We present a model-based clustering algorithm to cluster longitudinal mixed data. Assuming that the non-continuous variables are the discretization of underlying latent continuous variables, the model relies on a mixture of matrix-variate normal distributions, accounting simultaneously for within- and between-time dependence structures. The model is thus able to concurrently handle the heterogeneity, the association among the responses and the temporal dependence structure of longitudinal continuous, ordinal, binary, nominal and count data. An MCMC-EM algorithm is developed for parameters estimation.