Exploring Text-to-Video for Linguistically Responsive Teaching: A Case of the VEED GPT Model

• In Event: Language and AI Pedagogies, Technologies, and Practices

Proposal

Multilingual learners (MLLs), who are students in the process of learning English as a new or additional language, represent one of the fastest-growing groups in PreK-12 classrooms in the U.S. (U.S. Department of Education, 2022). However, research shows that teachers are not adequately prepared to teach this growing group of MLLs in the United States. In the monoglossic, English-only environment, MLLs' home language traditions are neglected, and their identities and cultures are underrepresented in K-12 classrooms (Brisk et al., 2002; Coady et al., 2016; Cochran-Smith et al., 2009; Darling-Hammond & Bransford, 2005; Ponzio, 2020; Yoon & Pratt, 2023).

Using an exploratory approach inspired by Adetayo et al. (2024), this paper seeks to critically analyze the potential and challenges of Video GPT by VEED (VEED.io) within the context of OpenAI’s ChatGPT 4, as a potential multilingual classroom teaching assistant. In particular, using the Linguistically Responsive Teaching (LRT) framework (Lucas & Villegas, 2010, 2013) and an asset-based approach, we aim to evaluate the features, challenges, and potential of Video GPT in assisting instructors and students, particularly those with MLLs.

To analyze the potential of AI-powered text-to-video tools, specifically VEED, we created a demo video on the lesson "Education in Ghana," targeting a multilingual and multicultural student audience. The demo focused on converting the lecture content to suit Mexican students with a Spanish language background while adjusting the spoken accent to an American accent, as most students were from the U.S. We incorporated Spanish captions to enhance comprehension and accessibility for the non-English-speaking audience. Additionally, we employed one of VEED’s avatar-based presentation features, which allowed for a visually engaging and consistent delivery of the content.

The findings suggest that VEED enhances accessibility by offering multilingual support, enabling teachers to deliver content in multiple languages, and making lessons more inclusive for English Language Learners (ELLs). Additionally, VEED's ability to integrate culturally relevant content into lessons highlights its potential to foster culturally responsive teaching practices.

However, the study also identified some limitations. VEED’s language and accent options are limited, which may lead to the exclusion of students whose languages and dialects are not represented. Additionally, the digital divide presents a barrier, as access to VEED’s full features may not be feasible for all educators or schools due to associated costs.

While this study serves as a pioneering examination of VEED’s applications in education, it is recommended that educators remain aware of these limitations and conduct further empirical testing in classroom environments to validate its practical effectiveness.

VEED’s multilingual text-to-speech (TTS) and captioning features ensure that content can be made accessible in various languages. The use of video lessons with multilingual support presents significant potential in PreK-12 education, particularly in countries like the U.S., where there is a diverse student population with varied linguistic backgrounds. Research indicates that in Gwinnett County, USA, approximately 80% of students are bilingual, speaking languages other than English, with English as their second language (Smith, 2024). This innovative tool could support teachers who may lack the capacity to address all the linguistic differences in their classrooms, which can affect the foundational learning of students in their early years (Relyea & Amendum, 2020; Rosheim et al., 2024).

VEED’s Video GPT can foster not only linguistically responsive teaching but also culturally responsive pedagogy. The content generated by the tool is based on the topics under instruction and can incorporate culturally relevant aspects into lessons (Hudley & Mallinson, 2017; Ladson-Billings, 2023). These lessons can be modified by the instructor to better reflect the cultural diversity of the students, thereby promoting inclusivity and cultural awareness in the classroom. Additionally, the tool has the potential to challenge assimilationist discourse and monoglossic ideologies that often dominate educational settings. By supporting multiple languages and dialects, VEED encourages pluralism and heteroglossic ideologies, recognizing and valuing the linguistic diversity of students (Ladson-Billings, 2021; Wallace & Brand, 2012). This allows for a more inclusive approach to education, where multiple languages and cultural backgrounds are acknowledged as assets rather than barriers.

VEED also serves as an excellent tool for teacher professional development. It can help educators learn more about their students’ cultural and linguistic backgrounds and assist in interpreting how these backgrounds impact learning. By using VEED, teachers can develop a deeper understanding of culturally responsive teaching practices and become more adept at incorporating these practices into their instruction (Pishghadam et al., 2023; Stepp & Brown, 2021). Another positive impact of VEED is its ability to boost the confidence of non-English-speaking instructors. Research such as Ghafar (2023) has shown that educators teaching in regions where English is the dominant second language face challenges, and AI tools like VEED could help address these challenges by providing a reliable resource for linguistically responsive teaching.

This study can serve as a foundational exploration for future research on using AI-powered tools like VEED and OpenAI’s Sora for video generation in education. Analyzing features like text-to-video AI tools may provide valuable insights into how these technologies can effectively enhance teaching in diverse linguistic environments. Despite this potential, VEED does have limitations. The number of languages and accents it can accommodate may exclude some students, particularly those whose languages or accents are not represented, making them feel left out. Additionally, teachers need technical skills to effectively manage video-based lectures in in-person classes, ensuring smooth integration of questioning and other interactive components. While VEED offers a free version, the costs associated with accessing its full features may contribute to the digital divide, particularly in underfunded schools. Therefore, we recommend a practical implementation of the VEED-generated lesson in a classroom while considering and addressing these limitations.

Authors

• Matthew Nyaaba, University of Georgia

• SungEun Min, Kutztown University