Multimedia GPT

Empowering your ChatGPT with image, video, and audio inputs. Topics


Last 30 days:

Open issues
PRs opened

Project type

Machine Learning

Project tech


Currently seeking

  • Developers
  • Testers

Contribution overview

The maintainers of this project have not provided a contribution overview.


Multimedia GPT connects your OpenAI GPT with vision and audio. You can now send images and audio recordings using your OpenAI API key, and get a response in both text and image formats. Right now, we are exploring ways to connect even more modalities of data, such as videos, PDFs, webpages, etc. All is made possible by a prompt manager inspired and built upon Microsoft Visual ChatGPT.


This project is at its starting phase, and more features will be added soon. Please consider ⭐ star if this idea is interesting. Any contributions would be appreciated, and we especially would like your feedback as a user of our technology. Testing this should be quick and fun!

Project listed on March 20, 2023