Using AI tools in a virtual desktop for transcription

Transcribing audio into text is part of the research process for many researchers. Manually transcribing text can be time-consuming, so an increasing number of researchers are using software to transcribe and translate, for example, interview or focus group audio recordings. Recognising the need, we developed training and piloted a transcription service, to enable researchers to use AI responsibly across multiple languages, while being mindful of data sovereignty considerations.In this talk, we will share the transcription training we have delivered and the pilot of a simple, easy-to-use, locally hosted, ephemeral digital transcription desktop in 2025. This desktop, developed in collaboration with the core Nectar team, runs on existing CeR-managed local infrastructure, and enables researchers to safely and efficiently transcribe digital audio content using AI-powered tools.Training, technical and ethical considerations, desktop environment development, support material creation and outcomes will be discussed.ABOUT THE AUTHOR(S)Yvette Wharton works at the Centre for eResearch, Waipapa Taumata Rau, University of Auckland. Most recently she has been working as the Research Data Management Programme Lead, working on the Secure Research Environment and machine-actionable Data Management Planning initiatives. http://orcid.org/0000-0002-6689-8840Noel Zeng works at the Centre for eResearch, Waipapa Taumata Rau University of Auckland. He worked on the Instrument Data Service and led consultancy projects with research groups in urban planning, archaeology and anthropology, supporting software development, data collection and analysis. He is interested in applying his software development and data analysis experience to collaborate with academics from across disciplines, especially social sciences and humanities.Sean Matheny began his career working in the physics department of the largest radiation oncology treatment provider in the U.S. There, he helped to improve QA, dosimetry, and treatment planning and delivery via technology, machine learning, and automation. For the last 8 years, he’s primarily worked in roles that have enabled research cloud platforms and HPC (high performance computing) in both the Centre for eResearch (University of Auckland), and NeSI. Currently, he helps operate the Auckland node of the Nectar Research Cloud, at the Centre for eResearch.Toby Johnson works as an eResearch Engagement Specialist at the Centre for eResearch, Waipapa Taumata Rau University of Auckland. He received his PhD in Psychology from the University of Exeter where he investigated computational models of learning. At the Centre for eResearch he provides digital research and AI skills training and assists researchers in accessing compute resources, including the Secure Research Environments. -----For more information about the eResearch NZ / eRangahau Aotearoa conference, visit: https://eresearchnz.co.nz/