Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Celtic
Suparmi Suparmi
English Education Department, Faculty of Tarbiyah and Teacher Training, Universitas Islam Negeri Maulana Malik Ibrahim Malang, Jawa Timur, Indonesia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Exploring the role of ChatGPT voice conversation feature in improving EFL students’ speaking self-efficacy Retno Tri Wahyuningtyas; Suparmi Suparmi
Celtic : A Journal of Culture, English Language Teaching, Literature and Linguistics Vol. 13 No. 1 (2026): Vol. 13 No. 1 (2026): June 2026
Publisher : University of Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/celtic.v13i1.44287

Abstract

This study aims to explore the role of ChatGPT's voice conversation feature in improving EFL students’ speaking self-efficacy. A qualitative design supported by quantitative data was employed, involving 21 students from the English Education department selected through purposive sampling. The data were collected through a questionnaire and semi-structured interviews. The questionnaire result revealed that students’ speaking self-efficacy was at a moderate level across all five dimensions: linguistic, communicative, task-specific, interactional, and affective self-efficacy. Meanwhile, the interview findings indicated that the ChatGPT voice conversation feature significantly enhanced students’ speaking confidence by providing real-time feedback, affirmative responses, and a natural human-like interaction. It also provided a non-judgmental environment that allowed students to practice speaking independently, serving as a motivating speaking partner. Hence, this study highlights the potential of the ChatGPT voice conversation feature as an AI-based digital tool that can be integrated into language learning to foster students’ speaking confidence and improve their speaking self-efficacy.
Co-Authors Retno Tri Wahyuningtyas