slideforge-dev PDF API
The pdf API from slideforge-dev — 4 operation(s) for pdf.
Operations 4
POST
/v1/deck/from-pdf/analyze
Inspect a PDF and propose an extraction strategy (no job, no charge)
#
The pdf API from slideforge-dev — 4 operation(s) for pdf.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/slideforge-dev:slideforge-dev-pdf-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: SlideForge PDF API
description: 'Agent-first PowerPoint generation. Send structured slide intents (a `form` plus typed fields) or a brief; get back a real, editable `.pptx`. The draw path is deterministic — no model renders your slide, so supplied numbers and text come out verbatim. Every response carries `status`, `fidelity` and `warnings` so an automated caller can tell whether the output is usable. $0.05 per slide; an unusable slide is not billed. Authenticate with a SlideForge API key (`Authorization: Bearer sf_live_…` or `X-API-Key`) — new accounts include 60 free slides, no credit card: https://slideforge.dev/sign-up'
version: 5.356.0
servers:
- url: https://api.slideforge.dev
security:
- bearerAuth: []
- apiKeyAuth: []
tags:
- name: PDF
paths:
/v1/render/from-pdf/analyze:
post:
tags:
- PDF
summary: 'Ingest: inspect a PDF, no job, no charge'
description: 'Free preview endpoint — no charge, no persistence.
Logs each call''s producer + page count + source classification to
slideforge.telemetry so we can see what real users upload and prioritize
which producers to support next. Fire-and-forget — never fails the
request.'
operationId: analyze_pdf_endpoint_v1_render_from_pdf_analyze_post
requestBody:
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/Body_analyze_pdf_endpoint_v1_render_from_pdf_analyze_post'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/PdfAnalysis'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/v1/deck/from-pdf/analyze:
post:
tags:
- PDF
summary: Inspect a PDF and propose an extraction strategy (no job, no charge)
description: Upload a PDF and receive metadata, per-page stats, source classification, and an estimated cost. Use this to show users what they're about to spend before calling `/v1/deck/from-pdf`. No job is created and the file is not persisted — re-upload the same file to `/v1/deck/from-pdf` when ready.
operationId: analyze_pdf_endpoint_v1_deck_from_pdf_analyze_post
requestBody:
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/Body_analyze_pdf_endpoint_v1_deck_from_pdf_analyze_post'
required: true
responses:
'200':
description: Analysis returned
content:
application/json:
schema:
$ref: '#/components/schemas/PdfAnalysis'
'400':
description: Invalid PDF (size, format, corrupted)
'413':
description: File too large
'429':
description: Rate limit exceeded
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/v1/render/from-pdf:
post:
tags:
- PDF
summary: 'Ingest: PDF (PowerPoint export) → editable PPTX deck'
description: POST /v1/deck/from-pdf — convert a PowerPoint-exported PDF into an editable PPTX.
operationId: deck_from_pdf_v1_render_from_pdf_post
requestBody:
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/Body_deck_from_pdf_v1_render_from_pdf_post'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'202':
description: Extraction queued
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/v1/deck/from-pdf:
post:
tags:
- PDF
summary: Convert a PDF (PowerPoint export) into an editable PPTX deck
description: 'Upload a PDF and receive an editable .pptx with the original text, layout, shapes, and images preserved.
Currently supports PDFs exported from slide tools (PowerPoint, Keynote, Google Slides, Canva, LaTeX Beamer, etc.). Text documents are not converted: to turn a document into slides, let the calling assistant read it and send the slides as intents.
**Max file size:** 50 MB.'
operationId: deck_from_pdf_v1_deck_from_pdf_post
requestBody:
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/Body_deck_from_pdf_v1_deck_from_pdf_post'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'202':
description: Extraction queued
'400':
description: Invalid PDF (size, format, corrupted)
'402':
description: Insufficient balance
'413':
description: File too large
'422':
description: Unsupported PDF source (not a PowerPoint export)
'429':
description: Rate limit exceeded
components:
schemas:
Body_analyze_pdf_endpoint_v1_deck_from_pdf_analyze_post:
properties:
file:
type: string
format: binary
title: File
description: The .pdf file to analyze
type: object
required:
- file
title: Body_analyze_pdf_endpoint_v1_deck_from_pdf_analyze_post
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
type: object
required:
- loc
- msg
- type
title: ValidationError
PdfFeatures:
properties:
aspect_ratio_first:
type: number
title: Aspect Ratio First
description: width / height of the first page
is_slide_aspect:
type: boolean
title: Is Slide Aspect
description: True if the first page sits in a slide-shaped aspect band (roughly 1.25–2.45 — covers 4:3, 16:10, 16:9, ultrawide)
is_doc_portrait:
type: boolean
title: Is Doc Portrait
description: True if the first page is portrait-oriented (aspect < 1.0)
consistent_dimensions:
type: boolean
title: Consistent Dimensions
description: True if every page in the document shares the same width/height
total_text_chars:
type: integer
title: Total Text Chars
description: Sum of extractable characters across all pages
total_text_spans:
type: integer
title: Total Text Spans
description: Sum of text spans (formatted runs) across all pages. Zero with non-zero total_text_chars suggests glyph-outlined text — readable but unformatted.
