Views
No views yet
| Model | APS (%) | DSD (%) | RP (%) | AVG (%) |
|---|---|---|---|---|
| Gemini 2.5-Flash* | 88.2 | 90.9 | 77.3 | 85.4 |
| Gemini 2.5-Pro* | 89.0 | 90.1 | 75.5 | 84.8 |
| GPT-4o-Mini-TTS* | 54.9 | 52.3 | 46.0 | 51.1 |
| ElevenLabs* | 42.8 | 50.9 | 59.1 | 50.9 |
| VoxInstruct | 47.5 | 52.3 | 42.6 | 47.5 |
| MiMo-Audio-7B-Instruct | 70.1 | 66.1 | 57.1 | 64.5 |
| VoiceSculptor | 75.7 | 64.7 | 61.5 | 67.6 |
Note
- Models marked with
*are commercial models.- InstructTTSEval — Huang, K., Tu, Q., Fan, L., Yang, C., Zhang, D., Li, S., Fei, Z., Cheng, Q., & Qiu, X. (2025).
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems.
arXiv preprint arXiv:2506.16381.
arXiv
1# Clone the repository and enter the directory
2git clone https://github.com/ASLP-lab/VoiceSculptor.git
3cd VoiceSculptor
4
5# Create and activate a Conda environment
6conda create -n VoiceSculptor python=3.10 -y
7conda activate VoiceSculptor
8
9# Install dependencies
10pip install -r requirements.txt1git lfs install
2git clone https://huggingface.co/ASLP-lab/VoiceSculptor-VDpython infer.py1@misc{VoiceSculptor,
2 title={VoiceSculptor: Your Voice, Designed By You},
3 author={Jingbin Hu and Huakang Chen and Linhan Ma and Dake Guo and Qirui Zhan and Wenhao Li and Haoyu Zhang and Kangxiang Xia and Ziyu Zhang and Wenjie Tian and Chengyou Wang and Jinrui Liang and Shuhan Guo and Zihang Yang and Bengu Wu and Binbin Zhang and Pengcheng Zhu and Pengyuan Xie and Chuan Xie and Qiang Zhang and Jie Liu and Lei Xie},
4 year={2026},
5 url={https://github.com/ASLP-lab/VoiceSculptor},
6}
7@misc{ye2025llasascalingtraintimeinferencetime,
8 title={Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis},
9 author={Zhen Ye and Xinfa Zhu and Chi-Min Chan and Xinsheng Wang and Xu Tan and Jiahe Lei and Yi Peng and Haohe Liu and Yizhu Jin and Zheqi Dai and Hongzhan Lin and Jianyi Chen and Xingjian Du and Liumeng Xue and Yunlin Chen and Zhifei Li and Lei Xie and Qiuqiang Kong and Yike Guo and Wei Xue},
10 year={2025},
11 eprint={2502.04128},
12 archivePrefix={arXiv},
13 primaryClass={eess.AS},
14 url={https://arxiv.org/abs/2502.04128},
15}