In recent years, along with advances in affective computing, automatic personality recognition has become an emerging area of research. However, the problem of correct personality recognition remains challenging. In this paper, the problem of automatic personality recognition is supported with the use of Generative Artificial Intelligence and specifically with the use of large language models, also known as LLMs. It is based on an existing personality recognition corpus in text, built with the support of traditional personality questionnaire techniques and text extracted from the audio of videos. Then, with the support of Generative AI, augmented and balanced versions of the same corpus were created for each personality trait. The obtained corpora were used to train and optimize different automatic and deep learning models. The results obtained with different classification models on these corpora show higher values in the accuracy and precision metrics compared to those obtained in the baseline study.