Project Info
This project did not submit a demo video on Devpost.
Inspiration
Our inspiration comes from the challenges faced by international students, who often struggle with poor mental health while being far from home. The emotional toll of adapting to a new environment, compounded by time zone differences and lack of real-time support, can leave students feeling isolated. DayTalks aims to bridge that gap by providing a supportive, AI-driven platform where users can express their emotions, track their mental health, and feel connected no matter the distance.
What it does
DayTalks is an AI-powered mental health app that allows users to log their emotions through voice recordings, track their moods over time, and receive personalized emotional insights, helping them stay connected and supported wherever they are.
How we built it
We developed the frontend using React.js and Tailwind CSS to create a dynamic, responsive, and user-friendly interface. The backend is powered by FastAPI, ensuring efficient and scalable communication. For emotional analysis, we integrated HumeAI to deliver real-time emotional intelligence. MongoDB manages user authentication and secure data storage. We incorporated Groq and Llama 3.1 to provide personalized feedback and insights, further enhancing user engagement. Additionally, Deepgram was used for accurate and seamless speech recognition, allowing users to easily log their emotions through voice.
Challenges we ran into
Creating a welcoming UI: Designing a mental health app that feels personalized and comforting while maintaining simplicity and usability. Implementing JWT tokens: Learning how to securely manage user authentication using JWT for a scalable, secure login system. Fetching user history: Ensuring efficient retrieval and display of personalized data was key to user experience. Optimizing backend efficiency: Ensuring smooth communication between the frontend and backend, especially with real-time interactions.
Accomplishments we're proud of
Building a full stack + AI-powered application in just 36 hours. Seamless teamwork and communication, even when faced with technical challenges. Creating a personalized and welcoming user interface, thoughtfully designed for mental health support.
What we learned
Early ideation is key: By brainstorming and planning before the hackathon, we were able to hit the ground running and start building immediately. The importance of UI prototyping: We realized the value of laying out the UI in tools like Figma, as it allows frontend developers to begin implementation faster and stay aligned with the design vision. Setting clear checkpoints: Establishing checkpoints throughout the hackathon helped us stay on track and ensure progress, making sure that we delivered a solid MVP on time.
What's next
Premium Subscription: Mood tracking synced with iCal. VeronicaAI talks back in conversations. Customizable AI voice for a personal touch. Collaboration: Smartwatch integration for on-the-go tracking. Partnerships with fitness centers and wellness industries. Corporate investment for employee wellness programs.
CalHacks 2024 Project: DayTalks
DayTalks is a mental health-focused web application designed to help users track and reflect on their emotional well-being. At the heart of DayTalks is its AI-powered friend, Veronica, who listens to users through voice recordings, analyzes the emotions conveyed, and provides personalized emotional insights. By leveraging cutting-edge AI and emotional analysis tools like HumeAI, the app creates a supportive environment where users can express themselves freely and receive meaningful feedback. By offering real-time feedback, DayTalks empowers users to understand their emotions better and take proactive steps to enhance their well-being.
Tech Stack:
- Frontend: React.js, Tailwind CSS
- Backend: FastAPI
- Database & Authentication: MongoDB, JWT
- Speech Recognition: Deepgram
- Emotional Analysis: HumeAI
- AI Feedback: Groq
Installation
To get a local copy up and running, follow these steps:
- Install Node.js and npm on your computer.
- Clone the Repository:
git clone https://github.com/your-username/calhacks-24.git
- Navigate into the project directory and then the frontend folder:
cd calhacks-24
cd frontend
- Install Frontend Dependencies
npm install
- Navigate back to the root project folder and into the backend folder:
cd ../backend
- If using FastAPI with Python, install backend dependencies (e.g., using pip)
pip install -r requirements.txt
- Install backend dependencies
npm start
Usage
- Open the app in your browser at http://localhost:3000.
- Sign in or create an account.
- Use the mood calendar to log your emotions or interact with the AI friend to receive personalized insights.
Features
- AI Friend Veronica: Interact with an AI-powered friend for personalized emotional insights.
- Mood Calendar: Log and visualize your moods on a calendar interface.
- Emotional Insights: Receive real-time emotional analysis and feedback using HumeAI.
- User Login: Secure authentication with JWT ensures users' mood logs and emotional insights are saved and accessible across sessions.
Contributors
License
This project is licensed under the MIT License - see the LICENSE file for details.
Analysis
View
Metric
- 26
- 10
- 7
- 4
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CSSIn code
- FastAPIIn code
- FlaskIn code
- HTMLIn code
- JavaScriptIn code
- PythonIn code
- ReactIn code
- Tailwind CSSIn code
- MongoDBClaimed
8 of 9 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
200 KB
Source files
75
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
lizatinku/CalHacks24
116 files · 10.0 MB · @ 7baf097
Structure
Interface
37 files · 32%Screens, components and styles rendered to the user.
Application logic
34 files · 29%Domain rules, services and shared utilities.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- Python49%
- JavaScript31%
- CSS14%
- XML3%
- HTML2%
- Markdown1%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
emotionTrack_server/requirements.txt
pypi · 40- aiofiles
- annotated-types
- anyio
- bcrypt
- certifi
- cffi
- charset-normalizer
- click
- cryptography
- dnspython
- ecdsa
- eval_type_backport
- fastapi
- h11
- httpcore
- httpx
- hume
- idna
- +22 more
frontend/package.json
npm · 28- @ffmpeg/ffmpeg
- @svgr/webpack
- @testing-library/jest-dom
- @testing-library/react
- @testing-library/user-event
- axios
- chart.js
- d3-scale
- frontend
- react
- react-calendar
- react-circular-progressbar
- react-dom
- react-icons
- react-scripts
- record
- recorder-js
- web-vitals
- +10 more
package.json
npm · 27- @ffmpeg/ffmpeg
- @svgr/webpack
- @testing-library/jest-dom
- @testing-library/react
- @testing-library/user-event
- axios
- chart.js
- d3-scale
- frontend
- react
- react-calendar
- react-circular-progressbar
- react-dom
- react-icons
- react-scripts
- recorder-js
- web-vitals
- +10 more
backend/requirements.txt
pypi · 5- deepgram-sdk
- Flask
- Flask-SocketIO
- httpx
- python-dotenv
src/requirements.txt
pypi · 5- deepgram-sdk
- janus
- PyAudio
- python-dotenv
- websockets
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.