4K
Run Growth:
32.1K
Growth Rate:
62.47%
Total runs:
42.9K
Run Growth:
42.3K
Growth Rate:
98.97%
Total runs:
33.6K
Run Growth:
6.1K
Growth Rate:
18.50%
Total runs:
24.7K
Run Growth:
24.5K
Growth Rate:
99.34%
Total runs:
17.5K
Run Growth:
14.2K
Growth Rate:
85.15%
Total runs:
17.5K
Run Growth:
-992
Growth Rate:
-5.58%
Total runs:
16.8K
Run Growth:
6.6K
Growth Rate:
36.71%
Total runs:
16.7K
Run Growth:
2.5K
Growth Rate:
14.40%
Total runs:
12.7K
Run Growth:
4.3K
Growth Rate:
34.18%
Total runs:
10.6K
Run Growth:
3.1K
Growth Rate:
30.17%
Total runs:
6.9K
Run Growth:
6.8K
Growth Rate:
98.33%
Total runs:
6.1K
Run Growth:
6.1K
Growth Rate:
100.00%
Total runs:
4.3K
Run Growth:
-2.6K
Growth Rate:
-62.38%
Total runs:
3.8K
Run Growth:
3.7K
Growth Rate:
96.65%
Total runs:
3.4K
Run Growth:
-7.8K
Growth Rate:
-232.39%
Total runs:
3.4K
Run Growth:
-3
Growth Rate:
-0.09%
Total runs:
2.9K
Run Growth:
-1.9K
Growth Rate:
-63.75%
Total runs:
2.7K
Run Growth:
-699
Growth Rate:
-25.26%
Total runs:
2.0K
Run Growth:
-1.6K
Growth Rate:
-78.54%
Total runs:
1.8K
Run Growth:
327
Growth Rate:
17.71%
Total runs:
1.8K
Run Growth:
192
Growth Rate:
10.78%
Total runs:
1.7K
Run Growth:
354
Growth Rate:
20.76%
Total runs:
1.7K
Run Growth:
-873
Growth Rate:
-51.17%
Total runs:
1.6K
Run Growth:
478
Growth Rate:
29.54%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
82.02%
Total runs:
1.3K
Run Growth:
916
Growth Rate:
69.24%
Total runs:
1.2K
Run Growth:
-1.2K
Growth Rate:
-106.23%
Total runs:
1.1K
Run Growth:
818
Growth Rate:
73.36%
Total runs:
1.0K
Run Growth:
653
Growth Rate:
64.78%
Total runs:
1.0K
Run Growth:
611
Growth Rate:
60.20%
Total runs:
693
Run Growth:
-114
Growth Rate:
-16.45%
Total runs:
663
Run Growth:
512
Growth Rate:
78.17%
Total runs:
652
Run Growth:
-225
Growth Rate:
-34.56%
Total runs:
612
Run Growth:
162
Growth Rate:
25.80%
Total runs:
511
Run Growth:
179
Growth Rate:
34.29%
Total runs:
504
Run Growth:
178
Growth Rate:
37.01%
Total runs:
480
Run Growth:
79
Growth Rate:
16.46%
Total runs:
471
Run Growth:
-83
Growth Rate:
-16.90%
Total runs:
465
Run Growth:
155
Growth Rate:
32.91%
Total runs:
455
Run Growth:
106
Growth Rate:
23.93%
Total runs:
429
Run Growth:
249
Growth Rate:
58.04%
Total runs:
426
Run Growth:
-1.7K
Growth Rate:
-401.43%
Total runs:
418
Run Growth:
418
Growth Rate:
100.00%
Total runs:
377
Run Growth:
235
Growth Rate:
63.34%
Total runs:
376
Run Growth:
-244
Growth Rate:
-65.24%
Total runs:
354
Run Growth:
239
Growth Rate:
66.39%
Total runs:
317
Run Growth:
-81
Growth Rate:
-25.55%
Total runs:
310
Run Growth:
147
Growth Rate:
47.12%
Total runs:
301
Run Growth:
28
Growth Rate:
9.33%
Total runs:
297
Run Growth:
-416
Growth Rate:
-140.07%
Total runs:
290
Run Growth:
-86
Growth Rate:
-29.66%
Total runs:
286
Run Growth:
-211
Growth Rate:
-74.04%
Total runs:
283
Run Growth:
143
Growth Rate:
49.48%
Total runs:
280
Run Growth:
-137
Growth Rate:
-48.93%
Total runs:
277
Run Growth:
-69
Growth Rate:
-24.91%
Total runs:
267
Run Growth:
186
Growth Rate:
69.40%
Total runs:
262
Run Growth:
135
Growth Rate:
51.92%
Total runs:
249
Run Growth:
89
Growth Rate:
37.39%
Total runs:
239
Run Growth:
116
Growth Rate:
48.95%
Total runs:
232
Run Growth:
99
Growth Rate:
38.67%
Total runs:
230
Run Growth:
60
Growth Rate:
26.43%
Total runs:
193
Run Growth:
3
Growth Rate:
1.57%
Total runs:
188
Run Growth:
99
Growth Rate:
52.11%