benheckmann Posted June 27, 2023 Posted June 27, 2023 Hey there! I am writing a lot of prompts for ChatGPT nowadays and I sometimes struggle with manually reformatting or retyping text that I want in my prompt which is not easily copy and pasteable. I wanted a way to quickly capture a screenshot and convert the text to plain text, then copy it to my clipboard - all in one go. This very simple workflow will allow you to select a window within your screen, then takes a temporary screenshot, recognizes the text in the window using tesseract and copies the text. (Note that you need to install tesseract for this to work (e.g. `brew install tesseract`) and might need to set screen recording permissions for Alfred) You can download the workflow and find the installation instructions on its GitHub page here: https://github.com/benheckmann/alfred-textshot/releases/tag/v1.0. Please let me know if this is of any use to you and if you have suggestions to extend or improve this.
vitor Posted May 29 Posted May 29 On 6/27/2023 at 10:27 AM, benheckmann said: Please let me know if this is of any use to you and if you have suggestions to extend or improve this. OCRing is indeed quite useful, no doubt. My two tips to improve it: Add a Bundle Id in the details. This could be something like benheckmann.textshot. A bundle identifier is important to uniquely identify a workflow (like macOS does for apps). Add a Keyword Input (and make it configurable). We sometimes forget shortcuts we used for something, and a Keyword is always an alternative.
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now