Architecture of a desktop application with voice recognition?

Question

Speech recognition

Good afternoon.
there is a desktop software (Windows), which can be given commands in text form (for example, "SAVE") via API (C#).
I want to fasten voice recognition so that I can speak into the microphone, the voice is recognized and the command is given for execution.
I know the API of this software - everything is clear here.
how to organize the recognition of voice commands into text? desktop libraries, cloud services?
(it is desirable that in C # it was possible to interact).

Answer 1

If I understand you correctly. Maybe this video will help you.

Answer 2

Google has such an API, though not free

Answer 3

HTTP API from Yandex https://tech.yandex.ru/speechkit/cloud/

Answer 4

Google the term ASR (Automatic Speech Recognition).