Read the text out of any image file or URL.
Image to Text extracts text from image files or remote image URLs using optical character recognition. Upload a JPG, PNG, or GIF up to 5 MB to receive the raw extracted text.
Try it — live request, no key required
No key required to try it. Get a key to use it in your app.
{
"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.",
"words": 28,
"characters": 170,
"lines": 5
}
}
Start from a template — a working app you can deploy in a minute
About the Image to Text API
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.
What people use it for
- Expense Receipt Scanning
- Accounting software converts uploaded photos of paper receipts into plain text to identify merchant names and purchase totals.
- ID Card Digitization
- When onboarding new bank customers, verify identity documents by pulling printed names and identification numbers straight from submitted photo files.
- Searchable Media Archives
- To index visual media, digital asset libraries scan promotional graphics by image URL to make embedded headlines and labels searchable.
- Assistive Screen Reading
- Transcribe text trapped inside web graphics and infographics before generating spoken audio descriptions for visually impaired readers.
Ways to call it
One endpoint, many ways in — REST with JSON, XML, YAML and CSV, plus GraphQL and an MCP interface for AI agents.
- JSON
- Default REST response
- XML
- Markup format
- YAML
- Human-readable
- CSV
- Tabular export
- GraphQL
- Query language
- MCP
- For AI agents
Which plan fits 10,000 image extractions a month?
Are word, character and line counts included on the Free plan?
What image formats and file sizes can I process?
Can I process an image via URL instead of uploading a file?
What happens if an image exceeds 5 MB or uses an unlisted format?
Request parameters — POST /v1/imagetotext
Sent as JSON in the request body. Premium parameters are accepted on every plan but only take effect on plans that include them. Anything not listed here is dropped rather than passed through.
Required
| Parameter | Type | Example | Description |
|---|---|---|---|
imageRequired | string | Upload an image file to extract text from (supported formats: JPG, PNG, GIF, max 5MB) |
curl -X POST "https://api.apiverve.com/v1/imagetotext" \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{}'Authentication
Send your key in the x-api-key header. That is the only auth step — no token exchange, and no per-endpoint scope to configure.
| Header | When | Value |
|---|---|---|
x-api-keyRequired | Every request | Your API key. Header names are case-insensitive, so X-API-Key is the same header. |
AuthorizationAlternate | Instead of the above | Bearer <key> — for clients that only expose bearer auth. Resolves to the same account and the same billing. |
content-typeRequired | POST body | application/json |
A 401 means the key is missing, invalid or expired. A 403 means the key is valid but not permitted here — blocked by a key restriction or an IP allow-list. Running out of credits is a 429.
Response — POST /v1/imagetotext
Every APIVerve endpoint returns the same three top-level keys, so one response handler covers your whole integration: status, error and data. Only data changes shape.
{
"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.",
"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.
| Field | Type | Example | Description |
|---|---|---|---|
text | string | "Ayear after that (in 2021) I hired somebody tpHfelp me write blog posts for
my personal website.
The point is, | like reinvesting the mone… | Extracted text content from the image using OCR |
wordsPremium | number | 28 | Total number of words extracted from image |
charactersPremium | number | 170 | Total character count in extracted text |
linesPremium | number | 5 | Number of lines detected in extracted text |
Response headers
Every response carries your balance, so your own code always knows where it stands without polling anything. All four are exposed to browsers through CORS.
| Header | What it carries |
|---|---|
x-api-remaining-credits | Credits left in the current cycle |
x-api-credits-used | Credits spent in the current cycle |
x-api-max-credits | The allowance for the cycle |
x-api-version | Version of the endpoint that answered |
Errors
Read the HTTP status first, then error for the specific reason. The body names the parameter that has to change.
| Status | Meaning | What to do |
|---|---|---|
400 | Input was rejected | Read error; it names the parameter that has to change. |
401 | Key missing or invalid | Check the header name and the key value. |
403 | Key valid, but not permitted here | A key restriction or an IP allow-list — never a bad key. |
429 | Rate limited, or out of credits | Read error to tell them apart, then back off or top up. |
What a call costs — 10 credits per call
Credits are shared across every APIVerve API — one balance, one key, one bill. Failed requests never count against it, so a rejected input costs nothing.
| Plan | Per month | Credits | Image to Text calls | Per 1,000 calls |
|---|---|---|---|---|
| Free | Free | 200 | 20 | Free |
| Starter | $29.99 | 200,000 | 20,000 | $1.50 |
| Pro | $99.99 | 1,000,000 | 100,000 | $1.00 |
| Mega | $299.99 | 4,000,000 | 400,000 | $0.75 |
Calls are what the credits buy at this API's rate — spend them here, on any of the other APIs, or across both. Nothing is reserved per endpoint.
