South Korea-based DoctorPresso has rolled out REDI, an advanced voice-based diary app that can detect early signs of depression by analysing users’ speech patterns.
REDI app is designed to analyse four important characteristics of the users’ voice- average pitch, pitch variability, spectral centroid, and spectral roll-off.
According to previous research, the voice elements change as the depression worsens, and lower pitch, greater variability, and shifts in the voice’s frequency range serve as indicators.
Considering the voice factors, REDI’s AI technology classifies users into three depression stages, non-depressed (ND), mild depression (mDE), and major depressive episode (MDE).
It is a new approach to mental health care and promises to change the way emotional well-being is being monitored and managed, said DoctorPresso.
Doctorpresso CEO HwanBo Jung said: “The strength of REDI is that it takes something we all do- speak- and turns it into a tool for mental health. It’s like having a mental health checkup in your pocket.
As REDI prepares for its global rollout, DoctorPresso is optimistic about the app’s impact.
“Mental health care is evolving. With REDI, we’re giving people the power to take control of their mental well-being in a way that’s easy, private, and effective”, he added.
Doctorpresso CMO Shin said: “While someone might not realize they’re depressed, their voice often carries subtle clues. With REDI, we can capture those clues and provide real-time analysis that helps users understand their emotional state in ways traditional tools can’t.”
According to the company, depression affects more than 258 million people worldwide and is not just an emotional struggle, but a major cause of disability and lost productivity.
Conventional screening methods, such as questionnaires, often fail to accurately assess the depth of a person’s mental state.
DoctorPresso harnessed the power of AI to develop an app that listens to what you say, and how you say it, providing deeper insights into your mental health.
Unlike other AI tools that transfer data to the cloud, REDI employs a Small Language Model (SLM), which processes all voice data directly on the user’s device.
Its real-time, voice-based depression screening capability could help millions recognise the early warning signs of mental health and seek help before conditions worsen.
The app also provides a habit-tracking calendar that monitors lifestyle factors such as sleep, alcohol consumption, and physical activity, which are closely linked to emotional health.
