Document Processing integrations on Metorial

Formdesk

Manage online forms, submissions, and visitors on Formdesk. Retrieve form lists, query and filter form results by date, status, or sync state, and export submissions to Excel, CSV, XML, or PDF. Add, update, and remove form result entries programmatically, including file uploads. Manage form visitors (list, add, update, remove, authenticate) and retrieve visitor-associated results. Pre-fill forms using data parking with ticketed URLs. Mark results as processed for incremental sync workflows. Supports single sign-on for users and visitors, and retrieves uploaded files and pre-defined filters.

Ghost

Manage a Ghost publishing platform including posts, pages, tags, members, newsletters, tiers, and site settings. Create, read, update, and delete posts and pages with support for draft, published, and scheduled states. Organize content with tags. Browse, add, and edit members and their subscriptions. Manage membership tiers and promotional offers. Configure and manage multiple newsletters. Upload images and themes. Read site settings and staff/user data. Access published content via a read-only Content API for headless CMS use cases. Register and manage webhooks for events such as post publishing, member changes, and tag updates.

Imejisio

Generate custom images from pre-designed templates using dynamic data via API. Create social media graphics, e-commerce banners, and marketing visuals by customizing text, colors, images, QR codes, and other components. List and search design templates with pagination. Use an AI design assistant to create or update designs from natural language prompts. Supports text patterns for rich inline formatting, auto-resize text, and public shareable design pages.

Imagekit

Upload, manage, transform, and deliver images and videos via a cloud-based media platform with integrated Digital Asset Management. Upload files from streams, URLs, or Base64 data with options for AI tagging, background removal, and pre/post transformations. Manage assets in folders and collections with search, copy, move, rename, delete, and version control. Retrieve file metadata including EXIF data and dimensions. Create and manage custom metadata fields. Purge CDN cache and check purge status. Receive webhook notifications for video transformation and upload transformation events. Supports AI-powered auto-tagging, background removal, visual search, and image generation from text prompts.

Imgix

Process, transform, and optimize images and videos in real time via URL-based parameters. Manage image sources backed by S3, GCS, Azure, and other storage providers. Upload, browse, search, and edit assets and their metadata. Apply transformations including resize, crop, format conversion, compression, watermarks, text overlays, background removal, and AI-powered background replacement. Generate video thumbnails, convert video to GIF, and optimize video playback. Purge cached assets from the CDN. Generate signed/secure URLs with expiration. Retrieve image and source analytics reports.

Kontentai

Manage structured content in a headless CMS. Create, update, publish, and deliver content items and their language variants across multiple environments. Manage content types, taxonomies, assets, workflows, collections, spaces, and languages. Retrieve published or preview content via REST and GraphQL APIs. Upload and organize binary files and assets with metadata. Define and manage workflow stages and transitions for content lifecycle. Synchronize content changes using queue-based Sync API with continuation tokens. Apply image transformations such as resizing, cropping, and format conversion. Manage users, roles, and project settings. Receive webhook notifications for changes to content items, assets, content types, languages, and taxonomies.

Langbase

Build and run AI agents using a unified LLM API across 600+ models. Create and manage pipes (AI agents) for text generation and chat. Store, upload, list, delete, and search documents using managed RAG memory with vector embeddings, chunking, and semantic similarity search. Manage conversation threads with full history and context. Parse and extract text from documents (PDFs, CSVs, etc.). Generate vector embeddings for text chunks. Generate AI images via multiple providers. Perform web search and web crawling through integrated tools. Supports tool calling, structured outputs, JSON mode, and vision-capable model inputs where supported by Langbase.

Llmwhisperer

Extract and convert complex documents — PDFs, scanned images, Office documents, and spreadsheets — into LLM-optimized text. Submit documents via file upload or URL with multiple extraction modes: native text, low-cost OCR, high-quality OCR, form extraction, and table extraction. Preserve document layout or extract plain text. Configure image preprocessing (median filter, Gaussian blur) to improve OCR quality. Select specific pages for extraction. Check extraction status for async processing and retrieve results when ready. Get line-level bounding box metadata for text highlighting and search. Register webhooks for extraction completion notifications. Track API usage metrics by processing mode and tag.

Matterport

Manage 3D digital twins of physical spaces on the Matterport platform. Search, create, update, and archive 3D models and their metadata including names, addresses, and visibility settings. Access and download model assets such as floor plans, point clouds, OBJ meshes, and panoramic imagery. Create, edit, and delete annotation tags (Mattertags) on 3D models. Purchase and manage add-on bundles like MatterPaks and floor plans. Manage folders, users, permissions, and custom roles at the account level. Import panoramic images for 3D reconstruction. Access AI-derived property intelligence including dimension estimates, room classification, and 2D floor plan geometry. Manage views and layers within models. Subscribe to webhook events for model lifecycle changes, state changes, transfers, and bundle updates.

