This project provides an AI-powered tool for real-time interview assistance, transcribing questions and generating responses. It targets individuals preparing for job interviews, offering a practice aid to improve confidence and response quality.

How It Works

The application utilizes OpenAI's Whisper model for accurate audio transcription and GPT models for intelligent response generation. It processes audio input, either through a microphone or system audio (via BlackHole on macOS), to capture interview questions. The transcribed text is then fed to a GPT model, which generates both concise and detailed answers displayed in a user-friendly GUI.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Requires Python 3.10+.
• An OpenAI API key is mandatory.
• For macOS, BlackHole is recommended for system audio recording.
• Setup involves cloning the repo, installing dependencies, and configuring the .env file with your OpenAI API key.

Highlighted Details

• Real-time audio processing and transcription.
• Intelligent response generation with quick and detailed answer options.
• Cross-platform compatibility (with macOS-specific audio routing).
• User-friendly GUI for interaction.

Maintenance & Community

Contributions are welcome via pull requests or issues. The project acknowledges inspiration from slgero/hack_interview and OpenAI developers.

Licensing & Compatibility

The repository does not explicitly state a license. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

This is a proof-of-concept tool intended for ethical use in practice and learning scenarios only. It is not designed for deceptive interview practices. The GUI is described as "hideous."