Skip to content

Application that simulates a voice-based AI interviewer. The interviewer uses Text-to-Speech (TTS) to ask questions, and Speech-to-Text (STT) to transcribe the candidate’s responses. An LLM (GPT-4) will provide context-driven follow-up questions and ultimately rate the candidate. Real time rating is visible to Admin only.

Notifications You must be signed in to change notification settings

Tashu014/livekit-assistant

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LiveKit Assistant

Demo Video Demo Video

Admin - Configure Interviewer Screen Admin - Configure Interviewer Screen

Admin - View Results Screen Admin - View Results Screen

First, create a virtual environment, update pip, and install the required packages:

$ python3 -m venv .venv
$ source .venv/bin/activate
$ pip install -U pip
$ pip install -r requirements.txt

You need to set up the following environment variables:

LIVEKIT_URL=...
LIVEKIT_API_KEY=...
LIVEKIT_API_SECRET=...
DEEPGRAM_API_KEY=...
OPENAI_API_KEY=...

Then, run the assistant:

$ python3 assistant.py download-files
$ python3 assistant.py start

Finally, you can load the hosted playground and connect it.

About

Application that simulates a voice-based AI interviewer. The interviewer uses Text-to-Speech (TTS) to ask questions, and Speech-to-Text (STT) to transcribe the candidate’s responses. An LLM (GPT-4) will provide context-driven follow-up questions and ultimately rate the candidate. Real time rating is visible to Admin only.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages