Fast voice agents with ConvFill

Voice agents are either fast or smart. ConvFill proposes a way to bridge that gap by training a smol talker model (0.6B!) to talk with cheat notes from a large reasoner model. The way it works is this: after the user's speech is transcribed, the talker replies quickly to buy itself time while

中文全文翻译正在补齐，可先查看下方英文原文。

Voice agents are either fast or smart. ConvFill proposes a way to bridge that gap by training a smol talker model (0.6B!) to talk with cheat notes from a large reasoner model. The way it works is this: after the user's speech is transcribed, the talker replies quickly to buy itself time while