A primary challenge for students with blindness or visual impairments (BVI) in programming education lies in the limited accessibility of debugging tools. While debugging is crucial, students with BVI often face significant barriers when trying to navigate to error messages, locate errors in the code, and verify fixes. This challenge is particularly problematic for Jupyter Notebook and its variants, as error messages are typically displayed in a separate block beneath the code. This separation makes it difficult for screen readers to effectively report the location and nature of errors.

To address this challenge, we developed AudioNB, an accessibility tool aimed at improving debugging support in Google Colab, a variant of Jupyter Notebook. AudioNB enhances debugging by providing real-time error message reading, direct navigation to the location of error, and quick syntax checks. It simplifies the debugging process for students with BVI, allowing them to work more efficiently by simplifying locating error messages or bugs.

The evaluation results demonstrate that AudioNB significantly reduced time-to-debug, with an average reduction of 72.5%. The debugging time reduction was consistently observed whenever the students returned to use AudioNB. Post-experiment surveys and interviews revealed positive user experiences and also provided information for potential pitfalls and future improvements.