> Conversational English is a format.

And as you said, format isn't enough. You need semantics.

If two applications know enough about the other side to know how to formulate their voice queries, they know at least enough to exchange those same queries as text, and skip the stupidly wasteful text->speech->text process.

(And if world wouldn't be so full of adversarial practices driving engineering stupidity, the developers would agree on an efficient binary format beforehand.)

The simplest "API" would be skipping the text-to-speech-to-text process, and send the text string in binary.

Well they could at least continue doing the same thing, at 100x the speed.

Over the phone? Voice recognition would fail even more. Google also mentioned some of the latency in answering is required by their processing.

Does this sound look familiar? ;)

https://www.youtube.com/watch?v=vvr9AMWEU-c

In other words, if M2M handshake works, switch away from voice.