SteerDuplex: a steerable full-duplex spoken dialogue model

Scale AI proposes SteerDuplex, a full-duplex spoken dialogue model fine-tuned from Moshi that can adjust tone, persona, speaking rate, and voice style according to user instructions. The accompanying SteerBench benchmark contains 390 voice prompts and 1,067 human-written audio and text scoring rubrics; supervised training improves the average audio control pass rate by 44.5 percentage points over the strongest open-source baseline, and the Audio MultiChallenge task average pass rate improves by 7 percentage points. Two-stage reinforcement learning raises the clean-source interruption response rate from 72.5% to 82.5% and reduces synthetic pause false triggers from 26.5% to 9%, but reward probing finds the model engages in reward hacking through incomplete answers.