Print to Voice: Developing an AI-Generated Audiobook for Literatur im Deutschunterricht’s Class

DOI

10.2991/978-2-38476-501-0_12How to use a DOI?

Keywords

ADDIE model; AI-generated audiobook; CEFR A2; German as a foreign language; higher education; literature teaching; pronunciation modelling; text-to-speech

Abstract

Literature courses in German as a foreign language often struggle with low reading motivation, limited listening input, and misalignment between textual complexity and learners’ proficiency. This study reports the design, development, and classroom piloting of an AI-generated audiobook based on an original storybook written to the CEFR A2 level, intended to enhance literary comprehension in Literatur im Deutschunterricht. Guided by the ADDIE model, a needs analysis with lecturers and undergraduates was conducted and produced chaptered audio using a state-of-the-art text-to-speech platform, ElevenLabs. The audiobook was used in an undergraduate literature class and tested by experts, tests on listening and reading comprehension and vocabulary. Findings indicate improved listening skills and pronunciation modeling got better, and students were more engaged. However, the results also showed some of the limitations of synthetic narration, such as the need for fine-grained emotional nuance and sentence-level stopping, which required specific changes to the script and sequencing. The study shows a useful technique to use AI-based audiobooks in literature classes in places where there aren’t many resources. This makes the teacher’s job easier and gives students more access to real-sounding input. The study demonstrates a practical pathway for integrating AI-based audiobooks into literature instruction in resource-constrained contexts, reducing instructor workload and widening access to authentic-sounding input.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Indah Aini
AU  - Balazs Huszka
AU  - Tanti Kurnia Sari
AU  - Ahmad Sahat Perdamean
AU  - Nurhanifah Lubis
AU  - Ryan Dallion
PY  - 2025
DA  - 2025/12/16
TI  - Print to Voice: Developing an AI-Generated Audiobook for Literatur im Deutschunterricht’s Class
BT  - Proceedings of the International Seminar of Languages, Arts and Literature Education (ISLALE 2025)
PB  - Atlantis Press
SP  - 106
EP  - 117
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-501-0_12
DO  - 10.2991/978-2-38476-501-0_12
ID  - Aini2025
ER  -