GPT Automator - Your voice-controlled Mac assistant. GPT Automator lets you perform tasks on your Mac using your voice. For example, opening applications, looking up restaurants, and synthesizing information.
Made by Luke Harries and Chidi Williams at the London EA Hackathon, February 2023.
# on Ubuntu or Debian
sudo apt update && sudo apt install ffmpeg
# on Arch Linux
sudo pacman -S ffmpeg
# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg
# on Windows using Chocolatey (https://chocolatey.org/)
choco install ffmpeg
# on Windows using Scoop (https://scoop.sh/)
scoop install ffmpeg
requirements.txt
or pyproject.toml
files..env
file from the .env.example
file and fill in the OpenAI API key.python gui.py
to run the GUI and click 'Record' to say your prompt. Alternatively, run python main.py [prompt]
to run the CLI.GPT Automator converts your audio input to text using OpenAI's Whisper. Then, it uses a LangChain Agent to choose a set of actions, including generating AppleScript (for desktop automation) and JavaScript (for browser automation) commands from your prompt using OpenAI's GPT-3 ("text-davinci-003"), and then executing the resulting script.
Checkout our blog posts for more information:
This project executes code generated from natural language and may be susceptible to prompt injection and similar attacks. This work was made as a proof-of-concept and is not intended for production use.
Author: chidiwilliams
Source Code: https://github.com/chidiwilliams/GPT-Automator