Image to Text

Overview

Image to Text works by using Optical Character Recognition (OCR) to extract text from images. It supports various image formats and provides the extracted text in a structured format.

Endpoint

One host, one path per API. The block below shows this call in four languages; every one of them is the same HTTP request. Making requests covers the timeouts, retries and parameter rules that apply to all of them. The SDKs wrap the same call in a typed client.

curl -X POST https://api.apiverve.com/v1/imagetotext \
  -H "x-api-key: your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://findingtom.com/images/uploads/what-is-medium-com/article-image-15.png"
}'

const res = await fetch('https://api.apiverve.com/v1/imagetotext', {
  method: 'POST',
  headers: {
    'x-api-key': 'your_api_key_here',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "url": "https://findingtom.com/images/uploads/what-is-medium-com/article-image-15.png"
}),
});

if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);

const { data } = await res.json();
console.log(data);

import requests

res = requests.post(
    "https://api.apiverve.com/v1/imagetotext",
    headers={"x-api-key": "your_api_key_here"},
    json={
    "url": "https://findingtom.com/images/uploads/what-is-medium-com/article-image-15.png"
},
    timeout=15,
)
res.raise_for_status()

print(res.json()["data"])

package main

import (
	"fmt"
	"io"
	"net/http"
	"strings"
)

func main() {
	body := strings.NewReader(`{
  "url": "https://findingtom.com/images/uploads/what-is-medium-com/article-image-15.png"
}`)
	req, _ := http.NewRequest("POST", "https://api.apiverve.com/v1/imagetotext", body)
	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("x-api-key", "your_api_key_here")

	res, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer res.Body.Close()

	out, _ := io.ReadAll(res.Body)
	fmt.Println(string(out))
}

Replace your_api_key_here with the key from your dashboard. When the inputs arrive as a list rather than one at a time, batch requests run up to 200 of them through this same API in a single call.

Authentication

Send your key in the x-api-key header. That is the only auth step — there is no token exchange and no per-endpoint scope to configure. Authentication covers creating, rotating and revoking keys.

Parameters

Sent as JSON in the request body. Premium parameters are accepted on every plan but only take effect on plans that include them.

Response

Every API returns the same three top-level keys, so one response handler covers your whole integration: status, error and data. Only data changes shape. Response format covers the envelope, the other output formats and how premium fields are withheld.

{
  "status": "ok",
  "error": null,
  "data": {
    "text": "Ayear after that (in 2021) I hired somebody tpHfelp me write blog posts for\nmy personal website.\n\nThe point is, | like reinvesting the money | make\nback into my business.",
    "confidence": 88,
    "words": 28,
    "characters": 170,
    "lines": 5
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Errors

Read the HTTP status first, then error for the specific reason. The body names the parameter that has to change. Error handling covers the full status list and which of them are worth retrying.

Set up Image to Text

Ready to put it to work? Set up Image to Text on APIVerve.

Related

More in AI/Computer Vision: