The advanced intonation model for speech synthesis described here has a three level architecture. An initial abstract characterisation designed to represent intonation at the level of cognitive percept is rewritten to an intermediate representation which is speaker independent, yet which accurately reflects physical pitch contours. At this stage the contours lack the variability associated with natural speech. This representation is then further rewritten to provide an actual physical contour (now including variability and other ‘natural’ phenomena such as micro-intonation). One or two examples are given for stages one and two, and some indication of how we tackle stage three.