An apparatus includes an audio output device, an audio input device and a processor. The audio output device may be configured to generate an audio message. The audio input device may be configured to receive audio input. The processor may be configured to analyze the audio input to perform a first authentication of a user and determine a command corresponding to the audio input, determine a confidence level of a classification of a user based on the first authentication and authenticate the user if the confidence level is above a pre-determined threshold. The classification may correspond to an approved list of users. The confidence level may be adjusted in response to one or more authentication factors. If the user is authenticated, the processor may be configured to perform the command.