Nanonets

Extract structured data from unstructured documents using AI-powered OCR and deep learning. Create and manage document processing workflows to extract fields and tables from invoices, receipts, forms, purchase orders, bank statements, and other document types. Upload documents as files or URLs for synchronous or asynchronous processing, receiving extracted data with confidence scores and bounding boxes. Train custom image classification and object detection models with labeled data. Manage human-in-the-loop review processes including approving, rejecting, and moderating extracted predictions. Apply post-processing transformations such as date formatting, currency detection, regex matching, lookup enrichment, and custom Python scripts. Import documents from email, Dropbox, Google Drive, OneDrive, and SharePoint. Export processed data to Google Sheets, QuickBooks, Xero, Salesforce, databases (PostgreSQL, MySQL, MSSQL), and other platforms. Receive webhook notifications on document processing, approval, rejection, and assignment events.

Ocr Web Service

Extract text from scanned documents and images using optical character recognition (OCR). Convert scanned PDFs and images into editable Word, Excel, PDF, RTF, and plain text formats. Supports 46 recognition languages, zonal OCR for extracting text from specific rectangular regions, multi-page document processing with page range selection, and word coordinate extraction. Accepts PDF, TIFF, JPEG, BMP, PNG, GIF, and ZIP inputs up to 100 MB. Retrieve account information including page balance and subscription details.

Oksign

Upload PDF or Word documents, define signature and form fields, and collect legally binding electronic signatures via eID, itsme, SMS, Smart-ID, or pen/scribble. Configure signer workflows with ordered email/SMS notifications and reminders. Bundle multiple documents into briefcases for single-link signing. Embed signing flows (SignExpress) or document editors (EditorExpress) into external applications. Manage contacts, retrieve signed document metadata and audit trails, and monitor account credits and storage. Supports simple, advanced, and qualified electronic signatures compliant with EU eIDAS regulation.

Parseur

Extract structured data from emails, PDFs, and other documents using AI-powered parsing. Upload and process documents (PDFs, images, emails), manage mailboxes (parsers) configured for specific document types, and retrieve parsed data in JSON, CSV, or XLS formats. Create and manage templates for data extraction, configure webhooks for event-driven notifications (e.g., document processed, process failed), and access mailbox schemas. Supports ready-made templates for invoices, resumes, leads, travel bookings, and more.

Passcreator

Create, manage, and distribute digital wallet passes (loyalty cards, coupons, event tickets, boarding passes, membership cards) for Apple Wallet and Google Wallet. Design and manage pass templates with custom fields, colors, images, and barcodes. Create personalized passes with custom data, barcode values, expiration dates, and stored values like loyalty points or gift card balances. Void passes to mark them as invalid. Send passes via email or SMS, and generate unique download page URLs. Bundle multiple passes for single downloads. Validate passes through scan configurations and the companion scanning app. Attach location-based notifications with geographic coordinates. Perform bulk updates using segments and a flexible query language. Search passes with partial and fuzzy matching. Retrieve detailed pass statistics including creation timelines and OS breakdowns. Receive real-time webhook notifications for pass lifecycle events, template changes, scans, and message delivery status.

Tinypng

Compress AVIF, WebP, JPEG, and PNG images using lossy compression while preserving visual quality. Resize images using scale, fit, cover, and thumb methods. Convert images between AVIF, WebP, JPEG, and PNG formats. Preserve image metadata such as copyright, creation date, and GPS location. Save optimized images directly to Amazon S3 or Google Cloud Storage buckets. Track monthly compression usage.

Vimeo

Upload, manage, and stream videos on Vimeo. Edit video metadata including titles, descriptions, tags, and privacy settings. Organize videos into showcases, folders, channels, and groups. Search for videos by keywords, category, or tags. Manage user profiles, followers, likes, and watch history. Create and control live streaming events with RTMP configuration. Retrieve embed codes and customize player settings. Manage thumbnails and text tracks (subtitles/captions). Subscribe to webhooks for real-time notifications on video uploads, plays, and status changes.

Tinyurl

Create, manage, and analyze shortened URLs. Shorten long URLs with custom aliases, branded domains, tags, and expiration dates. Retrieve, update, archive, and delete existing short links. View link analytics including click counts, geographic distribution, referrers, devices, and browsers. Perform bulk link operations and manage branded domains for custom short links.