ChatBot has potential as a language learning tool, especially for learning Chinese vocabulary. This study aimed to investigate the impact of using a newly developed ChatBot to learn Chinese vocabulary by comparing how it works in different learning environments and to explore the ChatBot with reference to the Technology Acceptance Model (TAM). This study was conducted with 58 students divided into two independent groups. The control group used ChatBot in a one-on-many classroom. The experimental group applied the ChatBot in one-on-one tutor sessions. A pretest and a posttest were used to measure the effect of the ChatBot, while TAM was explored through questionnaire and interview. Data analysis includes a paired-sample t test, analysis of covariance, and levels of effect. The results indicated that the ChatBot significantly improved the students' learning achievement and that having a one-on-one environment may lead to better outcome than what could be achieved in a classroom. The TAM model was tested using partial least square. The result showed that perceived usefulness was the predictor of behavioral intention, whereas perceived ease of use was not. The students agreed that the ChatBot benefited their learning of Chinese vocabulary, with several adjustments need to be made for further progress.