Skip to main content

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

Register now (opens in a new tab)
Google Gemini AI
OpenAI (ChatGPT, Whisper)

Connect Google Gemini AI and OpenAI (ChatGPT, Sora, DALL-E, Whisper) integrations

Explore ready-made Google Gemini AI and OpenAI (ChatGPT, Whisper) templates and start automating in minutes.

Get started free

Create a custom workflow

Connect Google Gemini AI with OpenAI (ChatGPT, Sora, DALL-E, Whisper) through Make to automatically trigger conversational responses, visual content creation, and audio transcriptions based on Google Gemini AI inputs—creating intelligent workflows that respond to your needs without manual intervention.

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.

Google Gemini AI
Trigger: Watch events
OpenAI (ChatGPT, Whisper)
Action: Select an action
1. Select a trigger

  • Triggers when a long running task has finished.

2. Select an action

  • Analyzes images according to specified instructions.

  • 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.

  • Creates and executes a batch of API calls.

  • Creates a new skill.

  • Creates a new immutable skill version.

  • Creates a new vector store and optionally adds files to it, or adds files to an existing vector store.

  • Deletes an existing conversation.

  • Deletes an existing model response.

  • Deletes a skill. This action cannot be undone.

  • Deletes a skill version. This action cannot be undone.

  • Deletes a vector store. This action cannot be undone.

  • Downloads a file from a container.

  • Downloads a skill as a ZIP file using its ID.

  • Downloads a skill version as a ZIP file.

  • Creates an edited or extended image given one or more source images and a prompt.

  • Generates a chat completion.

  • Qualifies whether the provided image or text(s) contains violent, hateful, illicit or adult content.

  • Generates a response.

  • Transcribes an audio to text.

  • Translates an audio to English.

  • Creates an embedding vector representing the input text.

  • Generates images using GPT Image.

  • Generates an audio file based on text input and settings.

  • Retrieves details of the specified batch.

  • Retrieves an existing model response.

  • Returns information about a specific skill by its ID.

  • Returns information about a specific skill version.

  • Performs an arbitrary authorized API call.

  • Generates text responses from prompts without requiring an account or connection.

  • Identifies information in a prompt's text and returns it as structured data.

  • Updates the default version pointer for a skill.

  • Uploads a file to be used across the OpenAI platform.

Select a trigger and an action

Create workflow (opens in a new tab)

Triggers and actions

Connect OpenAI (ChatGPT, Sora, DALL-E, Whisper) as a trigger with Google Gemini AI as an action through Make's integration platform. When OpenAI (ChatGPT, Sora, DALL-E, Whisper) detects or processes specific inputs, it triggers automated actions in Google Gemini AI to generate conversational responses, create visual content, or transcribe audio files. This trigger-action workflow enables you to automatically route outputs from OpenAI (ChatGPT, Sora, DALL-E, Whisper) directly into Google Gemini AI's suite of tools, creating automation chains that respond dynamically to your inputs without manual intervention.

Analyze images (Vision)
Analyzes images according to specified instructions.
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
Create a batch
Creates and executes a batch of API calls.
Action
Create a file search store
Creates a new file search store.
Action
Create a skill
Creates a new skill.
Action
Create a skill version
Creates a new immutable skill version.
Action
Create a vector store or add files
Creates a new vector store and optionally adds files to it, or adds files to an existing vector store.
Action
Delete a conversation
Deletes an existing conversation.
Action
Delete a file in a file search store
Deletes a file from a selected files search store.
Action
Load more

How to set up Google Gemini AI and OpenAI (ChatGPT, Whisper) in 5 easy steps

Date

·

Duration

Step 1

Set up your Google Cloud project

Log in to Google Cloud Platform with your Google account and create a new project by clicking 'Create or select a project' and then 'New project'. Give your project a name and location, then click 'Create'. This project serves as the foundation that will allow Make to connect with Google Gemini AI and use its features in your automated workflows.

