How vocal biomarkers can help deliver more empathetic public services

There is an old, apocryphal saying that people listen to 20 percent of what you say and 80 percent of how you say it. While that may have frustrated plenty of subject-matter experts over the years, it reveals an inconvenient truth: tone, cadence, and vocal delivery often matter more than the content of your speech.

A new generation of technologies is now taking this a step further. Tools like Empath‑AI are using ‘vocal biomarkers’ – measurable acoustic patterns in the human voice – to detect when someone may be distressed, struggling cognitively, or in need of additional support. It is a way of looking beyond people’s words, helping frontline service providers in the public sector adapt the way their conversations to the situation of the person they are speaking to.

The principle is already codified in legislation like the Consumer Duty Act. While laws like this are well‑intentioned – requiring organisations to put customers’ interests first and treat those in vulnerable circumstances fairly – they have a major flaw: they assume people are willing to share their situation or condition with a stranger, or even realise they are struggling at all in the first place.

The way we feel changes our voices

Anyone who has suffered from bouts of depression or anxiety will tell you the effects are physiological as well as biological. Your emotional state triggers changes in the nervous system that ripple through the body, including the muscles and breathing patterns that control the voice. Vocal cords respond to stress, anxiety, fatigue, or cognitive strain, creating subtle acoustic variations that are often detectable before a person consciously realises they are struggling.

These changes are far from random – different combinations form patterns that correlate with emotional or cognitive states. Without realising it, you will have done it yourself. When you have come home from work and asked your partner or flatmate how their day was and they tell you “it was fine”, but you know from their tone it was not, that is your brain picking up on vocal biomarkers. Empath-AI formalises this intuition, analysing the underlying acoustic features that sit beneath language itself.

The voice contains thousands of distinct acoustic variations across pitch, cadence, vocal energy, breath flow, and micro‑patterns that can be measured in milliseconds. When someone is anxious, the throat muscles tighten, airflow becomes restricted and the voice may sound strained or shaky. Depression often leads to quieter, lower‑energy speech. Cognitive decline or dementia can produce longer pauses between words – a kind of ‘cognitive stutter’ where the vocal cords struggle to maintain rhythm.

How the technology works

One way of thinking about technology like Empath-AI’s is as an X‑ray for the voice: a way of seeing beneath the surface to understand when someone might be struggling, even if they are trying to hold it together. It does not diagnose conditions or apply clinical labels and the customer does not need to say anything about their condition. Instead, the tool alerts the user that the person they are speaking to may need a gentler pace, clearer explanations, or additional support in a conversation.

These systems use advanced machine‑learning models trained on large datasets of vocal recordings. Rather than focusing on what people say, the models analyse how they say it: the variations in pitch, breathiness, timing, and vocal-fold vibration that shift when someone is feeling out of sorts or under strain. It identifies patterns that are statistically associated with moments when people may need additional support.

We are working with Empath-AI to build the ‘pattern layering’ infrastructure that aggregates multiple signals and amplifies the ones that matter most. The system is designed with strict safeguards, given it often involves sensitive or emotional content, confidentiality, data protection, and ethical governance.

Applying it to the public sector

Using vocal biomarkers originated in clinical research, but the technology is now being applied in adjacent sectors – and adoption is already underway in public services in other countries. The fire service in Cincinnati in the USA is using vocal analysis to support staff wellbeing. The Peruvian police force is using it in a different way, to help combat scamming and organised crime.

The potential applications across UK public services are broad. Whether it is policing, fire, or ambulance services, early detection of distress could help prevent crises, improve decision‑making, and support frontline workers who routinely face traumatic situations.

In prisons, officers could be alerted when an inmate is anxious, depressed, or at risk of self‑harm, enabling earlier intervention. The Ministry of Justice is already exploring technologies that support staff wellbeing and reduce burnout – a growing issue as services feel the strain of tight budgets and recruitment and retention challenges.

And in welfare services, integrating vocal biomarker technology into DWP telephony systems could make assessments more dignified and reduce the length of stressful conversations. People applying for benefits often face significant emotional strain, and early detection of distress could help staff adjust their approach, reduce misunderstandings, and improve outcomes.

More broadly, it also aligns with wider efforts to keep people in the workforce. Initiatives like Keep Britain Working emphasise the importance of supporting individuals before they fall out of the work, and struggle to return. Early detection of distress could help public services provide timely assistance, prevent burnout, and improve retention – which is absolutely critical at a time when finding the right talent is proving difficult.

A more empathetic future for public services

That broader context is absolutely critical. The UK’s mental health crisis is deepening, particularly among younger generations – according to NHS England, one in five people between the ages of eight and 25 have a probable mental health condition. Public services need to work in that context and prevention is consistently more effective – and more cost‑efficient – than cure. Vocal biomarker technology offers a way to change your approach or intervene earlier, and support people before they reach breaking point.

Ultimately, whatever their circumstances, people want to be treated with dignity. Tools like Empath-AI do not replace human judgement or compassion – if anything, they can enhance them. By giving frontline professionals better insight into how someone is feeling on the other side of the conversation, it helps them respond with empathy, patience, and care.

Public services are at their best when they recognise the humanity of the people they serve. Vocal biomarker technology offers a way to strengthen that connection, ensuring that the state listens not just to what people say, but how they are saying it.