Now liveExplore Expression APIs
hume.ai logo
All posts

Case Study

Voice AI for Eldercare

To truly connect with users and provide a natural, empathic experience, EverFriends.ai needed an AI solution capable of understanding and responding to emotional cues. They found their answer in Hume's Empathic Voice Interface (EVI). EVI merges generative language and voice into a single model trained specifically for emotional intelligence, enabling it to emphasize the right words, laugh or sigh at appropriate times, and much more, guided by language prompting to suit any particular use case.

hume.ai logo
Hume AI Team
Share
Everfriends   Hero

Key Impacts

  • 88% of users reported increased mental stimulation
  • 90% of users reported decreased loneliness in 5-week trial
  • Positive effects seen within 3-5 sessions
  • 24/7 AI companionship at fraction of traditional care costs

About EverFriends

Loneliness and cognitive decline are major challenges in eldercare. In the U.S., 5.7 million people currently live with dementia, projected to reach 16 million by 2030 (source). Forty-three percent of adults over 60 report loneliness (source), and 24% of those over 65 are socially isolated (source). With professional companion costs rising, many families seek more affordable solutions.

EverFriends leverages empathic AI to provide affordable, always-available companionship. Its mobile app offers compassionate, responsive AI companions that enhance emotional well-being, support cognitive function, and help reduce loneliness in older adults and individuals with dementia.

Integrating Emotional Intelligence with EVI

To create a natural, emotionally aware experience, EverFriends integrated Hume’s Empathic Voice Interface (EVI)—a single model combining generative language and voice, trained for emotional intelligence. EVI can emphasize words, laugh or sigh at the right moments, and adapt to specific use cases through prompt design.

CEO Daniel Hungerford notes: "We were able to implement EVI fairly easily into our app. The team at Hume was very helpful with whatever we needed and with suggestions when we needed further guidance."

EVI has enabled EverFriends to deliver four key capabilities:

  1. Adaptive & Personalized: EVI adjusts its pace, style, and emotional tone to each user's needs.
  2. Emotional Support: Validates feelings and offers encouragement like “this is normal” or “you can do this.”
  3. Cognitive Support: EVI helps maintain cognitive function by assisting with story recall and maintaining consistency in memories. Preliminary research suggests these exercises may help slow cognitive decline (source).
  4. Daily Routine Reminders: Delivers daily prompts in a supportive, respectful tone.

EVI's Impact

While still in early stages, integrating Hume's EVI into EverFriends has shown promising results:

  1. Increased mental stimulation: 88% of pilot participants reported increased mental stimulation through brief 15-minute digital sessions.
  2. Reduced loneliness: In the same pilot program, an impressive 90% of users reported decreased feelings of loneliness during the initial five-week trial, with positive effects emerging within the first 3-5 sessions.

The CEO of EverFriends believes these metrics are largely driven by the voice-based element of interaction. When talking about one particular 77-year-old user, he mentions that:

She found companionship through our app during those quiet evening hours when loneliness felt most acute. Many elderly users struggle with traditional text-based interfaces - speaking out loud is not just more natural, it's more accessible for those with vision impairments, arthritis, or limited technology experience.

Looking Ahead

In 2025, EverFriends.ai plans to expand to users with autism, brain injuries, and mild cognitive impairment. The team anticipates growing its partnership with Hume as features like multilingual support become available, stating, "We will continue to use each other as sources of feedback and improvement to make our missions as effective and impactful as possible for those we serve."

By using EVI, EverFriends.ai delivers personalized, emotionally intelligent care that improves quality of life while easing the burden on caregivers and healthcare systems.

For more information on how empathic AI can enhance your digital solutions, please contact Hume AI.

Keep reading

Transforming AI Phone Support with WebAppClouds

EVI's conversational naturalness makes it exceptional for phone support. It recognizes tone, emotion, and phrasing, keeping interactions warm and efficient. The platform's intelligent end-of-turn detection ensures conversations flow smoothly without awkward pauses or interruptions. For WebAppClouds' clients, this translates to support customers actually enjoy. Instead of navigating complicated menus, customers simply say what they need, whether it's booking, rescheduling, or getting information. EVI integrates seamlessly with the WebAppClouds system, enabling real-time scheduling updates while delivering faster responses and consistent brand experiences.

Aaron Greene / Nov 6, 2025

GAF Powers Professional Training with Hume’s Text-to-Speech

To support their extensive training programs and marketing initiatives, GAF leverages Hume's text-to-speech technology to make internal training videos and marketing voiceovers. Our partnership addresses several key needs: Professional training content: Delivering consistent, high-quality audio for thousands of contractors and employees. Marketing collateral: Producing engaging voiceovers for promotional content and product demonstrations. Scalable production: Generating content without the logistics and cost of traditional voice recording. Hume's voice design also proved ideal for GAF. The platform's natural, expressive voices maintain the authoritative yet approachable tone that GAF needs to communicate with contractors, retailers, and customers. Unlike synthetic voices that can sound robotic or overly casual, Hume's TTS technology delivers the polished, trustworthy quality expected from an industry leader.

Aaron Greene / Nov 3, 2025