Skip to main content

Make Waves ’26 Step into AI’s glass box. Prague, 19–20 Oct.

Register now (opens in a new tab)
OpenAI (ChatGPT, Whisper)
0CodeKit

Connect OpenAI (ChatGPT, Sora, DALL-E, Whisper) and 0CodeKit integrations

Explore ready-made OpenAI (ChatGPT, Whisper) and 0CodeKit templates and start automating in minutes.

Get started free

Create a custom workflow

Transform OpenAI outputs from ChatGPT, DALL-E, Sora, and Whisper into instant automated workflows with 0CodeKit—no manual work required. Every AI-generated response, image, video, or transcription automatically triggers custom actions in your no-code development pipeline, creating direct integration between AI creation and execution. Harness the power of intelligent automation where OpenAI's creative output flows directly into your 0CodeKit projects in real-time.

Create a custom workflow

Every automation starts with a trigger and an action. Select one from each app to generate a workflow tailored to your needs.

OpenAI (ChatGPT, Whisper)
Trigger: Watch batch completed
0CodeKit
Action: Select an action
1. Select a trigger

  • Triggers when a batch is completed.

2. Select an action

  • This module inserts new blank pages into a PDF at specified positions.

  • This module retrieves detailed metadata from a PDF, such as the dimensions of each page, enhancing document analysis and management.

  • Blur a image with optional blur strength.

  • Builds a url with UTM parameters.

  • Calculates body mass index values from height and weight in metric system measures.

  • This module is deprecated, please use instead [Calculate Trip Between Two Locations].

  • Calculate trip between two locations, using either addresses or coordinates, to plan your route efficiently.

  • Provides content analysis results, including assessments for adult, racy, and gory content, along with respective scores.

  • This endpoint can be used to check the status of scheduled code executions created by using the Asynchronous Python Code endpoint.

  • Checks content of input text and states if it's 'safe'.

  • Detects if the requested day is a weekend or a working day.

  • Checks if the email domain belongs to a free-mailer (gmail, yahoo, outlook etc.).

  • This module allows to create a rate limit for incoming request in order to manage traffic.

  • Detects if a EU VAT rate applies.

  • Compare strings using available algorithms.

  • Reduce the file size of PDFs

  • Searches if a text contains a given input.

  • Takes a CSV string and converts it to a valid JSON.

  • Convert an image to a different image format.

  • This module will convert a CSV file with headers to a multiple row format for uploading into other APIs.

  • Converts a currency into another on specific dates.

  • Convert HTML to image.

  • Convert a PDF file to Base64.

  • This module converts a PDF from a given URL into individual image files for each page, providing downloadable URLs for each image in the response.

  • Converts timezones around the global timezones.

  • Creates a global variable.

  • Stores a JSON object online and access it in other scenarios or applications.

  • Creates a PDF file from HTML or URL, and acts as a HTML to PDF converter.

  • Creates a tinyurl and shortened URL.

  • This module generates a blank PDF document, providing a versatile starting point for various document creation and editing tasks.

  • Upload a buffer and returns a temporary file URL. Works best in combination with our other APIs and other SaaS.

  • Extract/crop a region of the image.

  • Decodes a QR code from a URL or buffer.

  • Decode and validate JWT Token.

  • Decode JWT Token.

  • Decrypts a ciphertext with a selected method.

  • This module removes encryption from PDF documents, restoring access to content for authorized users and systems.

  • Deletes a file from 0-CodeKit storage.

  • Deletes a Global Variable.

  • Deletes a JSON Bin stored online.

  • Deletes a shortened URL.

  • Deletes a scheduled task.

  • Identifies image colors, including dominant foreground and background colors, accent color, and whether the image is black and white.

  • Categorizes emails based on subject and content for efficient message classification.

  • Identifies and reports the number of faces along with their positions within an image.

  • Detects the text in a picture using Optical Character Recognition AI.

  • Converts Word file to PDF using URL or buffer as input.

  • Downloads a saved file by file name from 0-CodeKit storage.

