Image to Text (OCR)

Read text from an image, including screenshots and document photos. Returns extracted text, a confidence estimate and detected language.

Pay by wallet (x402) AI-generated image-to-text

Example

Example answer

{
  "text": "",
  "text_type": null,
  "confidence": "high",
  "language_detected": null
}

Inputs

Field	Type	Required	What it is
`base64`	string	No	Base64-encoded image
`image_url`	string	No	URL to image

Output fields

How reliably each field appears in a successful answer.

Field	Type	Appears
`text`	string	Always (present in every successful answer)
`text_type`	string	Always (present in every successful answer)
`confidence`	string	Always (present in every successful answer)
`language_detected`	string	Always (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "image-to-text",
    "inputs": {
      "image_url": "https://upload.wikimedia.org/wikipedia/commons/a/a9/Example.jpg"
    },
    "max_price_cents": 5
  }'

{
  "tool": "strale_execute",
  "arguments": {
    "slug": "image-to-text",
    "inputs": {
      "image_url": "https://upload.wikimedia.org/wikipedia/commons/a/a9/Example.jpg"
    },
    "max_price_cents": 5
  }
}

import { Strale } from "straleio";

const strale = new Strale({ apiKey: process.env.STRALE_API_KEY! });
const result = await strale.do({
  capability_slug: "image-to-text",
  inputs: {
    "image_url": "https://upload.wikimedia.org/wikipedia/commons/a/a9/Example.jpg"
  },
  max_price_cents: 5,
});

import os
from straleio import Strale, DoRequest

strale = Strale(api_key=os.environ["STRALE_API_KEY"])
result = strale.do(DoRequest(
    capability_slug="image-to-text",
    inputs={
        "image_url": "https://upload.wikimedia.org/wikipedia/commons/a/a9/Example.jpg",
    },
    max_price_cents=5,
))

# No account. The first request answers 402 with the price in USDC;
# an x402 client pays it from your wallet and repeats the request.
curl -i 'https://api.strale.io/x402/v2/image-to-text?image_url=https%3A%2F%2Fupload.wikimedia.org%2Fwikipedia%2Fcommons%2Fa%2Fa9%2FExample.jpg'

Limitations

Handwriting and complex layouts reduce OCR accuracy
AI-powered OCR — handwritten text, low-resolution images, and complex layouts (multi-column, overlapping) have lower accuracy
What to do instead: Pre-process images to improve contrast and resolution before submission for better OCR results
Input images are limited to 4 MiB decoded
Images supplied by URL or base64 are refused above 4 MiB of decoded data, with a caller_input error naming the input field and no charge. Resize or compress the image before submitting.