---
title: "Run OCR"
slug: "run-ocr"
tags: ["run ocr"]
updated: 2026-10-28T12:04:54Z
published: 2026-10-28T12:04:54Z
canonical: "docs.revealdata.com/run-ocr"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://docs.revealdata.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Run OCR

**Optical Character Recognition (OCR)** allows users to generate searchable text from PDF or image sets. To run a bulk OCR job follow these steps:

1. Select your documents, click **OCR** on the Grid Toolbar. The OCR Documents modal will appear.
2. **Act On -** Choose ***Selected documents*** (if relevant) or ***All documents in results list****.*
3. **OCR Settings -**
  1. **Job Name** - The job name will enable monitoring of the status of the job under **Jobs Management > OCR**.
  2. Choose a **Source.**
    1. **PDF** - You can choose a PDF set right under this field.
    2. **Image Set** **-** You can choose to use images from any image set, including original images.

Selecting **Image** will display the **Generate Missing Images** and **Imaging Template** options below.
  3. **Generate Missing Images -** If there are no images generated in the original image set, these images can be generated as part of the OCR job.
  4. **Imaging Template -** Specifies how the images have been rendered to assist in character recognition.
  5. **Text Set -** The generated text can be stored into any existing text set as selected here, or optionally you may create a new Text Set by selecting **+Create new** without having to leave this screen. For example, instead of mixing this OCR set in with ***OCR / Loaded*** you may wish to create a Text Set called ***OCR Added*** or, where the OCR might be of redacted images, ***OCR / Redacted****.*
  6. **Overwrite Existing Text -** You may choose to overwrite text that already exists in the text set, or to OCR those documents without text in the destination text set.
4. Click **Submit** to run.

When an OCR job runs against a PDF set, PDFs without an existing text layer are automatically converted into searchable PDFs. PDFs that already contain text remain unchanged.

The resulting text is saved to the selected text set and automatically indexed when the job completes, making it available for searching without requiring manual reindexing. Native View PDFs are not converted, preserving existing redactions.

![](https://cdn.us.document360.io/3e21d801-ca9f-4c51-93db-9cbd32741f3d/Images/Documentation/ocr-documents.png)
5. Results will be displayed in the **OCR** table on the [***Jobs Management***](/reveal/docs/jobs-management) screen.
  1. Click **Jobs** on the Navigation menu at the left side of the project window.
  2. In Jobs Management navigate the list to open the **OCR**.

> [!NOTE]
> Note
> 
> Review OCR only supports English. You can OCR other languages in Processing. See [OCR – Supported Languages](/reveal/docs/ocr-supported-file-types). This limitation does not affect the translation of native files and native file extractions.

## Related

- [Duplicate Status Detection](/duplicate-status-detection.md)
- [About Ask](/about-ask.md)
- [Email Threading Overview](/email-threading-overview.md)
- [Translate (Translation)](/translate-translation.md)
- [Analyze and Search Emotional Intelligence](/analyze-and-search-emotional-intelligence.md)