A multimodal AI system helps family members, caregivers, and therapists understand how a person communicates and choose a response tailored to that person's needs, history, and context.
Listen
Capture communication beyond words. Video and audio capture vocalizations and speech patterns that may otherwise be difficult to interpret.
Interpret
Put each signal into a person's context. A personalized AI model combines observed signals with the person's communication patterns, routines, and prior responses to identify possible needs.
Guide and learn
Recommend a response, learn what helps. Provide personalized next-step guidance to the clinical and family team. Record the person's response to inform future recommendations.
$10M+
in NIH and ARPA-H funding
Partners
Notre Dame + Texas A&M
Built for everyone who cares.
VoiceLove recommends; families and caregivers decide. We’re looking for partners in health systems, therapy practices, and payers.