StepAudio 3 Realtime Technical Report
StepAudio 3 Realtime debuts an audio-language model with Think-While-Speaking reasoning, delivering full-duplex voice dialogue with top benchmark results.
StepAudio 3 Realtime is an audio-language foundation model built around a continuous listen-converse-think-act loop for real-time spoken interaction. Think-While-Speaking runs private reasoning in parallel with speech, reaching a 73.0 macro average on StepAudioChat in reasoning mode. The model reports 90.6 on MMSU, 98.9 overall on the Artificial Analysis Full-Duplex Bench, and 56.0% macro task success on tau-Voice. An integrated Voice Agent handles asynchronous tool execution without disrupting dialogue flow.
- Uses a listen-converse-think-act loop with Think-While-Speaking parallel reasoning to preserve low latency.
- Scores 90.6 on MMSU, 98.9 on Artificial Analysis Full-Duplex Bench, and 56.0% on tau-Voice.
- Seamless Duplex models handle pauses, backchannels, and interruptions; Voice Agent executes tools asynchronously.
From the original article
1 min read at huggingface.co
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.
By Bin Lin, Bo Zhao, Boyang Zhang · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.