Any Doc.
Premium Deck.
In Seconds.

Drop a PDF, Word doc, or plain text. raw2slides' AI reads it, picks a design system, rewrites your content into slides, and fetches matching visuals — all in one command.

terminal
$ python main.py --input policy.pdf --slides 12
[1/5] Ingesting policy.pdf... 4,213 chars
[2/5] Gemini Design Intelligence... Style: Executive Boardroom
[3/5] Curriculum Engine... 12 slides generated
[4/5] Fetching visuals... 8 images cached
[5/5] Compiling PPTX...
[DONE] output/final_deck.pptx (2.1 MB)
Scroll
0 % Quality Score
0s Avg. Gen Time
0+ Layout Types
0x Image Sources

Design Intelligence

Gemini analyzes your content and selects the optimal design system — color palette, typography, image style, and layout density. No templates. Fully AI-driven.

Pass 1: analyze_design()

Curriculum Engine

Compresses or expands your content into exactly the slide count you specify (1–20). Applies Executive, Briefing, or Training mode automatically based on scope.

Pass 2–3: generate_curriculum()

Auto Visual Engine

Gemini generates precise image keywords. The engine queries Unsplash → Pexels → Pixabay with automatic fallback. Images are center-cropped and embedded pixel-perfectly.

fetch_image() → cache

Built for
serious work.

Enterprise-grade output in a single CLI command. Works with PDFs, DOCX, PPTX, and plain text — no GUI, no drag-and-drop theatre.

Executive Summary 1–3 slides

High-level goals, key metrics, immediate actions only.

Standard Training 8–20 slides

Objectives, section dividers, knowledge checks, recaps.

Compressed Briefing 4–7 slides

Problem, framework, solution, timeline.

title
split
agenda
content
recap
divider
knowledge_check
.PDF .DOCX .PPTX .TXT

Full table extraction from DOCX. Shape text iteration from PPTX. Page-by-page parsing from PDF.

Three image sources. Zero manual searching.

Gemini generates a laser-specific keyword per slide. The fetcher queries all three sources with automatic fallback and landscape-preference filtering.

U
Unsplash
P
Pexels
X
Pixabay
01

Drop Your Doc

Pass any PDF, DOCX, PPTX, or TXT file as --input. The parser extracts all text and table content automatically.

02

AI Design Pass

Gemini reads your content and returns a complete design system: style, tone, color palette, image mood, and text density.

03

Curriculum + Visuals

Content is ranked, compressed, and mapped to your slide count. Images are auto-fetched per slide using Gemini-generated keywords.

04

PPTX Output

A pixel-perfect 16:9 deck drops to output/final_deck.pptx. Optionally export to PDF with a single flag.

Start generating
premium decks now.

One command. Any document. A commercial-grade training deck in under 30 seconds. No design skills required.

pip install
raw2slides

No spam. No credit card. Free beta access.