Spaces:
Sleeping
Sleeping
| title: AI Interview Bot | |
| emoji: π€ | |
| colorFrom: blue | |
| colorTo: indigo | |
| sdk: gradio | |
| app_file: app.py | |
| python_version: 3.13 | |
| license: mit | |
| sdk_version: 5.25.1 | |
| # π€ AI Interview Bot (1-on-1) | |
| This Space features 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! | |
| --- | |
| ## π‘ Features | |
| - β One-on-one video interview with webcam + mic | |
| - ποΈ Speech-to-text (voice input using Web Speech API) | |
| - π§ AI Interview logic via OpenAI GPT-4o | |
| - π Text-to-speech voice replies from the bot | |
| - π Live transcript display | |
| --- | |
| ## π How to Use | |
| 1. Click **"Start Interview"** β the bot will ask its first question aloud. | |
| 2. Speak your answer β 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. | |
| --- | |
| ## π§ 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. |