Open-Source AI Presentation Generator and API (Gamma, Beautiful AI, Decktopus Alternative)

Presenton is an open-source application for generating presentations with AI — all running locally on your device. Stay in control of your data and privacy while using models like OpenAI and Gemini, or use your own hosted models through Ollama.

✨ Now, generate presentations with your existing PPTX file! Just upload your presentation file to create template design and then use that template to generate on brand and on design presentation on any topic.

[!NOTE] Enterprise Inquiries: For enterprise use, custom deployments, or partnership opportunities, contact us at suraj@presenton.ai.

[!IMPORTANT] Like Presenton? A ⭐ star shows your support and encourages us to keep building!

[!TIP] For detailed setup guides, API documentation, and advanced configuration options, visit our Official Documentation

✨ More Freedom with AI Presentations

Presenton gives you complete control over your AI presentation workflow. Choose your models, customize your experience, and keep your data private.

• ✅ Custom Templates & Themes — Create unlimited presentation designs with HTML and Tailwind CSS
• ✅ AI Template Generation — Create presentation templates from existing Powerpoint documents.
• ✅ Flexible Generation — Build presentations from prompts or uploaded documents
• ✅ Export Ready — Save as PowerPoint (PPTX) and PDF with professional formatting
• ✅ Built-In MCP Server — Generate presentations over Model Context Protocol
• ✅ Bring Your Own Key — Use your own API keys for OpenAI, Google Gemini, Anthropic Claude, or any compatible provider. Only pay for what you use, no hidden fees or subscriptions.
• ✅ Ollama Integration — Run open-source models locally with full privacy
• ✅ OpenAI API Compatible — Connect to any OpenAI-compatible endpoint with your own models
• ✅ Multi-Provider Support — Mix and match text and image generation providers
• ✅ Versatile Image Generation — Choose from DALL-E 3, Gemini Flash, Pexels, or Pixabay
• ✅ Rich Media Support — Icons, charts, and custom graphics for professional presentations
• ✅ Runs Locally — All processing happens on your device, no cloud dependencies
• ✅ API Deployment — Host as your own API service for your team
• ✅ Fully Open-Source — Apache 2.0 licensed, inspect, modify, and contribute
• ✅ Docker Ready — One-command deployment with GPU support for local models

Presenton Cloud

We're launching Presenton Cloud which will make it very easy to create presentations through UI, API and MCP. Join our waitlist for early beta.

Deploy on Cloud (one click deployment)

Running Presenton Docker

1. Start Presenton

Linux/MacOS (Bash/Zsh Shell):

docker run -it --name presenton -p 5000:80 -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest

Windows (PowerShell):

docker run -it --name presenton -p 5000:80 -v "${PWD}\app_data:/app_data" ghcr.io/presenton/presenton:latest

2. Open Presenton

Open http://localhost:5000 on browser of your choice to use Presenton.

Note: You can replace 5000 with any other port number of your choice to run Presenton on a different port number.

Deployment Configurations

You may want to directly provide your API KEYS as environment variables and keep them hidden. You can set these environment variables to achieve it.

• CAN_CHANGE_KEYS=[true/false]: Set this to false if you want to keep API Keys hidden and make them unmodifiable.
• LLM=[openai/google/anthropic/ollama/custom]: Select LLM of your choice.
• OPENAI_API_KEY=[Your OpenAI API Key]: Provide this if LLM is set to openai
• OPENAI_MODEL=[OpenAI Model ID]: Provide this if LLM is set to openai (default: "gpt-4.1")
• GOOGLE_API_KEY=[Your Google API Key]: Provide this if LLM is set to google
• GOOGLE_MODEL=[Google Model ID]: Provide this if LLM is set to google (default: "models/gemini-2.0-flash")
• ANTHROPIC_API_KEY=[Your Anthropic API Key]: Provide this if LLM is set to anthropic
• ANTHROPIC_MODEL=[Anthropic Model ID]: Provide this if LLM is set to anthropic (default: "claude-3-5-sonnet-20241022")
• OLLAMA_URL=[Custom Ollama URL]: Provide this if you want to custom Ollama URL and LLM is set to ollama
• OLLAMA_MODEL=[Ollama Model ID]: Provide this if LLM is set to ollama
• CUSTOM_LLM_URL=[Custom OpenAI Compatible URL]: Provide this if LLM is set to custom
• CUSTOM_LLM_API_KEY=[Custom OpenAI Compatible API KEY]: Provide this if LLM is set to custom
• CUSTOM_MODEL=[Custom Model ID]: Provide this if LLM is set to custom
• TOOL_CALLS=[Enable/Disable Tool Calls on Custom LLM]: If true, LLM will use Tool Call instead of Json Schema for Structured Output.
• DISABLE_THINKING=[Enable/Disable Thinking on Custom LLM]: If true, Thinking will be disabled.
• WEB_GROUNDING=[Enable/Disable Web Search for OpenAI, Google And Anthropic]: If true, LLM will be able to search web for better results.

