I need the two API because in IBM watson has a features that the accuracy in terms in identifying the speakers but in converting process of speech to text is not really exact. While in Google cloud speech to text API has better result in terms in converting the speech to text, they can identify the English-Philippine accent but in identifying the speakers the IBM watson API has a better result. I want to create a speech to text application that can identify the speakers. My question is, Is it possible that the IMB watson API and Google cloud speech to text API will be combine?
You can try to combine the output from both using the timing information. Get the words+timestamps from one, and the speaker-labels+timestamps from the other one, then align words and labels using the timestamps.