---
title: "Deploy Presenton Presentations"
description: "Presenton AI presentation generator with login and PPTX/PDF export"
category: "AI/ML"
url: https://railway.com/deploy/presenton-presentations
---

# Deploy Presenton Presentations

Presenton AI presentation generator with login and PPTX/PDF export

**[Deploy Presenton Presentations on Railway](https://railway.com/template/presenton-presentations)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/presenton-presentations/manifest.json

- **Creator:** Anton Orel's Projects
- **Category:** AI/ML
- **Total deploys:** 3

## Template content

### Presenton

- **Image:** ghcr.io/presenton/presenton:v0.9.12-beta@sha256:dd444e4384df0caeb7cb96a26bfa7543a12d2be19c83d661446b2087d09aed54
- **Start command:** `/bin/sh -ec 'n=$(printf %s "${AUTH_PASSWORD:-}" | LC_ALL=C.UTF-8 wc -m) || n=0; if ! [ "$n" -ge 16 ] || ! [ "$n" -le 128 ]; then echo "Presenton refused to start: AUTH_PASSWORD must stay set to 16 to 128 characters" >&2; exit 64; fi; case "${AUTH_USERNAME:-}" in ""|*[!A-Za-z0-9._@-]*) u=0 ;; *) u=$(printf %s "$AUTH_USERNAME" | LC_ALL=C wc -c) || u=0 ;; esac; if ! [ "$u" -ge 3 ] || ! [ "$u" -le 128 ]; then echo "Presenton refused to start: AUTH_USERNAME must stay set to 3 to 128 of the characters A-Z a-z 0-9 . _ @ -" >&2; exit 64; fi; if [ -n "${DISABLE_AUTH:-}" ]; then echo "Presenton refused to start: DISABLE_AUTH must be unset, it turns off every login" >&2; exit 64; fi; if [ -z "${PRESENTON_PUBLIC_URL:-}" ] && [ -n "${RAILWAY_PUBLIC_DOMAIN:-}" ]; then export PRESENTON_PUBLIC_URL="https://${RAILWAY_PUBLIC_DOMAIN}"; fi; exec node /app/start.js'`
- **Health check:** /api/v1/auth/status
- **Public domain:** Yes

## Documentation

# Deploy and Host Presenton Presentations

Presenton is an open-source AI presentation generator. Give it a topic, notes or a document, and it writes the outline and the slides with the language model you connect, then exports the deck as PowerPoint (PPTX) or PDF. This template runs the official Presenton image, pinned by digest, with a generated admin login and a volume that keeps your decks, exports and settings.

## About Hosting Presenton Presentations

The template deploys one Presenton service with a 5,000 MB volume at `/app_data`. Sign in as `admin` with the generated `AUTH_PASSWORD` from the service's Variables tab. Presenton creates that account on the first boot, before it serves any request, and its first-run setup stays closed. Keep `AUTH_USERNAME` and `AUTH_PASSWORD` set: the service refuses to start without a password of 16 or more characters, and refuses `DISABLE_AUTH`. Presenton's login protects the UI, the API, your presentations, uploads and exports, and the MCP endpoint; by upstream design, uploaded fonts and template assets are served without a login.

Bring your own model key: after signing in, open Settings and connect OpenAI, Anthropic, Google, Azure OpenAI, Bedrock, OpenRouter, an Ollama server or any OpenAI-compatible endpoint. Calls are billed to your provider account. The database, uploads, images, exports and settings live on the volume, so they survive restarts and redeploys.

## Why Deploy Presenton Presentations on Railway

Railway gives Presenton HTTPS on a public domain, generates the admin password and keeps `/app_data` on a persistent volume. The image is pinned by digest, so every deploy runs the same build, and PPTX and PDF export work out of the box with the Chromium inside the image. The administrator can add users and API keys, and other tools can generate decks through the REST API or the `/mcp` endpoint with an API key. Give accounts only to people you trust: every user spends the shared model key, and any signed-in user can make the service fetch a URL of their choice.

## Common Use Cases

- Turn notes, a brief or an uploaded document into a first-draft slide deck.
- Generate recurring reports or sales decks from a script through the REST API.
- Let an AI agent create and export presentations through Presenton's MCP server.
- Give a small team one shared presentation generator with its own model key.

## Dependencies for Presenton Presentations Hosting

- An API key for a language model provider, or an OpenAI-compatible endpoint you run yourself.
- Optional: an image provider key (for example Pexels or Pixabay) for slide images.

### Deployment Dependencies

- [Presenton](https://presenton.ai)
- [Presenton source](https://github.com/presenton/presenton)
- [Presenton documentation](https://docs.presenton.ai)


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/presenton-presentations
