This paper focuses on AI tutors in foreign language learning, a field of application of AI tutors with great development, especially during the last years, when great advances in natural language understanding and processing in real time, have been achieved. These tutors attempt to address needs for improving language skills (speaking, or communicative competence, understanding). In this paper, a mixed-methos empirical study on the use of different kinds of state-of-the-art AI tutors for language learning is reported. This study involves a user experience evaluation of typical such tools, with special focus in their conversation functionality and an evaluation of their quality, based on chat transcripts. This study can help establish criteria for assessing the quality of such systems and inform the design of future tools, including concerns about data privacy and secure handling of learner information.