healthnexus tab versions d4d

The Bridge2AI-Voice project provides an ethically sourced, multi-institutional, diverse dataset linking derived representations of human voice to detailed clinical and demographic information to enable research on voice as a biomarker of health. Version 1.0 includes derived data (e.g., spectrograms and acoustic features) for 12,523 recordings from 306 adult participants across five North American sites, with associated phenotype data and validated questionnaires. Original audio waveforms are not included in this initial release to minimize re-identification risk; transcripts of free speech are also removed.