Google Cloud Vision Make integrationAutomate Google Cloud Vision with Make.
What if every image your team receives could be read, tagged and checked without anyone opening it? The Google Cloud Vision Make integration gives you 9 modules, 4 actions and 5 searches, to turn pictures and scanned files into data. This guide shows you how to connect it and build your first scenario.
Verified Trustpilot reviews · AI, automation & growth agency
What can the Google Cloud Vision Make integration do for you?
The Google Cloud Vision Make integration lets a Make scenario, the automation you build in Make, hand an image or a scanned file to Google's vision service and get back text, labels, faces, colors or a safety verdict. Each result becomes data the next step can use, with no code to write.
Scanned paperwork turned into text. A signed delivery note or a multi-page PDF lands somewhere your scenario can reach it. Run Text Detection (OCR) within a File and Iterate the Result Array reads it page by page, so an accounting tool or a spreadsheet can receive the words instead of a picture.
A photo library that sorts itself. Run Label Detection within an Image names what a picture shows, and Compute Image Dominant Colors and Iterate the Result Array gives its main colors. A product team can file pictures by subject and shade without tagging them by hand.
Uploads screened before they go public. Detect Potentially Unsafe or Undesirable Content within an Image gives each user picture a verdict before it reaches a website or a community space.
What the integration does not do: it has no trigger, so something else has to start the scenario, and there is no Make an API Call module for requests the 9 modules do not cover. The same service often has an n8n node too; the n8n vs Make comparison helps you choose, and the Make training walks you through your first builds.
How do you connect Google Cloud Vision to Make?
- 01
Prepare your Google Cloud project
Your Google Cloud Vision AI account needs billing enabled. In Google Cloud Platform, create or select a project, open APIs & Services > Library, search for Cloud Vision API and click Enable. If you see Manage instead, it is already on.
- 02
Create and copy an API key
Still in the Google console, go to APIs & Services > Credentials, click + Create Credentials > API key, then copy the value shown and keep it somewhere safe. Make will ask for it in the next step.
- 03
Link the account in Make
Add any Google Cloud Vision module to your scenario and click Create a connection. A connection is your account linked to Make once and reused by every module of the app. Give it a name if you like, paste the key into API Key, click Sign in with Google and confirm access.
Your first scenario: read the text in a new image
GoalWhen an image arrives in the app where your files land, Make reads its text with Google Cloud Vision and labels what it shows.
- 01
Create the scenario
From the Scenarios page, create a new scenario and click the + to add the first module. Since Google Cloud Vision has no trigger, pick the app where your images arrive and use its trigger to start the flow.
- 02
Add the OCR action
Click the + to the right of that first module, search for Google Cloud Vision and choose Run Text Detection (OCR) within an Image. Then click Create a connection, paste your API key and let Make link the account for every module that follows.
- 03
Map the image
Fill the module fields by mapping the image coming from the first module. A bundle is one item passing from module to module, here one picture. If the image is a document, tick the option for dense text.
- 04
Add label detection
Click the + again and add Run Label Detection within an Image on the same picture. You now get both the words and a list of what the photo shows, ready for any module you add next.
- 05
Test with Run once
Click Run once to execute the scenario one time, then open each module to read the bundles it received. Every module run counts as one operation, the unit Make tracks on your plan.
- 06
Schedule and switch it on
Set the schedule on the first module, every 15 minutes by default, then switch the scenario on. From then on, each new image gets read and labeled without you touching it.
What the Google Cloud Vision modules do
Google Cloud Vision gives you 9 modules in 2 groups. For each one: what it does for you, when to reach for it, and what to watch out for.
Images
8 modulesRun Localizer for Object Detection within an Image and Iterate the Result Array
Run Handwriting Detection within an Image
ActionIn Make“Runs detection to extract handwriting from an image.”
You get the handwritten words from a picture back as text you can store or forward, which saves retyping notes, filled paper forms or annotated sheets.
Run Label Detection within an Image
ActionIn Make“Detects and extracts information about entities within an image, across a broad group of categories.”
This action tells you what an image shows, across a wide range of categories, so your scenario can file or route a picture by its subject instead of its file name.
Run Text Detection (OCR) within an Image
ActionIn Make“Runs text detection / optical character recognition (OCR) to extract text from an image. If the image is a document, check the flag to optimize the detection for dense text and documents.”
Printed words inside a photo or a screenshot come back as plain text, ready to drop into a CRM, a sheet or an email. OCR stands for optical character recognition.
Run Landmark Detection within an Image and Iterate the Results
SearchIn Make“Detection identifies landmarks in an image. One landmark in the image produces one record in the result array.”
Famous places in a photo get named for you, which lets a travel or real estate team tag pictures by location without guessing.
Run Face Detection within an Image and Iterate the Result Array
SearchIn Make“Detects and extracts multiple faces within an image along with the associated key facial attributes such as emotional state or wearing headwear. One face in the image produces one record in the result array.”
Each face in a picture comes back with its main attributes, such as the emotion shown or whether the person wears headwear, so you can count people or flag photos to review.
Compute Image Dominant Colors and Iterate the Result Array
SearchIn Make“Computes and iterates an array of dominant colors wirthin an image.”
You learn which colors dominate an image, handy for tagging visuals by shade or checking that a picture matches a brand palette before publishing it.
Detect Potentially Unsafe or Undesirable Content within an Image
ActionIn Make“Detects potentially unsafe or undesirable content within an image.”
A picture gets a safety check before anyone sees it, so your scenario can hold back images that look inappropriate and let the rest through.
Run Text Detection (OCR) within a File and Iterate the Result Array
SearchIn Make“Runs text detection / optical character recognition (OCR) to extract text from a PDF/TIFF file. One page in the file produces one record in the result array.”
Whole PDF or TIFF files get read page by page, so a scanned contract or a stack of invoices becomes text your scenario can search and pass along.
Other modules
1 moduleRun Localizer for Object Detection within an Image and Iterate the Result Array
SearchIn Make“Object localization identifies multiple objects in an image and provides info for each object in the image. One object in the image produces one record in the result array.”
Several objects in one image are found and described one by one, so a photo of a shelf or a room turns into a list of the items it contains.
Need help automating Google Cloud Vision with Make?
A person reads every message.
