Abstract: A voice support server is used to provide voice control functionality to a third party application that does not natively support voice control functions. The voice support server implements a domain specific to the third party application that maintains a domain-specific language model (DLM) reflecting the functionality of the third party application. The DLM comprises a plurality of intent patterns corresponding to different commands and their possible variations that may be issued by the user, and maps each intent pattern to a corresponding action to be performed by the third party application. Received audio data is analyzed to determine one or more user utterances, which are transcribed and compared to the intent patterns of the DLM to identify an intent corresponding to the user utterance. The voice control module may then transmit instructions to the third party application to perform the action corresponding to the identified intent.