I haven't experienced a regression, but voice modes have always been stupider than frontier models. In my experience Grok's voice mode suffers the least from this, and it's been getting better over time. It's especially good (compared to ChatGPT or Gemini) on things that involve current events or web research. Just yesterday in the car I got it to locate and read and explain a recent academic paper and multiple of my questions were answered with several minute long monologues that contained useful and accurate information.