# Nepali & Hindi OCR: read Devanagari text from images (`rounded_narcissus/nepali-document-reader`) Actor

Turn photos and scans of public documents (notices, bills, menus, signs, gazette pages) into text in Nepali, Hindi or English. Offline Tesseract OCR, no API key. Returns text, confidence and script share per image.

- **URL**: https://apify.com/rounded_narcissus/nepali-document-reader.md
- **Developed by:** [Pradip Malla](https://apify.com/rounded_narcissus) (community)
- **Categories:** AI, Automation, Other
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$10.00 / 1,000 page reads

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Nepali & Hindi OCR: read Devanagari text from images

Send image links and get the text back as JSON. It reads Nepali (Devanagari), Hindi and English, using the open-source
Tesseract engine inside the Actor. There is no API key to bring and no outside AI service is called.

**Good for:** notices, bills, menus, shop signs, posters, gazette and ward-office pages, printed forms and letters, anything
printed in Nepali or Hindi that a general OCR tool reads badly.

**Not for:** identity documents (citizenship, passport, licence, personal PAN). Do not send them. It is built for public documents.

### Input

| Field | What it is |
|---|---|
| `images` | Public `https` links to PNG, JPEG or WebP images, or `data:image/...;base64,...` strings. One output row per image. |
| `languages` | Any of `nep`, `hin`, `eng`. Default `["nep","eng"]`. |
| `maxImages` | Upper limit per run (default 20, max 100). |

Example input:

```json
{ "images": ["https://example.com/notice.jpg"], "languages": ["nep", "eng"] }
```

### Output (one row per image)

```json
{
  "image": "https://example.com/notice.jpg",
  "ok": true,
  "text": "नेपाल सरकार\nपर्यटन विभाग\n…",
  "confidence": 92,
  "devanagariShare": 0.685,
  "characters": 84,
  "lines": 4,
  "languages": ["nep", "eng"],
  "readAt": "2026-11-03T07:30:00.000Z"
}
```

A row that could not be read has `ok: false` and an `error` (not an image, private link, PDF, no text found).
A `SUMMARY` record gives the counts of images read, failed and skipped.

### Price

Pay per event, `page`: **$0.01 per image read**. Failed or empty images are not charged. Nothing else is billed on top.

### Honest limits

- Printed text only. Handwriting is read poorly or not at all.
- Accuracy depends on the picture: sharp, straight, well-lit scans at 150 dpi or more read best. Check `confidence`;
  below about 60 the text needs a human look.
- Mixed scripts work, but small English words inside Nepali lines can be misread. Tables and columns come out as lines in
  reading order, not as cells.
- PDFs are not supported: export each page as an image first.
- Links to private networks, `file:` links and links with a username or password are refused.
- Images up to 15 MB each.

# Actor input Schema

## `images` (type: `array`):

Public https links to PNG, JPEG or WebP images, or data:image/...;base64 strings. PDFs are not supported: export each page as an image first. One row of output per image.

## `languages` (type: `array`):

Tesseract models to use together: nep (Nepali), hin (Hindi), eng (English). Default reads Nepali and English.

## `maxImages` (type: `integer`):

Upper limit of images read in one run; extra ones are skipped and reported.

## Actor input object example

```json
{
  "images": [
    "https://upload.wikimedia.org/wikipedia/commons/9/94/Creative_Development_and_Production_-_New_Audiences_-_Nepali_-_Motivation_-_Banners_-_DPLA_-_aa54e38b02c5f5d63a802b2ac326622d_%28page_1%29.jpg"
  ],
  "languages": [
    "nep",
    "eng"
  ],
  "maxImages": 20
}
```

# Actor output Schema

## `results` (type: `string`):

One row per image: the text read, confidence 0-100, the share of Devanagari letters, and an error when the image could not be read.

## `summary` (type: `string`):

Counts of images read and failed, saved as the SUMMARY record.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "images": [
        "https://upload.wikimedia.org/wikipedia/commons/9/94/Creative_Development_and_Production_-_New_Audiences_-_Nepali_-_Motivation_-_Banners_-_DPLA_-_aa54e38b02c5f5d63a802b2ac326622d_%28page_1%29.jpg"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("rounded_narcissus/nepali-document-reader").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "images": ["https://upload.wikimedia.org/wikipedia/commons/9/94/Creative_Development_and_Production_-_New_Audiences_-_Nepali_-_Motivation_-_Banners_-_DPLA_-_aa54e38b02c5f5d63a802b2ac326622d_%28page_1%29.jpg"] }

# Run the Actor and wait for it to finish
run = client.actor("rounded_narcissus/nepali-document-reader").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "images": [
    "https://upload.wikimedia.org/wikipedia/commons/9/94/Creative_Development_and_Production_-_New_Audiences_-_Nepali_-_Motivation_-_Banners_-_DPLA_-_aa54e38b02c5f5d63a802b2ac326622d_%28page_1%29.jpg"
  ]
}' |
apify call rounded_narcissus/nepali-document-reader --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,rounded_narcissus/nepali-document-reader"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/GhcciOoEluedL4Wz5/builds/vFmaScuCXNLekDgK9/openapi.json