You can also set the following environment variables to customize the image generation provider and API keys:

• IMAGE_PROVIDER=[pexels/pixabay/gemini_flash/dall-e-3]: Select the image provider of your choice.
• Defaults to dall-e-3 for OpenAI models, gemini_flash for Google models if not set.
• PEXELS_API_KEY=[Your Pexels API Key]: Required if using pexels as the image provider.
• PIXABAY_API_KEY=[Your Pixabay API Key]: Required if using pixabay as the image provider.
• GOOGLE_API_KEY=[Your Google API Key]: Required if using gemini_flash as the image provider.
• OPENAI_API_KEY=[Your OpenAI API Key]: Required if using dall-e-3 as the image provider.

You can disable anonymous telemetry using the following environment variable: - DISABLE_ANONYMOUS_TELEMETRY=[true/false]: Set this to true to disable anonymous telemetry.

Note: You can freely choose both the LLM (text generation) and the image provider. Supported image providers: pexels, pixabay, gemini_flash (Google), and dall-e-3 (OpenAI).

Using OpenAI

docker run -it --name presenton -p 5000:80 -e LLM="openai" -e OPENAI_API_KEY="******" -e IMAGE_PROVIDER="dall-e-3" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest

Using Google

docker run -it --name presenton -p 5000:80 -e LLM="google" -e GOOGLE_API_KEY="******" -e IMAGE_PROVIDER="gemini_flash" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest

Using Ollama

docker run -it --name presenton -p 5000:80 -e LLM="ollama" -e OLLAMA_MODEL="llama3.2:3b" -e IMAGE_PROVIDER="pexels" -e PEXELS_API_KEY="*******" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest

Using Anthropic

docker run -it --name presenton -p 5000:80 -e LLM="anthropic" -e ANTHROPIC_API_KEY="******" -e IMAGE_PROVIDER="pexels" -e PEXELS_API_KEY="******" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest

Using OpenAI Compatible API

docker run -it -p 5000:80 -e CAN_CHANGE_KEYS="false"  -e LLM="custom" -e CUSTOM_LLM_URL="http://*****" -e CUSTOM_LLM_API_KEY="*****" -e CUSTOM_MODEL="llama3.2:3b" -e IMAGE_PROVIDER="pexels" -e  PEXELS_API_KEY="********" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest

Running Presenton with GPU Support

To use GPU acceleration with Ollama models, you need to install and configure the NVIDIA Container Toolkit. This allows Docker containers to access your NVIDIA GPU.

Once the NVIDIA Container Toolkit is installed and configured, you can run Presenton with GPU support by adding the --gpus=all flag:

docker run -it --name presenton --gpus=all -p 5000:80 -e LLM="ollama" -e OLLAMA_MODEL="llama3.2:3b" -e IMAGE_PROVIDER="pexels" -e PEXELS_API_KEY="*******" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest

Note: GPU acceleration significantly improves the performance of Ollama models, especially for larger models. Make sure you have sufficient GPU memory for your chosen model.

Generate Presentation over API

Generate Presentation

Endpoint: /api/v1/ppt/presentation/generate

Method: POST

Content-Type: multipart/form-data

Note: Make sure to set Content-Type as multipart/form-data and not application/json.

Request Body

Parameter	Type	Required	Description
prompt	string	Yes	The main topic or prompt for generating the presentation
n_slides	integer	No	Number of slides to generate (default: 8, min: 5, max: 15)
language	string	No	Language for the presentation (default: "English")
template	string	No	Presentation template (default: "general"). Available options: "classic", "general", "modern", "professional" + Custom templates
documents	File[]	No	Optional list of document files to include in the presentation. Supported file types: PDF, TXT, PPTX, DOCX
export_as	string	No	Export format ("pptx" or "pdf", default: "pptx")

Response

{
    "presentation_id": "string",
    "path": "string",
    "edit_path": "string"
}

Example Request

curl -X POST http://localhost:5000/api/v1/ppt/presentation/generate \
  -F "prompt=Introduction to Machine Learning" \
  -F "n_slides=5" \
  -F "language=English" \
  -F "template=general" \
  -F "export_as=pptx"

Example Response

{
  "presentation_id": "d3000f96-096c-4768-b67b-e99aed029b57",
  "path": "/static/user_data/d3000f96-096c-4768-b67b-e99aed029b57/Introduction_to_Machine_Learning.pptx",
  "edit_path": "/presentation?id=d3000f96-096c-4768-b67b-e99aed029b57"
}

Note: Make sure to prepend your server's root URL to the path and edit_path fields in the response to construct valid links.

For detailed info checkout API documentation.

API Tutorials

• Generate Presentations via API in 5 minutes
• Create Presentations from CSV using AI
• Create Data Reports Using AI

Roadmap

• [x] Support for custom HTML templates by developers
• [x] Support for accessing custom templates over API
• [x] Implement MCP server
• [ ] Ability for users to change system prompt
• [X] Support external SQL database

UI Features

1. Add prompt, select number of slides and language

2. Select theme

3. Review and edit outline

4. Select theme

5. Present on app

6. Change theme

7. Export presentation as PDF and PPTX

Community

Discord

License

Apache 2.0