Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.14005

StepAudio 3 Realtime Technical Report

Bin Lin·Bo Zhao·Boyang Zhang·Boyong Wu·Chao Yan·Chen Geng·Chen Wu·Cheng Yi·Chengli Feng·Chenglin Zhu·Chengting Feng·Chengyuan Yao·Daijiao Liu·DanNi Wan·Daxin Jiang·Dongjian Li·Dongqing Pang·Fei Tian·Feng Tian·Future Li·Gang Yu·Guanglong Yang·Haoyang Zhang·Hongyuan Wang·Jia Peng·Jiahao Song·Jialong Xue·Jiamin Fan·Jiangjie Zhen·Jianzheng Gao·Jincheng Wen·Jinghua Liang·Jinglan Gong·Jun Chen·Li Xie·Liang Zhao·Lifang Zhang·Lingli Ji·Lun Cai·Min Xu·Peilin Li·Peng Yang·Pengfei Tan·Qingjian Lin·Qinxin Du·Ruijie Xiong·Runze Li·Shenghua Hu·Shengqian Qin·Shi Qiu·Siqi Tu·Siyi Zhou·Tianjiao Deng·Wanying Lu·Weiming Niu·Wen Sun·WenWen Qu·Xiangyu Zhang·Xianwei Zhang·Xiaosu Su·Xing Chen·Xinyu Liu·Xuerui Yang·Yan Wu·Yang Li·Yang Yang·Yechang Huang·Yibo Zhu·Yifan Zhang·Yinuo Yan·Youjun Chen·Yu Fu·Yu Luo·Yu Zhou·Yujie Chen·Yumang Wang·Yunzhou Ju·Yuxiang Yang·Yuxin Li·Yuxin Zhang·Zekai Liu·Zengwei Yao·Zhaoxin Yuan·Zhenwei Mou·Zhiquan Zhang·Zhiyue Wu·Zichao Li·Zichao Zhou·Ziqi Ren·Zixuan Wang
View original source ↗Read source document ↗Export metadata ↓

Abstract

Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a continuous listen-converse-think-act loop. Deep Perception captures rich acoustic cues to interpret user intent, while Seamless Duplex models synchronized audio streams to handle pauses, backchannels, and interruptions naturally. Crucially, we resolve the tension between deep deliberation and latency via Think-While-Speaking, executing private reasoning in parallel with spoken delivery. In reasoning mode, StepAudio 3 reaches a 73.0 macro average on StepAudioChat. With Think-While-Speaking, it achieves dialogue and reasoning performance comparable to dedicated reasoning models while speaking in real time. Furthermore, an integrated Voice Agent handles asynchronous tool execution without disrupting the dialogue flow. StepAudio 3 Realtime achieves top-tier performance across key dimensions: an exceptional 90.6 on the MMSU benchmark, 98.9 Overall on the Artificial Analysis Full-Duplex Bench, and a 56.0% macro task-success rate on $τ$-Voice.

