ppt-master: AI generates native PowerPoint from any document.
What problem it solves
AI-generated presentation workflows can produce decks that are difficult to refine because elements are flattened or confined to a fixed template. PPT Master addresses this by generating native PowerPoint objects that remain editable, while supporting multiple source formats, existing templates, transitions, animations, and narration.
Key features
Native, editable PowerPoint output — Generated decks use native shapes, connectors, text, pictures, fills, effects, charts, and tables rather than flat text boxes or a filled-in template. Template and structured workflows can also produce decks with real slide masters and layouts.
Source: README
Multiple content routes — The workflow can generate a new deck from source documents, pasted content, or a topic. It can also extract reusable templates, fill an existing `.pptx` while preserving its design, or enhance a finished deck.
Source: README, projects
Transitions, animation, and narration — Finished decks can receive native transitions and animations, while speaker notes can be used to create audio narration. The image-to-PPTX workflow also supports OCR-derived native text and layer-aware image assembly.
Source: README
Local, model-flexible workflow — The workflow runs as a skill inside agent-capable AI tools and exports locally, allowing users to choose different model providers. Apart from enabled AI and media services, the pipeline runs on the user's machine.
Source: README
Source conversion and image workflows — The project supports documents such as PDFs and DOCX, as well as pasted text and source images. Image conversion includes OCR text evidence, text-removed bases, checked image layers, and animated GIF generation.
Source: README
Quick start
Copied verbatim from the project's README.
git clone https://github.com/hugohe3/ppt-master.git
cd ppt-masterpip install -r requirements.txtYou: Please create a PPT from projects/q3-report/sources/report.pdfWho it may suit
This may suit people who regularly prepare or revise PowerPoint presentations and want AI-generated slides to remain editable. It may also suit Python and AI-agent users who want to build presentation workflows from documents, templates, pasted content, or images.
Topics to discuss
Which native PowerPoint object types should the workflow support next?
How should preservation contracts differ between new decks, existing templates, and image conversions?
Which agent tools and model workflows provide the clearest setup experience for new users?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/hugohe3/ppt-master#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…