Sponsored by
APIMaster
tencent / AuK-Flash
Model's Last Updated: September 09 2026
text-to-speech
Introduction of AuK-Flash
Model Details of AuK-Flash
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 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.
| 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-Flash on huggingface.co
2.8K
Total runs
0
24-hour runs
231
3-day runs
612
7-day runs
2.8K
30-day runs
More Information About AuK-Flash huggingface.co Model
Url of AuK-Flash
AuK-Flash huggingface.co Url
Provider of AuK-Flash huggingface.co
Other API from tencent
Total runs:
381.8K
Run Growth:
253.3K
Growth Rate:
66.34%
Total runs:
102.6K
Run Growth:
-14.1K
Growth Rate:
-13.78%
Total runs:
90.7K
Run Growth:
-582.4K
Growth Rate:
-642.43%
Total runs:
54.6K
Run Growth:
-6.2K
Growth Rate:
-11.36%
Total runs:
51.3K
Run Growth:
31.1K
Growth Rate:
60.68%
Total runs:
49.8K
Run Growth:
-592
Growth Rate:
-1.19%
Total runs:
42.6K
Run Growth:
42.2K
Growth Rate:
98.97%
Total runs:
32.5K
Run Growth:
5.0K
Growth Rate:
15.27%
Total runs:
24.6K
Run Growth:
24.6K
Growth Rate:
100.00%
Total runs:
17.8K
Run Growth:
2.6K
Growth Rate:
14.60%
Total runs:
17.4K
Run Growth:
-2.5K
Growth Rate:
-14.44%
Total runs:
17.2K
Run Growth:
1.3K
Growth Rate:
7.84%
Total runs:
16.2K
Run Growth:
14.5K
Growth Rate:
89.76%
Total runs:
11.4K
Run Growth:
3.1K
Growth Rate:
27.39%
Total runs:
10.0K
Run Growth:
2.7K
Growth Rate:
27.31%
Total runs:
7.7K
Run Growth:
7.7K
Growth Rate:
100.00%
Total runs:
6.1K
Run Growth:
6.1K
Growth Rate:
100.00%
Total runs:
4.4K
Run Growth:
-2.6K
Growth Rate:
-57.85%
Total runs:
4.0K
Run Growth:
842
Growth Rate:
21.08%
Total runs:
3.8K
Run Growth:
3.6K
Growth Rate:
95.66%
Total runs:
3.1K
Run Growth:
-10.1K
Growth Rate:
-326.27%
Total runs:
3.0K
Run Growth:
-1.7K
Growth Rate:
-57.22%
Total runs:
2.8K
Run Growth:
-700
Growth Rate:
-25.30%
Total runs:
2.3K
Run Growth:
2.1K
Growth Rate:
91.75%
Total runs:
1.9K
Run Growth:
-1.7K
Growth Rate:
-86.51%
Total runs:
1.9K
Run Growth:
1.4K
Growth Rate:
73.42%
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:
402
Growth Rate:
23.40%
Total runs:
1.7K
Run Growth:
-873
Growth Rate:
-51.17%
Total runs:
1.6K
Run Growth:
-606
Growth Rate:
-38.43%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
82.02%
Total runs:
1.3K
Run Growth:
891
Growth Rate:
68.64%
Total runs:
1.1K
Run Growth:
847
Growth Rate:
75.22%
Total runs:
1.0K
Run Growth:
611
Growth Rate:
60.20%
Total runs:
693
Run Growth:
-114
Growth Rate:
-16.45%
Total runs:
630
Run Growth:
153
Growth Rate:
24.29%
Total runs:
618
Run Growth:
-265
Growth Rate:
-42.88%
Total runs:
578
Run Growth:
237
Growth Rate:
41.00%
Total runs:
567
Run Growth:
411
Growth Rate:
72.49%
Total runs:
512
Run Growth:
186
Growth Rate:
36.33%
Total runs:
480
Run Growth:
79
Growth Rate:
16.46%
Total runs:
468
Run Growth:
153
Growth Rate:
32.69%
Total runs:
443
Run Growth:
92
Growth Rate:
21.55%
Total runs:
429
Run Growth:
248
Growth Rate:
57.81%
Total runs:
425
Run Growth:
136
Growth Rate:
32.00%
Total runs:
418
Run Growth:
418
Growth Rate:
100.00%
Total runs:
360
Run Growth:
-251
Growth Rate:
-69.72%
Total runs:
360
Run Growth:
213
Growth Rate:
59.17%
Total runs:
360
Run Growth:
-117
Growth Rate:
-32.50%
Total runs:
326
Run Growth:
185
Growth Rate:
56.75%
Total runs:
317
Run Growth:
-81
Growth Rate:
-25.55%
Total runs:
297
Run Growth:
-416
Growth Rate:
-140.07%
Total runs:
294
Run Growth:
156
Growth Rate:
53.06%
Total runs:
290
Run Growth:
-86
Growth Rate:
-29.66%
Total runs:
289
Run Growth:
117
Growth Rate:
40.48%
Total runs:
287
Run Growth:
5
Growth Rate:
1.74%
Total runs:
280
Run Growth:
-137
Growth Rate:
-48.93%
Total runs:
277
Run Growth:
-69
Growth Rate:
-24.91%
Total runs:
271
Run Growth:
102
Growth Rate:
37.64%
Total runs:
255
Run Growth:
123
Growth Rate:
48.24%
Total runs:
230
Run Growth:
87
Growth Rate:
37.83%
Total runs:
229
Run Growth:
52
Growth Rate:
22.71%
Total runs:
226
Run Growth:
95
Growth Rate:
42.04%
Total runs:
219
Run Growth:
137
Growth Rate:
62.56%
Total runs:
194
Run Growth:
109
Growth Rate:
56.19%
Total runs:
184
Run Growth:
-26
Growth Rate:
-14.13%