Upload an existing file or attachment not bigger than 500 MB.

Creates a brand new text file from plain text content you specify.

Allow or deny the download permission for an existing shared link.

Set or remove the password of an existing shared link.

This is an advanced action which makes a raw HTTP request that includes this integration's authentication.

Finds a folder by name. Make sure the number of files/folders in the watched folder does not exceed 6000.

Searches for files in a folder that match a search term in the contents or name. Requires a Dropbox Business account.

Lists all files and folders within a specific Dropbox folder. Make sure the number of files/folders in the watched folder does not exceed 6000.

Add a fillable form field (text field or checkbox) to a PDF at a specified position.

Add Text to PDF

Generate a

Seamlessly convert a variety of formats such as URLs, HTML code, documents, spreadsheets, presentations, images, and more into PDF.

Allows the execution of a custom API call to the PDF.co API. This is intended for advanced users.

Extract data from invoices, reports, statements, and other documents using AI-based templates. This tool is beneficial for automating data extraction tasks and reducing manual workload.

Extract information from a PDF document such as page count, page size, author, description, keywords and also any form field information.

Converts a scanned PDF or image file into a text-searchable PDF.

Tools to rotate and delete pages from your PDF files effectively.

Add text, images, signatures to a PDF, fill PDF form fields, or create a new PDF from templates.

Add/Remove Password and Security Features to/from PDF file

Locate and replace specified text within a PDF document

Allows you to search for specific text within PDF documents or scanned images.

This operation segments a PDF document based on barcode search, creating new PDF files for each segment.

(Recommended) Upload an image(s) and send a message or question about it. Powered by Responses API.

(Recommended) Summarize, classify, and analyze text. Powered by Responses API.

Sends a Chat to OpenAI and generates a Completion, optionally storing messages as we do. Powered by Chat Completions API.

Classify your text into one of your provided categories. Powered by Chat Completions API.

Generate vector embeddings for text input.

Creates a new transcription, using Whisper, from an audio or video file.

Sends unstructured text and returns structured data using OpenAI's "Function Calling" capability. Powered by Chat Completions API.

Generates an image using a relevant OpenAI model.

Enter a block of text and generate a summary. Powered by Chat Completions API.

Creates a new translation.

This is an advanced action which makes a raw HTTP request that includes this integration's authentication.

Finds a file by filename.

Retrieve the status and details of a video generation job created with Sora. Use this to check if a video is ready for download.

Find or Create file

Moves a file to a new location at the path you specify.

Adds a new line to an existing text file, or creates a file if it doesn't exist.

Set or remove the expiration date of an existing shared link.

Set the visibility and access level for an existing shared link.

Search for files and folders using advanced filters like file type, category, and content matching.

Search for a specific file by name. Make sure the number of files/folders in the watched folder does not exceed 6000.

Find existing shared links for files or folders in your Dropbox.

Generate Barcode and add to existing PDF

Add an image, logo, or signature to a PDF at a specified position.

Transform your invoice processing with our advanced AI. Enjoy quick, accurate data extraction that eliminates manual effort and saves you valuable time.

Decode barcodes from images or PDF documents swiftly and accurately.

Convert PDF to JPG, PNG, CSV, XML, JSON and other formats

Analyze the text of an input document using AI and return its class (such as: invoice, order, industry). This can utilize custom rules and is helpful for quickly identifying the origin of a document.

Send Email With Attachment

Convert HTML or URL to PDF with advanced options (e.g. layout, orientation). Supports HTML templates (Handlebar and Mustache).

Combine multiple document formats into a single PDF. Supported formats include PDF, DOC, DOCX, XLS, JPG, PNG, and more.

Significantly reduce PDF file size by compressing and optimizing images and objects within the document.

This operation employs AI to scan a PDF document for tables, returning an array of found tables with coordinates and information about the detected columns.

Identify and remove specified text from a PDF document using text search or fixed-position coordinates

Search text inside PDF and replace with Image

This operation allows you to split a PDF document into multiple new PDF files, using specific page numbers or page ranges.

This operation segments a PDF document based on text search (with OCR), creating new PDF files for each segment.

Upload an image and send a message or question about it. Powered by Chat Completions API.

Generate an analysis of the overall sentiment of a block of text. Powered by Chat Completions API.

Classifies if text is potentially harmful.

(Recommended) Send a chat to OpenAI, optionally storing messages for continuous conversation. This enhanced action can also help with web search, file search, and advanced tooling such as MCP. Powered by Responses API.

Creates a new image by editing an existing image with a prompt.

Create a new video generation job using Sora. Returns a video job ID that can be used to check the render status.

(Recommended) Improved structured data extraction with better formatting options and more reliable schema adherence. Powered by Responses API.

Sends a prompt to OpenAI and generates a completion.

Converts a given text to speech.

Writes the content of an email based on your provided prompt for use in a subsequent step.

Find a conversation for native OpenAI conversation management.

Find a stored Responses API result by response ID for audit trails and debugging.

This best matches a query string (like "big animal") to a list of document strings (like "mouse", "cat", "buffalo", and "blue whale").