<p>Voice assistants are in full expansion due to the numerous benefits they have demonstrated. However, it has been found that some users exhibit specific speech patterns that impede effective interaction with them. In this paper, we propose a language correction system powered by generative artificial intelligence, which addresses potential communication errors in interactions with voice assistants. This system is designed to improve the comprehension of commands on Alexa devices, so its goal is to correct simple voice inputs. During these interactions, there are instances where Alexa misinterprets or fails to understand certain commands; our system tries to infer the word the user really wanted to express. In this study, we conducted two types of tests: one involving evaluation with users aged 65 and older, and another simulating speech impairments or disorders. The approach presented would increase the understanding of an average of 73% of those commands that Alexa did not understand on the interaction with older adults, enhancing interaction quality. Two main factors affect Alexa’s comprehension: low voice intensity and pronunciation difficulties related to users’ advanced age. In the second test, when we simulated some disorders, only 41% of the words and sentences read achieved a similarity score above 0.9. This indicates that the Alexa device struggles to comprehend inputs from users with significant speech impairments. Moreover, in our second test with the second prompt, the correction accuracy of our system rose again to 76%, obtaining good results addressing and solving users’ errors. This improvement highlights the potential of our system to facilitate the communication between conversational agents and users.</p>