A voice-first mental wellness app where you simply speak about your day — no typing, no forms. Using Gemini's native multimodal audio capabilities, the app listens to your raw voice and extracts deep emotional signals directly from speech, without converting to text first. For every entry, AI surfaces: mood patterns, stress and energy levels, recurring themes, specific emotions tied to life events, and a breakdown of positive vs. negative self-talk with identified anxiety triggers. Users can review and opt out of any signal before it hits their dashboard — keeping them in full control of their emotional data. Over time, the dashboard becomes a personal emotional map: visual charts and trend analysis let users track their mental well-being journey across days, weeks, months, or years. The app learns what patterns precede a spiral and intervenes in real time — triggering breathing exercises, guided grounding, ambient music, physical movement prompts, or suggested journal entries tailored to what actually works for that user. The goal: steer every user toward positive self-talk, surface actionable insights for mental well-being, and catch emotional spirals before they happen.
More from Google I/O Hackathon
Billie Gene is a rapid vaccine-design research acceleration platform built to reduce the early bottleneck in responding to emerging viral outbreaks such as…

Our technology has reached the point where society needs to stop putting human lives at risk and start leveraging the tools around us. Picture this: a…

An RL environment to help train your managed agents in your voice.
1 in 4 Americans lives with a disability, yet most cities have no systematic way to audit pedestrian infrastructure for ADA compliance at scale. Manual…

Gemini Lifeguard Rescue is an AI-powered water safety system that helps lifeguards detect and respond to emergencies faster. The demo focuses on beach rescue…

Autonomous Android Simulator Player Fleet & Telemetry Ingest It is a premium, real-time platform designed to run autonomous gameplay testing agents on a…
