MindMac - Better privacy-first, native ChatGPT Desktop for macOS. New: GPT-4-Vision and Internet Browsing

Hey there, looks great, but unfortunately I am still running a Mac Pro 2013 (yes the trashcan one) and the newest OS I can run is 12.7.4. Is there a bit technical blocker to allowing this app to work on my OS?

Thank you for your question! Some of the new macOS APIs aren’t quite cooperating with macOS 12 Monterey, so I’ve decided to prioritize support for macOS 13 and higher first. Rest assured, I’ll work on supporting macOS 12 as well in the near future. Stay tuned for updates!

Hello all,

As you may be aware, OpenAI unveiled its groundbreaking GPT-4o model yesterday, marking a significant milestone. This new model boasts both vision and text capabilities, with the promise of audio and video features coming soon. GPT-4o is now available on MindMac v1.9.16, which includes numerous enhancements and new functionalities. Users can also explore audio features in addition to DeepSeek models in this version.

Please read the full change log below.

:rocket: New

  • Added support for OpenAI’s new flagship GPT-4o model with vision and text capabilities.
  • Introduced DeepSeek models.
  • Added new models while removing deprecated ones for Perplexity.
  • Implemented Speech to Text feature with support from both OpenAI models and Apple native capability for prompt input.
  • Added support for Text to Speech, allowing users to choose between OpenAI models and Apple’s native capability for reading AI responses out loud.
  • Added actions for file upload, allowing audio files to be uploaded for transcription, summarization, translation, and key point extraction.
  • Added support for copying and pasting files (image, audio, document) into prompt editor.

:sparkles: Improved

  • Updated app Settings UI.

:wrench: Fixed

  • Resolved occasional scroll issue causing jumping.
  • Resolved issue of receiving infinite responses from Ollama llama2 model.
  • Addressed problem with stream response not functioning well with Perplexity models.
  • Fixed issue where the message view was being overlapped when the prompt editor grew in size.
  • Fixed issue that unable to use top_p, top_k parameters with Ollama endpoints.

Let’s check it out at here and share your feedback. Thank you all!