Initiating synthesized speech outpout from a voice-controlled device

A voice-controlled device for controlling synthesized speech output, the voice-controlled device comprising:

• a processor device;
• and
• a memory operably coupled to the processor device and storing computer-executable instructions causing:
• capturing, with a sensor, an image of a face of at least one person;
• accessing a database of previously stored images of facial features;
• in response to
• not recognizing the at least one person then selecting a first set of conversational starters;
• recognizing the at least one person and recognizing a previous communication with the person then selecting a second set of conversational starters;
• recognizing the at least one person and not recognizing a previous communication with the person then selecting a third set of conversational starters;
• recognizing the at least one person and recognizing previous communications with the person but do not know the person's identity then selecting a fourth set of conversational starters;
• detecting, with at least one sensor, whether the at least one person remains within a first settable distance from the voice-controlled device;
• and
• in response to the person being detected and a settable period of time having elapsed, then outputting synthesized speech using one of the set of conversational starters.

A computer program product for controlling synthesized speech output, the computer program product comprising:

• a non-transitory computer readable storage medium readable by a voice-controlled device and storing program instructions for execution by the voice-controlled device, said program instructions comprising:
• capturing, with a sensor, an image of a face of at least one person;
• accessing a database of previously stored images of facial features;
• in response to
• not recognizing the at least one person then selecting a first set of conversational starters;
• recognizing the at least one person and recognizing a previous communication with the person then selecting a second set of conversational starters;
• recognizing the at least one person and not recognizing a previous communication with the person then selecting a third set of conversational starters;
• recognizing the at least one person and recognizing a previous communication with the person but do not know the person's identity then selecting a fourth set of conversational starters;
• detecting, with at least one sensor, whether the at least one person remains within a first settable distance from the voice-controlled device;
• and
• in response to the person being detected and a settable period of time having elapsed, then outputting synthesized speech using one of the set of conversational starters.