Explore related subjects

cs.SDeess.AS

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Bin Lin, Bo Zhao, Boyang Zhang, Boyong Wu, Chao Yan, Chen Geng, Chen Wu, Cheng Yi, Chengli Feng, Chenglin Zhu, Chengting Feng, Chengyuan Yao, Daijiao Liu, DanNi Wan, Daxin Jiang, Dongjian Li, Dongqing Pang, Fei Tian, Feng Tian, Future Li, Gang Yu, Guanglong Yang, Haoyang Zhang, Hongyuan Wang, Jia Peng, Jiahao Song, Jialong Xue, Jiamin Fan, Jiangjie Zhen, Jianzheng Gao, Jincheng Wen, Jinghua Liang, Jinglan Gong, Jun Chen, Li Xie, Liang Zhao, Lifang Zhang, Lingli Ji, Lun Cai, Min Xu, Peilin Li, Peng Yang, Pengfei Tan, Qingjian Lin, Qinxin Du, Ruijie Xiong, Runze Li, Shenghua Hu, Shengqian Qin, Shi Qiu, Siqi Tu, Siyi Zhou, Tianjiao Deng, Wanying Lu, Weiming Niu, Wen Sun, WenWen Qu, Xiangyu Zhang, Xianwei Zhang, Xiaosu Su, Xing Chen, Xinyu Liu, Xuerui Yang, Yan Wu, Yang Li, Yang Yang, Yechang Huang, Yibo Zhu, Yifan Zhang, Yinuo Yan, Youjun Chen, Yu Fu, Yu Luo, Yu Zhou, Yujie Chen, Yumang Wang, Yunzhou Ju, Yuxiang Yang, Yuxin Li, Yuxin Zhang, Zekai Liu, Zengwei Yao, Zhaoxin Yuan, Zhenwei Mou, Zhiquan Zhang, Zhiyue Wu, Zichao Li, Zichao Zhou, Ziqi Ren, Zixuan Wang. 2026-09-19. StepAudio 3 Realtime Technical Report. https://arxiv.org/abs/2609.14005

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Streaming Generation for Music Accompaniment

Music generation models can produce high-fidelity coherent accompaniment given complete audio input, but are limited to editing and loop-based workflows. We study real-time audio-to-audio accompaniment: as a model hears an input audio stream (e.g., a singer singing), it has to also simultaneously generate in real-time a coherent accompanying stream (e.g., a guitar accompaniment). In this work, we propose a model design considering inevitable system delays in practical deployment with two design variables: future visibility $t_f$, the offset between the output playback time and the latest input time used for conditioning, and output chunk duration $k$, the number of frames emitted per call. We train Transformer decoders across a grid of $(t_f,k)$ and show two consistent trade-offs: increasing effective $t_f$ improves coherence by reducing the recency gap, but requires faster inference to stay within the latency budget; increasing $k$ improves throughput but results in degraded accompaniment due to a reduced update rate. Finally, we observe that naive maximum-likelihood streaming training is insufficient for coherent accompaniment where future context is not available, motivating advanced anticipatory and agentic objectives for live jamming.

cs.SD↗
arXiv2026

M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR

The Continuous Integrate-and-Fire (CIF) mechanism provides effective alignment for non-autoregressive (NAR) speech recognition. This mechanism creates a smooth and monotonic mapping from acoustic features to target tokens, achieving performance on Mandarin competitive with other NAR approaches. However, without finer-grained guidance, its stability degrades in some languages such as English and French. In this paper, we propose Multi-scale CIF (M-CIF), which performs multi-level alignment by integrating character and phoneme level supervision progressively distilled into subword representations, thereby enhancing robust acoustic-text alignment. Experiments show that M-CIF reduces WER compared to the Paraformer baseline, especially on CommonVoice by 4.21% in German and 3.05% in French. To further investigate these gains, we define phonetic confusion errors (PE) and space-related segmentation errors (SE) as evaluation metrics. Analysis of these metrics across different M-CIF settings reveals that the phoneme and character layers are essential for enhancing progressive CIF alignment.

cs.SD↗
arXiv2026

Decoding Order Matters in Autoregressive Speech Synthesis

Autoregressive speech synthesis often adopts a left-to-right order, yet generation order is a modelling choice. We investigate decoding order through masked diffusion framework, which progressively unmasks positions and allows arbitrary decoding orders during training and inference. By interpolating between identity and random permutations, we show that randomness in decoding order affects speech quality. We further compare fixed strategies, such as \texttt{l2r} and \texttt{r2l} with adaptive ones, such as Top-$K$, finding that fixed-order decoding, including the dominating left-to-right approach, is suboptimal, while adaptive decoding yields better performance. Finally, since masked diffusion requires discrete inputs, we quantise acoustic representations and find that even 1-bit quantisation can support reasonably high-quality speech.

cs.SD↗