Enhancing Students Speaking Skills Through Small Group Discussion Supported by ChatGPT Voice at SMPN 4 Koto Baru

This study aimed to examine the effect of Small Group Discussion supported by ChatGPT Voice on student’s speaking skills at SMPN 4 Koto Baru. A quantitative approach with a pre-experimental one-group pretest-posttest design was employed. The participants considered of 27 seventh-grade A student’s selected through total sampling. Data were collected using speaking tests assessing pronunciation, fluency, vocabulary, and grammar. The data were analyzed using descriptive statistics, the Shapiro-Wilk normality test, and Wilcoxon Signed-Rank Test. The results showed that the students mean score increased from 34.81 in the pre-test and 44.44 in the post-test. The Wilcoxon Signed-Rank Test yielded a significance value of 0.000 (p < 0.05). Therefore, the null hypothesis (H0) was rejected, and the alternative hypothesis (Ha) was accepted. Indicating that Small Group Discussion supported by ChatGPT Voice has a significant positive effect on students speaking skills. These findings suggest that integrating collaborative learning with AI-assisted speaking practice can serve as an effective strategy for improving students speaking skills.