This talk introduces a new approach to generate strongly constrained texts. We consider standardized sentence generation for the typical application of vision screening. To solve this problem, we formalize it as a discrete combinatorial optimization problem on words and show how constraint programming and multivalued decision diagrams (MDD), a well-known data structure to deal with constraints can be used to solve it. We show how part of the language is kept thanks to n-grams. Once the sentences are obtained, we apply a language model (LLM: GPT-3) to keep the best ones. We detail this for English and also for French where the agreement and conjugation rules are known to be more complex. We will also discuss about some possible improvements for a better integration of LLM into constraint programming.(This presentation, does not require any knowledge in LLM or in constraint programming.)