[biot]

  > Of course the voice goes through each companies respective
  > search engines, they kinda have to to work unless there's
  > some standard for voice queries I'm not aware of.

There is. Convert the voice query to text, then send the resulting text to the user's preferred search engine.

[kllrnohj]

Does not trigger the same (and spoken) response that at least Siri and "Ok Google" do.

And there are plenty of commands that don't result in a normal search at all, such as "ok google, what song is playing?" or "ok google, when is my next flight?"

[biot]

Of course, but both fall back to a plain old web search when the request can't be processed specially. In those cases, why not fall back to your search engine of choice?

[cbr]

You get better transcriptions and better search results if you give your search backend a probability-weighted list of possible transcriptions and let it combine that with what it thinks you might be trying to search for given the context it has for you.

[0x0]

As an end-user I'd like to choose to use my preferred search engine with a singular voice-to-text query, rather than an array of possible voice-to-text-queries, even if it means losing context...

[TheSoftwareGuy]

As another end-user I have the opposite opinion.