O

OCRBook

Read scanned books like real text.
Language

Turn scanned PDFs into clean, searchable books.

Import your scanned PDF, run OCR, then read it as real text β€” with page breaks and a layout that stays close to the original.

Offline-friendly Fast search Privacy-first

Key features

Everything you need to turn scanned books and documents into usable text.
PDF & image import

Open from Files, iCloud Drive, or other apps. Keep everything organized in a simple library.

Page-aware OCR

Designed for long, multi-page scans. Keeps text aligned with each page for easy navigation.

TXT mode

Read as clean text with page breaks preserved β€” closer to an ebook, without losing context.

Search & copy

Jump to keywords instantly. Copy and share passages, or export the full OCR text.

TTS ready

Listen to long documents with system text-to-speech when enabled.

Private by design

Your files stay on device unless you choose to share or export. No ads, no tracking.

Quick start

From first launch to your first readable book in minutes.
Step 1 Import a scanned PDF

Tap Import and select a PDF from Files, iCloud Drive, or Share Sheet.

Step 2 Run OCR (all pages or a range)

Choose full book OCR or only selected pages. Processing runs as efficiently as possible.

Step 3 Switch to TXT view

Tap TXT to read reconstructed text while keeping page breaks familiar.

Step 4 Search & reuse

Search for keywords, copy passages, and export text for notes or other tools.

Local AI with Ollama (optional)

Prefer local processing? Connect OCRBook to your own Ollama server.

Use Ollama to summarize, translate, or ask questions β€” while keeping content on your own machine. If you connect over plain HTTP, traffic may not be encrypted. Use a trusted network or HTTPS where possible.

Smart summarization workflow

Long documents are split, summarized, and merged automatically β€” with a clear plan before OCRBook starts.
Configurable context length

Match the plan to your Ollama server with a 4K–128K context length slider, so requests fit what your hardware can actually handle.

See the plan before you run it

OCRBook previews the exact strategy and number of server calls a summary will take β€” no surprises once it starts.

Built for full books, not just pages

When a document is too long for one response, OCRBook splits it into parts, summarizes each one, and merges the results automatically.

Choose how long the summary should be

Ask for a quick recap or a much longer, detailed summary β€” even for a very long book β€” and the workflow adjusts itself to match.

Full-document chat that doesn't silently truncate

Attach the whole document to chat. If it's too long for the context window, OCRBook scans it part by part for the answer instead of cutting it off.

Cancel anytime

Summarization and full-document chat run as a visible, step-by-step workflow that you can cancel at any point.

Fits in one request Single pass

The document fits your chosen context window, so one request produces the full summary.

Longer document Map-reduce

The document is split into parts, each part is summarized, then the partial summaries are merged into one.

Very long document Hierarchical merge

Partial summaries are merged over several rounds before the final summary is written.

Longer summary requested Sectional summary

For long, detailed summary requests, the result is written as multiple sections and stitched together on your device.

FAQ

Does OCRBook modify my original PDF?
No. Your original file stays untouched. OCR text is stored separately and you can switch between views anytime.
Does it work offline?
Yes. OCR and reading work offline. Optional integrations may require a network connection if you enable them.
Can I export the OCR text?
Yes. Copy passages, share selected text, or export the full OCR result as a plain text file.