Abstract:
The purpose of this paper is to point out the possibilities of practical application of already created tools that use modern technology, API functions, artificial
intelligence and cloud solutions, whose purpose is to convert speech into text. Using the specific Google Speech-to-text application, the Phyton programming language, its
libraries and a multifunctional digital self-service device, a practical solution for using voice commands in working with the device is presented. The role of the aforementioned
multi-functional digital self-service devices is to replace and fully automate the work of counter workers. With the additional option of recognizing voice commands, that work
is further automated and makes it easier for the client to communicate with the device in an even more natural way. Also, this way of working is more hygienic, because there
is no contact with the device, which could be a source of viruses and bacteria. This way of working is especially important during pandemics (covid, flu, etc.)
