The M-PIRO project developed state of the art techniques and tools in natural language generation, speech synthesis, user modelling, and their interaction with adaptive hypermedia and virtual reality systems. The project built on existing museum collection information database systems, and utilised the information management and design expertise from the museum partners. The M-PIRO software creates descriptions of museum artefacts automatically, using information stored in a database. Children, adults and experts all receive slightly different, personalised, descriptions. The system also remembers what viewers have looked at before in order to avoid repetition and to draw comparisons with previously seen objects. The technology generates text in English, Italian or Greek.