Explainable Artificial Intelligence (XAI) has emerged in response to the growing demand to create more transparent and understandable Artificial Intelligence (AI) models in critical domains such as health, finance, and justice. Numerous XAI methods and approaches have been developed in this field to explain how AI systems make their decisions. This paper proposes a new approach, the Meta-Explainers, inspired by the AI’s Meta-Classification theory. The proposal follows a semantic similar to that of the Meta-Classifiers, i.e., it is based on combining different explanations provided by several XAI methods into a single final explanation, called meta-explanation. Our approach not only simplifies the interpretation process for the end-user by consolidating multiple individual explanations into a single meta-explanation, but also improves the quality of the final explanation.