StepAudio 3 Realtime Technical Report
- 类型：arxiv
- 标识：2609.14005
- 链接：https://arxiv.org/abs/2609.14005
- 主分类：multimodal
- 形态：method
- TLDR：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
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-16-agent-rag-longcontext-candidates.json