--- title: "Deploy Presenton" description: "Open-source AI presentation generator with login and PPTX/PDF export" category: "AI/ML" url: https://railway.com/deploy/presenton-1 --- # Deploy Presenton Open-source AI presentation generator with login and PPTX/PDF export **[Deploy Presenton on Railway](https://railway.com/template/presenton-1)** Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/presenton-1/manifest.json - **Creator:** Agaz Self-Host - **Category:** AI/ML ## Template content ### Presenton https://presenton.ai/icon1.svg?icon1.0jrs3fpnt_7y8.svg - **Image:** ghcr.io/presenton/presenton:v0.9.12-beta@sha256:dd444e4384df0caeb7cb96a26bfa7543a12d2be19c83d661446b2087d09aed54 - **Start command:** `/bin/sh -c 'P="${PORT:-80}"; if [ "$P" != 80 ]; then sed -i "s/listen 80;/listen 80; listen $P;/" /etc/nginx/nginx.conf; fi; export AUTH_USERNAME="${AUTH_USERNAME:-admin}" DISABLE_ANONYMOUS_TRACKING="${DISABLE_ANONYMOUS_TRACKING:-true}"; exec node /app/start.js'` - **Health check:** /api/v1/auth/status - **Public domain:** Yes ## Documentation # Deploy and Host Presenton on Railway Presenton is an open-source AI presentation generator. You give it a prompt or a document, and it writes an outline, builds the slides from a design template and lets you edit them in the browser. You can export the result as PowerPoint (PPTX) or PDF. It works with OpenAI, Anthropic, Google, OpenRouter, Ollama and other model providers. ## About Hosting Presenton Presenton runs as one container: a Next.js web app and a FastAPI backend behind nginx, with Chromium for exports. This template runs the official image, pinned by digest, as a single service. Presentations, uploads, exports and settings are stored in SQLite and files on a volume at `/app_data`, so they survive redeploys. The server has its own login. The template creates the admin account at first start, using the username `admin` and a generated password, so nobody can claim an empty instance before you do. You bring your own AI provider key and enter it in Presenton's settings after you log in. The template stores no key of its own. ## Common Use Cases * Turn a prompt, a PDF or a Word document into an editable slide deck * Generate on-brand presentations from your own PPTX templates * Create decks from other tools through Presenton's REST API and MCP server ## Dependencies for Presenton Hosting * An API key for an AI model provider (OpenAI, Anthropic, Google, OpenRouter and others), or a reachable Ollama or OpenAI-compatible server * Optional: a Pexels or Pixabay key, or an image-generation provider, for slide images ### Deployment Dependencies * Presenton source and self-hosting docs: https://github.com/presenton/presenton * Release used by this template: https://github.com/presenton/presenton/releases/tag/v0.9.12-beta * Presenton documentation: https://docs.presenton.ai ### Implementation Details * **Image:** `ghcr.io/presenton/presenton:v0.9.12-beta`, pinned by digest. * **Login:** the username is `admin`. The password is the `AUTH_PASSWORD` variable on the Presenton service (Variables tab). The password only sets up the account on first start. To change it later, set a new `AUTH_PASSWORD`, add `AUTH_OVERRIDE_FROM_ENV=true`, redeploy once, then remove `AUTH_OVERRIDE_FROM_ENV`. To use a different admin name on a new deploy, add an `AUTH_USERNAME` variable before the first start. * **AI provider:** after you log in, open Settings, pick a provider, and paste your key and model. Presenton saves them on the volume, and only the admin can see them. * **Storage:** everything lives on the volume mounted at `/app_data`. * **Health check:** `/api/v1/auth/status`, which answers without a login and doesn't show any data. * **Telemetry:** anonymous usage tracking is off by default. Set `DISABLE_ANONYMOUS_TRACKING=false` to turn it on. ## Why Deploy Presenton on Railway? Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it. By deploying Presenton on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway. ## 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-1