Audio of a user speaking is gathered while spatial data of the face of the user is gathered. Positions of elements of the face of are identified, wherein relative positions of the elements cause a plurality of qualities of the user voice. A subset of positions of the elements are identified to have caused a detected first quality of the user voice during the period of time. Alternate positions of the one or more elements are identified that are determined to cause the user voice to have a second quality rather than the first quality. A graphical representation of the face that depicts one or more adjustments from the subset of the positions to the alternate positions is provided to the user.