  • Draws an image over specified pages of a PDF, sourced from a URL or directly provided, with customizable positioning, rotation, and dimensions, offering an option to return the modified PDF as a URL.

  • Draws specified text onto a PDF from a URL or buffer, allowing customization of font, position, rotation, size, color, and target pages, with the option to return the result as a URL.

  • This module modifies the metadata of a PDF, allowing for updated authorship, subject and keywords to better organize and identify documents.

  • Embed an existing XML Invoice into a PDF File.

  • Encodes a QR Code with Data or URL.

  • Encode a JWT Token.

  • Encrypts a message with a selected method.

  • This module secures PDF documents by applying encryption, protecting sensitive information from unauthorized access.

  • Retrieves the full and long URL of a shortened URL.

  • Extract Contact Information from text.

  • This function leverages an LLM to extract the specified information from the text and organizes it into a structured object.

  • Extracts the content between two strings start and end of a text body. The argument greedy can be set to true so that the resulting text contains the start and end in it.

  • Extracts text and specific data from documents, supporting OCR and specialized workflows. This endpoint is powered by Natif.ai.

  • Gets standard UTM parameters from a URL.

  • Flips an image by x or y-axis.

  • This function takes a query string and a list of target strings. It uses an LLM to find the best match(es), accounting for variations in the query string, and returns the closest match(es) based on the options provided.

  • Generate a barcode with options.

  • Generates a random name.

  • Generates a random number between the defined range and type.

  • Generates a random string of personalized lenght and characters.

  • Generate Image.

  • Use the collection of chart endpoints to generate and integrate charts in your automations.

  • Use the collection of chart endpoints to generate and integrate charts in your automations.

  • Generate JavaScript Code based on description.

  • Use the collection of chart endpoints to generate and integrate charts in your automations.

  • Generate Python code.

  • Gets a calendar-week by week number, year, date or a unix timestamp.

  • Retrieves selected global variable by its name.

  • Gets a JSON Bin.

  • Retrieves a random city from Planet Earth.

  • Get Current Month details: workdays, weekends, first and last day of month, number of days.

  • Get detailed information for a date period.

  • Get one or multiple HTML Elements (CSS Selector, XPath, Class and ID).

  • Get one or multiple HTML elements from URL.

  • Get SVG logo from URL provided.

  • This endpoint allows you to retrieve metadata information from a PDF file.

  • This endpoint can be used to generate random colors.

  • Helps you identify the gender of a person by their first name.

  • Gets the geolocation of an IP address.

  • Retrieves a Nation ISO-Alpha-3166 Country code from the name or a Nation name from the ISO-Alpha-3166.

  • Gets the page count from a PDF file either via URL or buffer.

  • Get Thumbnail from video URL.

  • Hashes a text with selected methods.

  • This endpoint accepts a website URL and converts it to an image.

  • Blur an image with buffer input.

  • Convert an input buffer image to a different image format.

  • Extract/crop a region of the image with buffer input.

  • Extract EXIF data from image with buffer input.

  • Flips an image by x or y-axis with buffer input.

  • Remove background from image eg. remove.bg with buffer input.

  • Resize an image to a specified heigth and width with buffer input.

  • Rotate an image with buffer input by specified angle and optional background color.

  • Sharpens an image with optional sigma value using buffer input.

  • Transcribe audio file with buffer input.

  • List public holidays from specified country for a given year.

  • Performs an arbitrary authorized API call.

  • Converts a markdown string to a PDF document.

  • Merges a video file and an audio file into a single video file, optionally applying various customizations like trimming, fading, and more.

  • Merges audio files like mp3, wav, ogg, flac, m4a into one audio file.

  • Merges multiple PDF files into a single PDF.

  • Convert a .msg file to json via url or buffer input.

  • This endpoint takes two images to return a single overlayed image.

  • Parse URL.

  • Extracts text from PDF documents.

  • Recognizes objects in a picture using AI.

  • Read a barcode and get the data

  • Reads an image from URL or buffer and extracts the EXIF data.

  • This function leverages AI technology to identify sensitive content according to the user's description and redacts it from the file by drawing black rectangles over it.