Call it from cURL — POST /v1/imagetotext
No SDK to install — this is a plain HTTPS call to /v1/imagetotext with your key in the x-api-key header. Swap in a real key and it runs as-is.
curl "https://api.apiverve.com/v1/imagetotext" \
-H "x-api-key: YOUR_API_KEY"Resources
Also published for
Only the languages APIVerve ships a client for are listed — the rest call the endpoint directly over HTTPS.
Call it from Node.js — POST /v1/imagetotext
Install the Node.js SDK, then call the Image to Text API with your key. The client wraps the same HTTPS request, so anything it returns is what the endpoint returns.
npm install @apiverve/imagetotextconst res = await fetch("https://api.apiverve.com/v1/imagetotext", {
headers: { "x-api-key": "YOUR_API_KEY" },
});
const { data } = await res.json();
console.log(data);Resources
Also published for
Only the languages APIVerve ships a client for are listed — the rest call the endpoint directly over HTTPS.
Call it from Python — POST /v1/imagetotext
Install the Python SDK, then call the Image to Text API with your key. The client wraps the same HTTPS request, so anything it returns is what the endpoint returns.
pip install apiverve-imagetotextimport requests
res = requests.get(
"https://api.apiverve.com/v1/imagetotext",
headers={"x-api-key": "YOUR_API_KEY"},
)
print(res.json()["data"])Resources
Also published for
Only the languages APIVerve ships a client for are listed — the rest call the endpoint directly over HTTPS.
Call it from C# / .NET — POST /v1/imagetotext
Install the C# / .NET SDK, then call the Image to Text API with your key. The client wraps the same HTTPS request, so anything it returns is what the endpoint returns.
dotnet add package APIVerve.API.ImagetoTextusing var client = new HttpClient();
client.DefaultRequestHeaders.Add("x-api-key", "YOUR_API_KEY");
var json = await client.GetStringAsync("https://api.apiverve.com/v1/imagetotext");
Console.WriteLine(json);Resources
Also published for
Only the languages APIVerve ships a client for are listed — the rest call the endpoint directly over HTTPS.
Call it from Go — POST /v1/imagetotext
No SDK to install — this is a plain HTTPS call to /v1/imagetotext with your key in the x-api-key header. Swap in a real key and it runs as-is.
req, _ := http.NewRequest("GET", "https://api.apiverve.com/v1/imagetotext", nil)
req.Header.Set("x-api-key", "YOUR_API_KEY")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))Resources
Also published for
Only the languages APIVerve ships a client for are listed — the rest call the endpoint directly over HTTPS.
Call it from PHP — POST /v1/imagetotext
No SDK to install — this is a plain HTTPS call to /v1/imagetotext with your key in the x-api-key header. Swap in a real key and it runs as-is.
$ch = curl_init("https://api.apiverve.com/v1/imagetotext");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, ["x-api-key: YOUR_API_KEY"]);
$response = curl_exec($ch);
echo $response;Resources
Also published for
Only the languages APIVerve ships a client for are listed — the rest call the endpoint directly over HTTPS.
Call it from Ruby — POST /v1/imagetotext
No SDK to install — this is a plain HTTPS call to /v1/imagetotext with your key in the x-api-key header. Swap in a real key and it runs as-is.
require "net/http"
uri = URI("https://api.apiverve.com/v1/imagetotext")
req = Net::HTTP::Get.new(uri)
req["x-api-key"] = "YOUR_API_KEY"
res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |h| h.request(req) }
puts res.bodyResources
Also published for
Only the languages APIVerve ships a client for are listed — the rest call the endpoint directly over HTTPS.
Zero-code embed — one snippet, no backend
Drop an interactive Image to Text form onto any page. The widget calls the API for you, so no key ever appears in your markup and there is nothing to deploy.
Changelog — Image to Text API
Every change to this endpoint, newest first. Breaking changes ship as a new version and the previous one keeps serving — response fields are added, never removed or retyped in place, so an integration written against v1 keeps working.
Entries are picked up from dated catalog snapshots, so the first one appears after the next snapshot that moves something. A period where nothing changed produces no entry — silence is a valid changelog for the Image to Text API.
AI/Computer Vision
Related articles
All articles →
Take Your App Multilingual (No Rewrite)Add language support to an existing app without rearchitecting. Practical strategies for translation, detection, and localization.Read 
Summarize Text with AI: A Practical GuideUse AI to summarize articles, documents, and user content. Tutorial with code for content platforms, research tools, and dashboards.Read 
Why Your Sentiment Analysis Is WrongSentiment analysis is powerful but often misused. Here's how to use sentiment data effectively.Read