Bulk OCR: Automatically generate text docs from image uploads in Google Drive

I’ve got a ton of screenshots (like a thousand or more) that I need to run through OCR. Google Drive seems to do the best job, but it’s a pain to do one by one. Right now, I have to upload each photo, then right-click and choose ‘Open with Google Docs’ to get the text. It works great, but it’s super slow.

Is there a way to make Google Drive do this automatically when I upload photos? Like, create a doc with the text for each image right away?

I know there’s probably some fancy API stuff that could help, but I’m not really a coder. I’m hoping there’s a simple program or something I could use instead. Any ideas?

hey there! i’ve dealt with similar stuff before. have u tried using zapier? it can automate the process of uploading to drive and creating docs. might take a bit to setup but once its running itll save u tons of time. theres also some chrome extensions that can help with bulk ocr in drive, tho i cant remember the names rn

I’ve encountered this issue before and found a workaround using Google Apps Script. It’s not as complex as it sounds. You can create a script that automatically runs OCR on new image uploads to a specific folder in your Drive. The script can be set to trigger whenever a new file is added, creating a corresponding Google Doc with the extracted text. While it requires some initial setup, it’s quite straightforward and doesn’t need advanced coding skills. Once configured, it’ll process your images automatically, saving you significant time and effort. If you’re interested, I can point you to some resources on how to set this up.

I’ve been in a similar situation with a massive backlog of scanned documents. What worked for me was using Google Cloud Vision API coupled with Google Apps Script. It sounds techy, but it’s surprisingly manageable.

Here’s the gist: You set up a script that monitors a specific folder in your Drive. When new images are added, it automatically runs them through the Cloud Vision API for OCR, then creates a new Google Doc with the extracted text.

The initial setup does require some basic scripting, but there are plenty of tutorials out there. Once it’s up and running, it’s hands-off. You just dump your images into the designated folder, and the script does the rest.

It’s not exactly a ‘simple program,’ but it’s the most efficient solution I’ve found for bulk OCR in Google Drive. Plus, it’s scalable - whether you have 100 or 10,000 images, it handles them all automatically.