total_images:
type: integer
title: Total Images
description: Sum of embedded images across all pages
total_drawings:
type: integer
title: Total Drawings
description: Sum of vector drawing primitives (rects, paths, lines) across all pages — high counts indicate hand-built slide content rather than scanned/raster
unique_fonts:
type: integer
title: Unique Fonts
description: Number of distinct fonts seen across the doc
pages_with_text:
type: integer
title: Pages With Text
description: Pages with at least 50 chars of extractable text
pages_image_only:
type: integer
title: Pages Image Only
description: Pages with images present but fewer than 50 chars of extractable text
pages_blank:
type: integer
title: Pages Blank
description: Pages with no text and no images
type: object
required:
- aspect_ratio_first
- is_slide_aspect
- is_doc_portrait
- consistent_dimensions
- total_text_chars
- total_text_spans
- total_images
- total_drawings
- unique_fonts
- pages_with_text
- pages_image_only
- pages_blank
title: PdfFeatures
description: 'Document-level structural features used by the bucket classifier.
Everything here comes from `fitz` primitives — no LLM calls. The fields
are deliberately concrete (counts, ratios, booleans) so threshold tuning
against a real corpus is reproducible.'
Body_deck_from_pdf_v1_deck_from_pdf_post:
properties:
file:
type: string
format: binary
title: File
description: The .pdf file to convert
name:
anyOf:
- type: string
- type: 'null'
title: Name
description: Human-readable job name
source:
anyOf:
- type: string
- type: 'null'
title: Source
description: Entry tag persisted on jobs.source (attribution)
type: object
required:
- file
title: Body_deck_from_pdf_v1_deck_from_pdf_post
Body_deck_from_pdf_v1_render_from_pdf_post:
properties:
file:
type: string
format: binary
title: File
description: The .pdf file to convert
name:
anyOf:
- type: string
- type: 'null'
title: Name
description: Human-readable job name
source:
anyOf:
- type: string
- type: 'null'
title: Source
description: Entry tag persisted on jobs.source (attribution)
type: object
required:
- file
title: Body_deck_from_pdf_v1_render_from_pdf_post
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
Body_analyze_pdf_endpoint_v1_render_from_pdf_analyze_post:
properties:
file:
type: string
format: binary
title: File
description: The .pdf file to analyze
type: object
required:
- file
title: Body_analyze_pdf_endpoint_v1_render_from_pdf_analyze_post
PdfPageInfo:
properties:
page_number:
type: integer
title: Page Number
description: 1-based page number
has_text:
type: boolean
title: Has Text
description: True if the page contains extractable text
has_images:
type: boolean
title: Has Images
description: True if the page contains embedded images
text_char_count:
type: integer
title: Text Char Count
description: Total characters of extractable text
text_preview:
type: string
title: Text Preview
description: First ~80 characters of text content (for the analysis card)
default: ''
type: object
required:
- page_number
- has_text
- has_images
- text_char_count
title: PdfPageInfo
description: Per-page summary returned by the analyzer (lean — used by the UI list).
PdfAnalysis:
properties:
producer:
type: string
title: Producer
description: PDF metadata producer string (telemetry only — never used for routing). Captured so we can correlate buckets with real-world tools after the fact.
default: ''
page_count:
type: integer
title: Page Count
description: Number of pages in the PDF
file_size_bytes:
type: integer
title: File Size Bytes
description: Source PDF size in bytes
bucket:
type: string
enum:
- slide-vector
- slide-raster
- doc-text
- doc-image-heavy
- scanned
- mixed
- unknown
title: Bucket
description: Routing decision derived from structural features. The /v1/deck/from-pdf endpoint accepts a file iff its bucket is currently implemented.
features:
$ref: '#/components/schemas/PdfFeatures'
description: Document-level structural features used by the classifier
estimated_cost_usd:
type: number
title: Estimated Cost Usd
description: Per-page price for the bucket × page_count
can_extract:
type: boolean
title: Can Extract
description: True iff /v1/deck/from-pdf will currently accept this file.
unsupported_reason:
anyOf:
- type: string
- type: 'null'
title: Unsupported Reason
description: Human-readable hint shown to the user when can_extract is False, explaining what's not yet supported.
pages:
items:
$ref: '#/components/schemas/PdfPageInfo'
type: array
title: Pages
description: Per-page summary, in document order
type: object
required:
- page_count
- file_size_bytes
- bucket
- features
- estimated_cost_usd
- can_extract
title: PdfAnalysis
description: Output of analyze_pdf() — what /analyze returns and what /generate uses to route.
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: 'SlideForge API key: `Authorization: Bearer sf_live_…`. Create one at https://slideforge.dev/console/keys'
apiKeyAuth:
type: apiKey
in: header
name: X-API-Key
description: Same key, header form — for clients that cannot set Authorization.