Generate context-aware text from images, audio, documents, or text input. Combine media with prompts, create and edit JSON data, and automate content generation through workflows.
       
⚡ Main Functions

• Media-based content generation.
   Creates context-aware text from images, audio, and documents.
• Text-based content generation.
   Generates contextual text from user-provided text input.
• JSON data creation and editing.
   Creates and edits JSON, including nested structures and conversions.

⚡ Key Features

🧩 Combined media and text prompts
     Uses images or audio together with text for enriched outputs.
🔄 JSON transformation and generation
     Supports conversions, nested data, and random JSON generation.



Documentation

We’ve created a detailed step-by-step guide for the Gemini API Plugin. It includes a comprehensive overview of all features, practical use cases, and answers to frequently asked questions.

       
Supported API Calls

✅ Get Model (Data): Retrieve details about a specific model as a data source.
✅ Get Model (Action): Retrieve details about a specific model triggered by a workflow action.
✅ List Models (Data): Fetch a list of available models as a data source.
✅ List Models (Action): Fetch a list of available models triggered by a workflow action.
✅ Upload Media (Action): Upload a media file for processing, triggered by a workflow action.
✅ Get File (Data): Retrieve details of a specific file as a data source.
✅ Get File (Action): Retrieve details of a specific file triggered by a workflow action.
✅ List Files (Data): Fetch a list of files as a data source.
✅ List Files (Action): Fetch a list of files triggered by a workflow action.
✅ Delete File (Action): Delete a specific file triggered by a workflow action.
✅ Generate Content From Text (Data): Generate content based on text input as a data source.
✅ Generate Content From Text (Action): Generate content based on text input triggered by a workflow action.
✅ Generate Content From File and Text (Data): Generate content using a file and text input as a data source.
✅ Generate Content From File and Text (Action): Generate content using a file and text input triggered by a workflow action.
✅ Generate JSON (Data): Generate structured JSON content as a data source.
✅ Generate JSON (Action): Generate structured JSON content triggered by a workflow action.
✅ Generate Chat (Data): Generate chat-based content as a data source.
✅ Generate Chat (Action): Generate chat-based content triggered by a workflow action.


FAQ

- What types of input can the plugin process?  
The plugin supports text, image, file and audio inputs to generate detailed and context-aware text content.

- Can the plugin create content directly from an image or audio file?
Yes, the plugin analyzes uploaded images or audio files to extract contextual information.

- How does the plugin process images or audio?  
The plugin extracts contextual information or descriptions from the uploaded image or audio files and generates relevant text content.

- Can I combine text and media inputs?  
Yes, the plugin allows you to combine text prompts with image or audio inputs to create more comprehensive text outputs.

- What is required to start using the plugin?  
You will need an API key from Gemini and familiarity with Bubble workflows to configure and trigger content generation.

   


Our Similar Plugins

- Google Perspective
- OpenAI ChatGPT 5 + Full ChatGPT 4
- OpenAI ChatGPT 4o Vision  Assistant
- Google Natural Language API
- Vapi Assistant AI Pro
- DeepSeek AI Models
- Replicate AI Models




Support

If you still have questions or unresolved issues, you can contact us.


Risk-free Trial

The most risk-free way to try out this plugin is to subscribe to it. If you unsubscribe a few days later you will be charged on pro-rata basis, so for example if the plugin monthly price is $5 then you’d pay only 17¢ per day ($5/30 days)!