Image to Text

​

Node Description

The Image to Text node extracts text from an image using an AI model. The AI Model is Open AI with GPT-4o or GPT-4o-mini.

​

Node Inputs

​

Required Fields

Image File(s):
The image(s) to extract text from.

or

Url(s):
The URL(s) of the image(s) to extract text from.

Instructions:
Detailed instructions specifying the text to extract from the image.

​

Node Output

Output:
The response generated by the AI model based on the instructions and the images.
The output can be a string or a structured object.
Example Output:

{
  "summary": "This is a test",
  "details": "This is a detailed description of the image."
}