This project is an AI Fitness trainer that generates personalized workout & diet plans based on a voice conversation with an AI Agent using Vapi. The user will register for an account using clerk authentication (google, github, & email), and then have a voice conversation with the AI agent to discuss infomation such as weight, height, dietary conditions, fitness goals, ect. This information will then be stored in a convex database and fed into Gemini API to generate a custom plan for the user in real time.
DEMO VIDEO:
Tech Stack:
- Next.Js, React, Tailwind & Shadcn UI
- Voice AI Assistant (Vapi)
- LLM Integration (Google Gemini API)
- Authentication & Authorization using Clerk
- Convex Database
- Set up authentication with clerk
- Set up and configure vapi voice agent
- Set up database with convex
- Implement webhook between clerk and convex
- Generate home screen & generate-program pages
- Connect requests to gemini api
- Build profile page
- Deploy
This is a Next.js project bootstrapped with create-next-app.
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun devOpen http://localhost:3000 with your browser to see the result.
You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.
This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.
To learn more about Next.js, take a look at the following resources:
- Next.js Documentation - learn about Next.js features and API.
- Learn Next.js - an interactive Next.js tutorial.
You can check out the Next.js GitHub repository - your feedback and contributions are welcome!
The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.
Check out our Next.js deployment documentation for more details.