# Project export: Ohlone A^2PI+

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: UC Berkeley AI Hackathon 2025
- Tagline: Over half of U.S. adults with mental health issues go untreated. Our AI- assistant detects mood from voice and instantly offers personalized support and resources in English or Spanish.
- Devpost: https://devpost.com/software/ohlone-a-2pi
- GitHub: not linked
- Demo: https://v0.dev/chat/emotion-detection-app-Dm4fy4avolH
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

The inspiration behind this project came from our shared interest in combining emotional intelligence with modern AI. Our team wanted to explore how technology could be more empathetic, especially for people struggling with emotional regulation, communication barriers, or mental health challenges. We believe machines should understand not only what we say but also how we feel when we say it. Seeing how platforms like groq, Anthropic, and Vapi are advancing voice AI made us curious about what we could build using their tools.

### What it does

The app creates generative responses based on the user’s voice input, providing insight into the complexity of their emotions, suggesting healthy coping habits, and offering additional resources for support.

### How we built it

Frontend Built using Next.js 15 + TypeScript Styled with Tailwind CSS and ShadCN UI Implemented MediaRecorder to capture audio Audio Conversion Initially used ffmpeg.wasm to convert audio blobs to 16kHz mono WAV format (which didn’t work as expected), so we switched to existing systems API Integration Google Gemini Google Cloud Natural Language API Test Mode Created a feature to generate and convert 1 second of silence for API testing

### Challenges we ran into

Debugging complex AI interactions and testing the system repeatedly to ensure accuracy and stability under continuous use.

### Accomplishments we're proud of

Built a fully working app in under a day. Integrated cutting-edge AI APIs. Created a seamless, multilingual mental health assistant offering instant, personalized support.

### What we learned

The importance of teamwork and quick problem-solving. How to effectively integrate advanced AI APIs. The challenges of debugging AI systems and ensuring accurate mood detection. And the real impact AI can have on mental health support.

### What's next

for Ohlone A²PI+ Expand to more languages, improve AI accuracy, add interactive features like acts of consolation, and test with real users to enhance support and usability.

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- Next.js (technology) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code
- Vercel (technology) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.