Orves Ingest · for Orves Kore

How your PDFs and audio get into a Kore.

Orves Ingest is an async API that starts with PDF, born-digital and scanned, and with audio and podcasts. Output is deterministic, and every element carries an exact anchor back to where it came from.

Request early access View pricing

Orves IngestIllustrative · not a final schema

A PDF element and its exact anchor

{ "text": "Renewal date: September 1, 2026",
  "anchor": { "page": 4,
             "box": [72, 310, 410, 332] } }

An audio segment and its time anchor

{ "text": "…renewal may be postponed again",
  "anchor": { "start": "00:14:32",
             "end": "00:14:36" } }

What it produces

Structure you can point back to.

PDF, born-digital and scanned

Text, tables and reading order. Digital and scanned documents come back as structured, ordered content.

Audio and podcasts

Transcript segments with time anchors. Spoken content becomes text that points to the moment it was said.

Deterministic and anchored

The same input gives the same output, and every element anchors to its place in the source.

How it works

From input to a Kore.

PDF or audio in

Submit a file to the API.

Async job

Submit, poll, fetch. Async by design.

Anchored output

Every element points back to its source.

Into your Kore

Orves Kore keeps the source with every fact.

Benchmarks

Measured before claimed.

We publish a quantitative claim only when a benchmark receipt exists and is linked. None exists yet, so no number appears here. Benchmark coming.

Feed your Kore.

Request early access View pricing