This work uses computational approaches to study literature. It addresses the question of characterisation in theatrical plays, concentrating on the work of Moliere, and trying to identify distinctive traits in the “voices” of some of the famous characters created by the French playwright. The used technique adopts a syntagmatic approach, targeting differences in the distribution of sequences of grammatical categories, derived from texts in a bottom up way. First of all morpho-syntactic motifs of length 3 to 5 are extracted from the lines of each character with the help of a sequential pattern mining algorithm; then the differences in the distribution of such motifs across the characters are investigated by means of Correspondence Analysis. In the first experiment four well known Moliere protagonists (Harpagon, Dom Juan, Scapin, Sganarelle) are compared; in the second one a set of minor characters (the so called “Reasoners”) are investigated. The combined conclusions of the two proposed experiments highlight the complex intersection between voice and register in determining the stylistic choices of the author. In order for his characters to be perceived as realistic, Moliere not only provides them with a distinctive voice, but also models their dialogue according to the communicative function they fulfil in the play.