Methods, systems and computer program products for processing video of tax documents and associated verbal input provided by a user and populating at least a portion of an electronic tax return with processing results. A video/voice processor associated with a tax return preparation application executed by a computing apparatus such as mobile communication device receives a video of a tax document and voice data. The document type is determined using video and/or voice data. Voice to text conversion can be used to determine what a user said about the document to determine the document type. Tax data determined from the video is used to populate a field of the electronic tax return. A front facing camera may be used to take a video of a tax document while a rear facing camera is used to detect a facial expression, which may result in certain dialogue with the user.