Is it possible to integrate voice-recognition as a processing unit?

My title is perhaps ambiguous as I lacked exact technical terminologies; however, what I meant above was that: in terms of interactive quiz and test slides, are we able to process the voice input from the users using voice-recognition provided by a third party (for example google)? Then what the core system would receive was Text processed and put into word sending from that third-party. Finally, it should finish the whole sequence by in-house by comparing the received text and […]