[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.