Digital image capture session and metadata association techniques are described. In one example, a user input is received to initiate an image capture session. At least one digital image is captured using a digital camera during the image capture session. Audio input data is also collected using an audio input device during the image capture session and converted into text data, e.g., speech-to-text. Metadata is generated based on the text data and associated with the at least one digital image. The at least one digital image is output as having the associated metadata as completion of the image capture session.