Skip to content
Escriba Suite Escriba Suite

Quick start

1. Run it

Section titled “1. Run it”

Pull the prebuilt image and start it with a single command:

Terminal window
docker run -d --name escriba --restart unless-stopped -p 8000:8000 \
  -e SECRET_KEY="$(openssl rand -hex 32)" \
  -e GOD_PASSWORD="change-me" \
  ghcr.io/diegoparras/escriba:latest

The image bundles everything (ffmpeg, Tesseract OCR, Whisper, embedded Redis). No additional services are needed.

2. Sign in

Section titled “2. Sign in”

Open http://localhost:8000 and sign in with the GOD_PASSWORD you set. There are three access levels — DIOS, ANGEL and HUMANO — each with its own password and limits. See Roles & access levels.

3. Convert your first document

Section titled “3. Convert your first document”
  1. Drag a file onto the drop zone (or click to pick one). You can also paste from the clipboard, or paste a URL / YouTube link.
  2. (Optional) open the advanced options to set the document language, force OCR, turn on anonymization, or pick which pages of a PDF to convert.
  3. Click Convert. The result appears with a live preview and the raw Markdown.

4. Get the result out

Section titled “4. Get the result out”

From the result card you can:

  • Copy the Markdown or download it as a file.
  • Export to Word, XML, EPUB, LaTeX and more formats.
  • Download a redacted PDF with sensitive data blacked out.
  • Open the LLM panel to see token counts and per-model cost estimates.

That’s the whole loop. Next, dig into converting and the anonymization engine.