SOURCE-LINKED INTELLIGENCE

SteerDuplex: Steerable Duplex Speech Dialogue Models

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Full-duplex spoken dialogue models support low-latency turn taking, interruption handling, and backchanneling, yet a key capability remains underexplored: steerability, the ability to reliably shift conversational behavior along attributes such as tone, persona, speaking rate, and voice style in response to user instructions. We introduce a taxonomy of text- and audio-based steerability that identifies substantial gaps in current full-duplex models. To address this gap, we introduce SteerDuplex, a Moshi-based full-duplex speech model fine-tuned on natural conversations and synthetic dialogues

Read original source ↗ Open in workspace

recordType

paper

region

Global