A computing device and method for controlling narration. The computing device comprises a display device displaying a visual user interface including textual information, and an electronic processor. The electronic processor executing instructions to identify a plurality of discrete textual data elements included in the textual information, map each of the plurality of discrete textual data elements to an audio data element, generate an implicit audio narration including the audio data element mapped to each of the plurality of discrete textual data elements and at least one of an audible tone and a pause between audio data elements mapped to at least two of the plurality of discrete textual data elements, and output the implicit audio narration.