Skip to main content

​
What does this node do?

The Image to Text node uses AI vision models to analyze images and extract text, descriptions, or structured data. It can read text from images (OCR), describe image contents, or answer questions about images. Common uses:
  • Extract text from screenshots or documents
  • Generate image descriptions for accessibility
  • Analyze product images
  • Extract data from charts or infographics

​
Quick setup

1

Add the Image to Text node

Find it in AI Nodes → Image to Text
2

Provide the image

URLs or File Inputs
3

Write your prompt

Tell the AI what to extract or describe

​
Configuration

​
Required fields

​
image
string
required
The image to analyze.Formats:
  • URL: https://example.com/image.jpg
​
prompt
string
required
Instructions for what to extract or describe.Examples:
  • “Extract all text from this image”
  • “Describe this product image in detail”
  • “What brand logos are visible?”
  • “Read the chart and provide the data”

​
Output

{
  "response": "The image shows a receipt from Acme Store dated January 15, 2024. Items: Coffee $4.50, Sandwich $8.99. Total: $13.49.",
  "confidence": 0.95
}

​
Examples

​
OCR - Extract text

Prompt: “Extract all text from this image exactly as it appears”

​
Product description

Prompt: “Describe this product for an e-commerce listing. Include color, material, and key features.”

​
Chart data extraction

Prompt: “Read the data from this bar chart and return as JSON with labels and values.”

Text to Image

Generate images from text

LLM

Process extracted text