Voices in Transition: EFL Learners’ Interaction with AI Tools to Improve Speaking
Authors
Zahratun Nufus
STAI Rasyidiyah Khalidiyah (Rakha) Amuntai
Pooveneswaran Nadarajan
Universiti Pendidikan Sultan Idris, Perak, Malaysia
Abstract
This study explores how English as a Foreign Language (EFL) learners experience and make sense of their interactions with Artificial Intelligence (AI) tools to develop speaking proficiency. Using a narrative inquiry approach, in-depth interviews and reflective journals were collected from 12 learners who regularly used ChatGPT, ELSA Speak, Duolingo, and MySpeaker Rhetorich. Grounded in Sociocultural Theory and Swain’s Output Hypothesis, the analysis examined how AI mediated learners’ cognitive and affective engagement within their Zones of Proximal Development. Findings revealed that AI tools created psychologically safe spaces, reduced speaking anxiety, and provided immediate, precise feedback, fostering greater fluency, accuracy, and learner autonomy. Learners valued AI’s personalization and accessibility but also noted limitations in cultural nuance, humor, and emotional depth, positioning AI as a supplement rather than a substitute for human interaction. This study offers qualitative insights into the affective and social dimensions of AI-mediated speaking practice, highlighting strategies for integrating AI into EFL pedagogy to support both linguistic development and emotional readiness for communication.