Private document extraction for macOS

Every document, machine-readable. Nothing leaves your Mac.

Batch-convert PDFs, Word, Excel, PowerPoint, HTML, and email into clean Markdown, tables, JSON, or retrieval-ready JSONL. Entirely offline.

Download on theMac App Store

USD 29.99 · one-time purchase

No subscription. No account.

macOS 14 or laterApple silicon + IntelNo model weights

extraction-manifest.json

{
  "source": "research-deck.pptx",
  "sha256": "83f9…b612",
  "bytes": 2849134,
  "output": "research-deck.jsonl",
  "chunks": 42,
  "engine": "docdistill-1.0"
}

Processed locally · network unavailable

Built for dependable pipelines

The details that make extraction trustworthy.

Batch extraction, without the cleanup

Drop in documents or a whole folder. DocDistill writes collision-safe output names and one extraction-manifest.json per batch, so every export remains traceable and no file is silently overwritten.

Structure-aware chunking

Chunks break on the document’s own headings—never mid-sentence. Oversized paragraphs split at sentence boundaries, and DocDistill can repeat the full heading path inside every chunk for retrieval context.

Receipts for every extraction

Every result records the source file’s SHA-256 and byte count, plus engine revision, app version, and extraction time. You can prove exactly what was processed, and by which build.

Honest empty results

A scanned PDF with no text layer is reported as “No readable text.” It is never exported as a plausible-looking empty file. DocDistill tells you when it cannot extract what is not there.

Input → useful output

Bring the files you have. Get the structure you need.

READS

PDF · Word · Excel · PowerPoint · OpenDocument · HTML · XML · email · plain text

WRITES

Clean Markdown · tables · JSON · retrieval-ready JSONL

One Mac app. One fair price.

Own your document pipeline for USD 29.99.

No subscription, no account, no cloud dependency. Requires macOS 14 or later. Universal for Apple silicon and Intel.

Download on theMac App Store