Step-Audio-R1 Technical Report
Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang, Haoyang Zhang, Yuxin Li, Daijiao Liu, Yayue Deng, Donghang Wu, Jun Chen, Liang Zhao, Chengyuan Yao, Hexin Liu, Eng Siong Chng, Xuerui Yang, Xiangyu Zhang, Daxin Jiang, Gang Yu
TL;DR
Step-Audio-R1 addresses the paradox of inverted reasoning benefits in audio-language models by introducing Modality-Grounded Reasoning Distillation (MGRD), an iterative framework that grounds reasoning in acoustic features rather than textual surrogates. The approach combines a frozen audio encoder, an LLM decoder, supervised and reinforcement learning, and iterative self-distillation to shift reasoning from transcripts to native acoustic analysis. Empirical results show Step-Audio-R1 outperforms Gemini 2.5 Pro and matches Gemini 3 Pro on comprehensive audio benchmarks, demonstrating that reasoning is transferable across modalities when anchored to the correct input. This work enables truly multimodal reasoning systems that deeply analyze audio signals and lays groundwork for future cross-modal AI systems.
Abstract
Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon persists in audio language models: they consistently perform better with minimal or no reasoning, raising a fundamental question - can audio intelligence truly benefit from deliberate thinking? We introduce Step-Audio-R1, the first audio reasoning model that successfully unlocks reasoning capabilities in the audio domain. Through our proposed Modality-Grounded Reasoning Distillation (MGRD) framework, Step-Audio-R1 learns to generate audio-relevant reasoning chains that genuinely ground themselves in acoustic features rather than hallucinating disconnected deliberations. Our model exhibits strong audio reasoning capabilities, surpassing Gemini 2.5 Pro and achieving performance comparable to the state-of-the-art Gemini 3 Pro across comprehensive audio understanding and reasoning benchmarks spanning speech, environmental sounds, and music. These results demonstrate that reasoning is a transferable capability across modalities when appropriately anchored, transforming extended deliberation from a liability into a powerful asset for audio intelligence. By establishing the first successful audio reasoning model, Step-Audio-R1 opens new pathways toward building truly multimodal reasoning systems that think deeply across all sensory modalities.