  • Remove background from image eg. remove.bg

  • This module deletes specified pages from a PDF document.

  • Rephrase a text too long to read by keeping relevant information.

  • Resize an image to a specified heigth and width.

  • This module adjusts the dimensions of pages within a PDF to specified sizes.

  • Retrieve remaining user credits.

  • Rotate an image by specified angle and optional background color.

  • This module rotates specified pages within a PDF document to a designated orientation, enhancing readability and presentation.

  • This endpoint can be used to execute complex python scripts and AI related code. Runs asynchronously and returns data to a Webhook. Use this for Selenium, Chrome and OpenAI / AI related python scripts.

  • Runs your javascript .js code and returns the result.

  • This module executes JavaScript scripts hosted on the 0CodeKit platform.

  • Runs your python code and returns the result.

  • This module executes Python scripts hosted on the 0CodeKit platform.

  • Schedules a webhook execution with JSON by setting up a cronjob or timer.

  • This module retrieves the HTML body of a website or text-only content if the option is chosen.

  • Sharpens an image with optional sigma value.

  • Splits a given string of potential names into its first name and last name.

  • Switches the input value with a JSON text of values or a URL to a remote JSON.

  • Transcribe audio file.

  • Gets the translation of a text or multiple sentences.

  • Updates a global variable.

  • Updates a JSON Bin.

  • Updates the destination URL of a shortened URL.

  • Uploads a file either from a URL or as a buffer. You can permanently store files up to 10MB and reuse them in workflows and scenarios.

  • Validated Factur-X/Zugferd XML PDF File invoice according to the specification (level EN16931)

  • Checks if the address provided is valid.

  • This module verifies the validity and format of a given phone number, providing detailed information including international and national formats, country code, and validation status.

  • Validates an email address matching it with standards and eventually corrects it.

  • Verifies a banking BIC.

  • Verifies a top-level- or subdomain.

  • Verifies a European banking-IBAN.

  • Checks if VAT number and its ID is valid.

  • Extract the audio from a video. This can be useful for transcription.

  • Modify a PDF to add a semi-transparent watermark text, with customizable parameters without obscuring content.

  • Modify a PDF to add a semi-transparent watermark image, with customizable parameters without obscuring content.

Select a trigger and an action

Create workflow (opens in a new tab)

Triggers and actions

0CodeKit serves as a trigger that initiates automated workflows when AI-generated content is produced—whether it's intelligent text responses from ChatGPT, visual content from DALL-E, videos from Sora, or audio transcriptions from Whisper. These OpenAI outputs automatically trigger OpenAI (ChatGPT, Sora, DALL-E, Whisper) to perform specific actions, such as processing the generated content into your development pipeline, building no-code solutions based on AI responses, or integrating AI-generated images and transcriptions directly into your OpenAI (ChatGPT, Sora, DALL-E, Whisper) projects. This trigger-action integration enables you to automatically execute OpenAI (ChatGPT, Sora, DALL-E, Whisper) operations whenever OpenAI produces new content, creating workflows where AI generation immediately flows into your no-code development environment without manual intervention.

Add Pages
This module inserts new blank pages into a PDF at specified positions.
Action
Advanced Get PDF Metadata Information
This module retrieves detailed metadata from a PDF, such as the dimensions of each page, enhancing document analysis and management.
Action
Analyze images (Vision)
Analyzes images according to specified instructions.
Action
Blur an Image
Blur a image with optional blur strength.
Action
Build a URL with UTM Parameters
Builds a url with UTM parameters.
Action
Calculate BMI Values
Calculates body mass index values from height and weight in metric system measures.
Action
Calculate the Distance between Adresses (old)
This module is deprecated, please use instead [Calculate Trip Between Two Locations].
Action
Calculate Trip Between Two Locations
Calculate trip between two locations, using either addresses or coordinates, to plan your route efficiently.
Action
Cancel a batch
Cancels an "in-progress" batch. The batch will be in status "cancelling" for up to 10 minutes, before changing to "cancelled", where it will have partial results (if any) available in the output file.
Action
Load more

How to set up OpenAI (ChatGPT, Whisper) and 0CodeKit in 5 easy steps

Date

·

Duration

Step 1

Create a new scenario in Make

Log into your Make account and start a new scenario by clicking the plus button. A scenario is a workflow that connects different apps together, allowing them to work automatically without manual effort.

