SteerDuplex: full-duplex speech model gains 44.5pp in steerability, new SteerBench released

ScaleAI · hf · 2026-09-22

ScaleAI researchers introduce SteerDuplex, targeting steerability — the underexplored ability of full-duplex spoken dialogue models to shift tone, persona, speaking rate, and voice style on instruction.

Model and benchmark are open for systematic research on spoken steerability.

Original post →

More from Research

Research channel →