Update README.md

README.md

@@ -1,12 +1,43 @@
 ---
-title: Interview Bot
-emoji: 🏃
-colorFrom: gray
-colorTo: green
+title: AI Interview Bot
+emoji: 🎤
+colorFrom: blue
+colorTo: indigo
 sdk: gradio
-sdk_version: 5.25.1
+sdk_version: 4.0.0
 app_file: app.py
-pinned: false
+python_version: 3.10
+license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🎤 AI Interview Bot (1-on-1)
+
+This is a Hugging Face Space featuring a **1-on-1 video interview bot** powered by **OpenAI GPT-4o** with **speech-to-speech** capabilities. It asks you questions, listens to your voice responses, and replies out loud in real time!
+
+---
+
+## 💡 Features
+
+- ✅ One-on-one video interview with webcam + mic
+- 🎙️ Speech-to-text (voice input using Web Speech API)
+- 🧠 AI Interview logic via OpenAI GPT-4o
+- 🔊 Text-to-speech voice replies from the bot
+- 📜 Live transcript display
+
+---
+
+## 🚀 How to Use
+
+1. Click **"Start Interview"** – the bot will ask its first question aloud.
+2. Speak your answer – your voice will be transcribed automatically.
+3. The AI interviewer will respond out loud and continue the conversation.
+4. Repeat until the bot ends the interview or you stop.
+
+---
+
+## 🧠 Model
+
+Uses `gpt-4o` from OpenAI with the following prompt format:
+
+```plaintext
+You are a smart, friendly AI interviewer. Ask one question at a time.