Date

·

Duration

Step 2

Add your first application

Click on the empty circle with a plus sign to open the app menu. Search for and select your first application, like OpenAI GPT-3 or OneSaas, then choose what action you want it to perform in your workflow.

Date

·

Duration

Step 3

Connect and authenticate your first app

Click 'Create a connection' when prompted and enter your login credentials or API key for the application. Give your connection a memorable name so you can easily recognize it later, then save it to continue building your scenario.

Date

·

Duration

Step 4

Add and connect your second application

Add another module by clicking the plus sign and select your second application. Create a connection for this app as well by entering the required credentials or API key, just like you did with the first application.

Date

·

Duration

Step 5

Test your connections

Use the test feature to make sure both applications are connected properly and can communicate with each other. Running a test ensures your scenario will work correctly before you activate it for regular use.

Automate AI workflows: OpenAI and 0CodeKit integration benefits

Discover how integrating OpenAI and 0CodeKit creates powerful automated workflows for document processing, content generation, and file management—all without coding expertise required.

Date

·

Duration

Automated AI-powered document processing

Automatically process PDFs, images, and files with OpenAI's GPT models through 0CodeKit's toolkit for efficient content extraction and analysis.

Date

·

Duration

Intelligent file generation workflows

Combine OpenAI's text and image generation capabilities with 0CodeKit's file handling to automatically create, convert, and manage AI-generated content.

Date

·

Duration

No-code AI workflow pipeline

Build sophisticated AI workflows without programming by connecting OpenAI's models with 0CodeKit's ready-to-use tools for data transformation and file operations.

Date

·

Duration

Scalable content processing automation

Process large volumes of documents, images, and files through OpenAI's AI models using 0CodeKit's batch processing capabilities without manual intervention.

Support

FAQs

Everything you need to know about Make. Can't find the answer you're looking for? Please chat to our team.

By connecting OpenAI and 0CodeKit through Make, you can create powerful automated workflows that combine OpenAI's advanced AI capabilities (GPT-4, DALL-E, Whisper) with 0CodeKit's versatile tools for processing PDFs, images, files, and code. For example, you could automatically extract text from PDFs using 0CodeKit, send it to ChatGPT for analysis or summarization, and then generate visual content with DALL-E—all without writing a single line of code. This integration eliminates manual data transfer between platforms and enables you to build sophisticated AI pipelines in minutes.

The integration opens up numerous possibilities: automatically transcribe audio files with Whisper and process them through 0CodeKit's file handlers, generate AI-powered content with GPT-4 and convert it into formatted PDFs, create images with DALL-E and batch process them using 0CodeKit's image tools, or extract data from documents with 0CodeKit and have ChatGPT analyze and generate insights. Make's visual workflow builder allows you to chain these actions together, creating custom automation that fits your specific business needs—from content creation pipelines to document processing systems.

No coding skills are required. Make's intuitive drag-and-drop interface allows you to connect OpenAI and 0CodeKit visually. You simply select triggers and actions from each application, map the data fields between them, and Make handles all the technical API connections in the background. Whether you want to process files with 0CodeKit before sending them to OpenAI's models, or vice versa, you can build these integrations through a user-friendly visual interface. This makes advanced AI automation accessible to marketers, entrepreneurs, and business professionals without technical backgrounds.

Make provides a robust integration platform with built-in error handling, data transformation tools, and monitoring capabilities. When you connect OpenAI and 0CodeKit, Make manages the API calls, handles authentication, and ensures data is properly formatted as it moves between applications. You can set up conditional logic to handle different scenarios, use Make's data transformation functions to prepare information for each service, and receive notifications if anything needs attention. Plus, Make's execution history lets you track every workflow run, making it easier to troubleshoot and optimize your OpenAI and 0CodeKit integrations for maximum reliability.