S2S or Cascading ?

One of the most frequently asked questions I get is whether you would implement s2s because of its lower latency and costs.

While it offers lower costs and lower latency/quicker responses, it doesn't provide the same level of configurability and control that we all expect. While foundational models make the voice agent sound like a human, a cascaded architecture allows it to behave like one too.

What about a hybrid approach where the latency and costs are as low as an S2S, and the configurability and control are like those of a cascading architecture? thoughts?