This paper proposes a solution to the problem of aggregating versatile probabilistic models, namely mixtures of probabilistic principal component analyzers. These models are a powerful generative form for capturing a high-dimensional, non Gaussian, data set. They simultaneously perform mixture fitting and dimensionality reduction. We demonstrate how such models may be advantageously aggregated by accessing mixture parameters only, rather than original data. Aggregation is carried out through Bayesian estimation with a specific prior and an original variational scheme. Experimental results illustrate the effectiveness of the proposal.