Date

·

Duration

Step 2

Generate your API key in Google AI Studio

After your Google Cloud project is ready, go to Google AI Studio and click 'Get API key', then select 'Create API key'. Choose your existing Google Cloud project from the list and click 'Create API key in existing project'. This API key is like a special password that allows Make to securely communicate with Google Gemini AI on your behalf.

Date

·

Duration

Step 3

Store your API key safely

Copy the API key that appears on your screen and save it in a secure location where you can easily access it later. Treat this key like you would a password, as it provides access to your Google Gemini AI services. You'll need this key in the next step to complete the connection in Make.

Date

·

Duration

Step 4

Add the Google Gemini AI module in Make

Log in to your Make account and open the scenario where you want to use Google Gemini AI. Add a Google Gemini AI module to your scenario, which will automatically prompt you to create a new connection. This is where you'll link your Make account with the Google Gemini AI service you set up earlier.

Date

·

Duration

Step 5

Complete the connection

Click 'Create a connection' when prompted and paste the API key you copied from Google AI Studio into the 'API Key' field. You can optionally give your connection a custom name to help you identify it later, then click 'Save'. Once saved, the connection is active and Google Gemini AI will be ready to use in your Make automation scenarios.

Build advanced AI workflows with Google Gemini AI and OpenAI integration

Combine Google Gemini AI and OpenAI (ChatGPT, Sora, DALL-E, Whisper) to compare outputs, ensure reliability, optimize costs, and build powerful multimodal workflows that leverage each platform's strengths.

Date

·

Duration

Multi-model AI comparison and validation

Automatically route the same prompts to both Google Gemini and OpenAI models to compare outputs, validate responses, and select the best AI-generated content for your specific use case.

Date

·

Duration

Intelligent fallback and redundancy system

Create a resilient AI workflow where if one service experiences downtime or rate limits, Make automatically switches to the alternative AI provider to ensure uninterrupted operations.

Date

·

Duration

Specialized task distribution

Leverage the unique strengths of each AI platform by routing specific tasks to the most suitable model, such as using Gemini for Google-integrated tasks and GPT-4 for complex reasoning.

Date

·

Duration

Cost optimization through smart routing

Automatically distribute AI requests between Google Gemini and OpenAI based on pricing, token limits, or task complexity to minimize API costs while maintaining quality output.

Support

FAQs

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

Integrating Google Gemini AI with OpenAI models through Make allows you to leverage the unique strengths of both AI platforms in a single automated workflow. You can compare responses from different models, use Gemini for certain tasks like code generation while using GPT-4 for creative writing, or create fallback systems where if one API is unavailable, your workflow automatically switches to the other. This integration enables you to build more robust, versatile AI solutions without writing complex code, simply by connecting the apps visually in Make's platform.

Not at all! Make's visual, no-code interface makes it straightforward to connect Google Gemini AI and OpenAI services. You simply authenticate both applications with your API keys, then drag and drop modules to create your workflow. Make handles all the technical complexity of API calls, data formatting, and error handling automatically. You can have your first integration running in minutes, whether you want to send the same prompt to both AIs for comparison, chain their outputs together, or create conditional logic based on their responses.

The integration opens up powerful automation possibilities: create a content generation pipeline where Gemini drafts technical documentation and GPT-4 refines it for readability; build a multilingual customer support system using both AIs for translation and response generation; develop a code review workflow where one AI writes code and the other reviews it; or create an image-to-text-to-image pipeline using DALL-E and Gemini together. You can also automate prompt testing across both platforms simultaneously, aggregate their responses for better decision-making, or use Whisper for transcription followed by Gemini or GPT for summarization and analysis.

Absolutely! Building custom integrations between Google Gemini AI and OpenAI would require significant development time, ongoing maintenance, server infrastructure, and technical expertise. Make eliminates all of these costs with its ready-made connectors and visual workflow builder. You only pay for your Make plan and the API usage from Google and OpenAI themselves. Make also includes built-in error handling, scheduling, and monitoring features that would take weeks to develop independently. Most users can start with Make's free tier to test integrations, then scale affordably as their automation needs grow, making it far more cost-effective than custom development.