James Anibal ^1,2* Hannah Huth ² Ming Li ² Lindsey Hazen ² Yen Lam ³ Hang Nguyen ³ Phuc Hong ³ Michael Kleinman ⁴ Shelley Ost ⁴ Christopher Jackson ⁴ Laura Sprabery ⁴ Cheran Elangovan ⁴ Balaji Krishnaiah ⁴ Lee Akst ⁵ Ioan Lina ⁵ Iqbal Elyazar ⁶ Lenny Ekawati ⁶ Stefan Jansen ⁷ Richard Nduwayezu ⁷ Charisse Garcia ² Jeffrey Plum ² Jacqueline Brenner ² Miranda Song ² Emily Ricotta ⁸ David Clifton ¹ Louise Thwaites ³ Yael Bensoussan ⁹ Bradford Wood ²

• ¹ University of Oxford, Oxford, United Kingdom
• ² National Institutes of Health (NIH), Bethesda, Maryland, United States
• ³ Oxford University Clinical Research Unit in Vietnam (OUCRU), Hanoi, Vietnam
• ⁴ University of Tennessee Health Science Center (UTHSC), Memphis, Tennessee, United States
• ⁵ Johns Hopkins Medicine, Johns Hopkins University, Baltimore, Maryland, United States
• ⁶ Oxford University Clinical Research Unit Indonesia, Jakarta Pusat, Indonesia
• ⁷ University of Rwanda, Kigali, Kigali City, Rwanda
• ⁸ Uniformed Services University of the Health Sciences, Bethesda, Maryland, United States
• ⁹ University of South Florida, Tampa, Florida, United States

Artificial intelligence (AI) models trained on audio data may have the potential to rapidly perform clinical tasks, enhancing medical decision-making and potentially improving outcomes through early detection. Existing technologies depend on limited datasets collected with expensive recording equipment in high-income countries, which challenges deployment in resource-constrained, high-volume settings where audio data may have a profound impact on health equity. This report introduces a novel data type and a corresponding collection system that captures health data through guided questions using only a mobile/web application. The app facilitates the collection of an audio electronic health record ("Voice EHR") which may contain complex biomarkers of health from conventional voice/respiratory features, speech patterns, and spoken language with semantic meaning and longitudinal context -potentially compensating for the typical limitations of unimodal clinical datasets. This report presents the application used for data collection, initial experiments on data quality, and case studies which demonstrate the potential of voice EHR to advance the scalability/diversity of audio AI.