At the moment, only the macOS version has been tested. The versions for Windows and Linux still need to be tested and completed.
Interviewee is a Java application that uses AI's API to provide audio transcribes, answers to interview questions and translating questions and answers to another language. The application captures audio during interviews, transcribes the conversations, and displays subtitles in real time, using AI's API for Speech-to-Text and Translation services.
Important! Our application does not encourage cheating in interviews or any fraudulent activities. We simply aim to help people be more confident in interviews and avoid silly mistakes.
Sometimes, interviews are conducted by people who are completely incompetent in what they are asking and often read questions from a list that have nothing to do with your field of expertise. Yet you still need to answer these questions to pass the interview, and this is where Interviewee can help you.
Additionally, sometimes you may be interviewed by a foreign company. Even if you're fluent in the foreign language, nerves can cause confusion or make you forget something crucial. Interviewee is here to help you with that.
In progress
- Real-time answering of interview questions.
- Real-time transcription of interview questions and answers.
- Integration with OpenAI's ChatGPT API for transcribing and translating audio.
- Support for multiple languages via OpenAI API translation.
- JavaFX-based GUI for displaying live transcriptions.
First, you need to install Homebrew, a package manager for macOS. You can install it by running the following command in the Terminal:
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
XCode Command Line Tools
BlackHole
Install XCode Command Line Tools by running the following command in the Terminal:
xcode-select --install
Install BlackHole, a virtual audio driver that allows you to route audio between applications. You can install it by running the following command in the Terminal:
brew install blackhole-2ch
Install Java 21 and Maven by running the following commands in the Terminal:
brew install openjdk@21
brew install maven
Setup "Multi-Output Device" and set it as a default sound output device for your macOS.
Guidelines are available HERE
Speakers audio on macOS will be recorded from the virtual "BlackHole 2ch" microphone. Your and BlackHole microphone
device names could be "BlackHole 2ch":
First, you need to install Chocolatey, a package manager for Windows. You can install it by running the following command in the PowerShell (run as administrator):
Set-ExecutionPolicy Bypass -Scope Process -Force; [System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor 3072; iex ((New-Object System.Net.WebClient).DownloadString('https://community.chocolatey.org/install.ps1'))
Install Java 21, Maven and Git by running the following commands in the PowerShell (run as administrator)
choco install openjdk
choco install maven
choco install git.install
Work in progress
Clone the repository:
git clone https://github.com/Alex777x/interviewee.git
Navigate to the Interviewee folder:
cd interviewee
Run Maven command:
mvn clean install
mvn clean javafx:run
Upon initiation, Interviewee will begin transcribing speaker output in real-time, generating a suggested response based on the conversation. Please note that it might take a few seconds for the system to warm up before the transcription becomes real-time.
- Start the application.
- Select the AI model and main language for the interview.
- Add your OpenAI API token.
- Click the "Start" button to begin the interview.
- The application will capture audio, transcribe it, and display the transcription in real-time.
- The application will also provide answers to the interview questions using the selected AI model.
- The application creates answers based on the value of the question text field. Use the "Clear" button to clear the question text field.
- Click the "Stop" button to end the interview or to pause answering questions.
In the current version, Interviewee creates small 3-second audio files and sends to OpenAI for recognition, and creates the question based on the recognized text. This approach is not optimal and will be improved in the future.
This project is licensed under the MIT License — see the LICENSE file for details.
Contributions are welcome! Feel free to open issues or submit pull requests to improve Interviewee.