https://github.com/divya19gupta/prepbot-interviewsimulator
https://github.com/divya19gupta/prepbot-interviewsimulator
Last synced: about 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/divya19gupta/prepbot-interviewsimulator
- Owner: Divya19gupta
- Created: 2025-06-24T13:37:39.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-06-24T14:21:59.000Z (about 1 year ago)
- Last Synced: 2025-06-24T14:44:12.591Z (about 1 year ago)
- Language: TypeScript
- Size: 134 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🎙️ PrepBot: AI Interview Simulator
PrepBot is an AI-powered interview simulator that asks questions, records spoken answers, transcribes them using speech-to-text, and provides instant feedback using an LLM (e.g., Gemini or GPT).
---
## 🚀 Getting Started
### 1. Clone the Repo
```bash
git clone https://github.com/Divya19gupta/PrepBot.git
cd PrepBot
```
### 2. Add Your API Keys
Create a `.env` file in the `server/` folder with the following format:
```env
GEMINI_API_KEY=your_gemini_key
```
### 3. Install Whisper.cpp in the Project
```cd server
git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp
make
sh ./models/download-ggml-model.sh base.en
cmake -B build
```
### 4. Run the App
#### Backend
```bash
# In /server
npm i
npm run dev
```
#### Frontend
```bash
cd ../client
npm i
npm run dev
```
---
## 🛠 Features
- 🎤 Voice recording with `MediaRecorder`
- 🧠 Answer transcription (via Whisper API or whisper.cpp)
- 🤖 AI feedback scoring using Gemini or GPT
- 📊 Scored on clarity, relevance, structure, and confidence
---
## 📌 Notes
- Be sure to **not commit your `.env`** file or `node_modules/`.
- You can deploy this locally or host with services like Render, Railway, or Vercel.
---
