https://github.com/furkankhann/interviewbot
Welcome to FurkanBot – an intelligent voice assistant built using Flask, Google Gemini (Generative AI), and gTTS. It listens to your voice, processes your query using an AI model (with Furkan's persona), and responds both as text and speech.
https://github.com/furkankhann/interviewbot
agentic-ai flask gemini gemini-api machine-learning nlp python webapp
Last synced: 2 months ago
JSON representation
Welcome to FurkanBot – an intelligent voice assistant built using Flask, Google Gemini (Generative AI), and gTTS. It listens to your voice, processes your query using an AI model (with Furkan's persona), and responds both as text and speech.
- Host: GitHub
- URL: https://github.com/furkankhann/interviewbot
- Owner: FurkanKhann
- Created: 2025-06-16T20:07:16.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-07-06T19:24:40.000Z (12 months ago)
- Last Synced: 2025-07-06T20:33:28.066Z (12 months ago)
- Topics: agentic-ai, flask, gemini, gemini-api, machine-learning, nlp, python, webapp
- Language: Python
- Homepage: https://bot-1-nizh.onrender.com/
- Size: 34.2 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🎙️ FurkanBot – AI-Powered Voice Assistant
Welcome to **FurkanBot** – an intelligent voice assistant built using **Flask**, **Google Gemini (Generative AI)**, and **gTTS**. It listens to your voice, processes your query using an AI model (with Furkan's persona), and responds both as text and speech.
Live demo coming soon!
---
## 🚀 Features
✅ Voice input via browser (Web Speech API)
✅ Gemini-powered answers with personalized tone
✅ gTTS voice output
✅ Clean UI with loader
✅ 5-second auto-record timeout
✅ Easy to run locally
---
## 📦 Tech Stack
- **Frontend**: HTML, CSS, JavaScript
- **Backend**: Python + Flask
- **AI**: Google Generative AI (Gemini API)
- **Speech**: Web Speech API (input) + gTTS (output)
---
## 🧠 Project Structure
```text
FurkanBot/
├── app.py # Flask backend
├── talker.py # Gemini prompt logic (persona-based)
├── interview.txt # Furkan's persona description
├── templates/
│ └── index.html # Web interface (HTML + CSS + JS)
├── .env # Stores API key (not committed)
├── requirements.txt # Python dependencies
└── README.md
```
## ⚙️ Setup Instructions
### 1. Clone the Repository
```bash
git clone https://github.com/FurkanKhann/FurkanBot.git
cd FurkanBot
```
### 2. Create a Virtual Environment
```bash
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
```
### 3. Install Dependencies
``` bash
pip install -r requirements.txt
```
### 🧠 How It Works
Speech is captured using the browser’s microphone.
Text is sent to Flask backend (/ask endpoint).
Gemini generates a response based on interview.txt.
gTTS converts text to speech and returns it as base64 audio.
Audio + text is rendered in the browser.
### 🧪 Run the App
``` bash
python app.py
```