This study explores the role of Automatic Speech Recognition (ASR) technology in bridging the pronunciation gap for English language learners, particularly third-semester students of the English Education Department at UIN Walisongo Semarang. In addition, this study analyzes students’ learning experiences in using the ASR technology in ELSA Speak application, including the benefits and challenges they encounter. Using a qualitative case study approach, data were collected through questionnaires and interviews with 9 participants who actively use the ELSA Speak application, and the data were analyzed using thematic analysis. The findings indicate that ASR technology in ELSA Speak provides immediate feedback, allowing learners to identify and correct pronunciation errors efficiently. Moreover, the application enhances learner autonomy and motivation by offering flexibility in practice time and location. The study also highlights that ASR technology improves pronunciation awareness, particularly in distinguishing commonly mispronounced phonemes. However, challenges such as reliance on internet connectivity, limited access to premium features, and occasional inaccuracies in voice recognition were identified. Despite these limitations, participants reported increased confidence and engagement in pronunciation learning. The results suggest that ASR technology in ELSA Speak serves as an effective supplementary tool for pronunciation learning. However, for optimal results, it should be integrated with traditional speaking practice and instructor feedback. These findings contribute to understanding the impact of ASR technology in language learning and provide insights for educators on leveraging digital tools to support pronunciation development.