[FREE] ChatGPT Extension - All OpenAI Models: GPT-5.4, GPT-4o, Vision, GPT-imagem-2, Image Edit, TTS, Batch & Function Calling

[Teddy_Brask-Andersen]

Thanks! Do you know of any extensions that support WebSockets and headers?
Is your extension free or a sponsor version?

[_Ahmed ((Mr. Koder)‬‏)]

Try this

[PAID] ChatGPT extension to create fantastic conversations with gpt models

New update, now you can generate images with DALLE

[Teddy_Brask-Andersen]

Hi, thanks! I got it. It looks like what I was looking for

[_Ahmed ((Mr. Koder)‬‏)]

Thanks, I hope so ,
And I I am waiting for your feedback

[Teddy_Brask-Andersen]

Hi, do you have a demo.aia? the one in the download can’t load in kodular as a project.
I’m focused in the gpt stream part.

Br Teddy

[_Ahmed ((Mr. Koder)‬‏)]

Try with MIT app inventor the aia file originally for AI2 not kodular

[Teddy_Brask-Andersen]

It’s loading perfectly in App Inventor - Thx.

[Passos_0213]

17. UploadTrainingFile (NEW)

• Description: Uploads a JSONL file for use in fine-tuning.

• Parameters:

  • apiKey (Text): Your OpenAI API key.
  • filePath (Text): Path to the JSONL file to upload.

• Returns: Triggers FileUploaded event with the file ID or ReportError if an error occurs.

• How it works: This method sends a multipart/form-data HTTP POST request to OpenAI’s API to upload the specified JSONL file for fine-tuning purposes.

18. StartFineTuningJob (NEW)

• Description: Starts a fine-tuning job using an uploaded JSONL file.

• Parameters:

  • apiKey (Text): Your OpenAI API key.
  • trainingFileId (Text): The ID of the uploaded JSONL file.
  • model (Text): The base model to fine-tune (e.g., gpt-4o-mini or gpt-3.5-turbo).
  • suffix (Text): Optional suffix to append to the fine-tuned model’s name.

• Returns: Triggers FineTuningJobStarted event with job details or ReportError if an error occurs.

• How it works: This method sends an HTTP POST request to OpenAI’s fine-tuning endpoint, creating a fine-tuning job using the provided file and model.

[charlesaccount (CharlesKoder93)]

Thanks, Ahemed, I have pm’d you.

[Passos_0213]

Creating GPT JSONL files

Click here to access my website that generates the files in an intuitive way.

https://imgur.com/lFQ4lNG.png

[Passos_0213]

NEW - Version 9 (GPT Embedding)

[Passos_0213]

News

The extension was factored into categories and recompiled with Fast Cli and ProGuard.

[Mental_Magic]

I´m trying to use Vision with an image from a component but I´m geting error all the time, only working with URL images, any ideas?

[Passos_0213]

Unfortunately, it is a problem with the MIT App Inventor base system itself, which does not allow working with base 64 images.

[Passos_0213]

How did I solve this problem by sending to an Image2URL conversion server?

[Mental_Magic]

do you know any free api service to do that?

[Passos_0213]

I designed a solution with Imgur and Imbb server: [FREE] Convert images to URL with Imgur API

[Mental_Magic]

thank you so much! I will check it out

[charlesaccount (CharlesKoder93)]

Hi @Passos_0213 , I sent a pm regarding the extension, thanks

[Passos_0213]

ChatGPT Extension v10 - What’s New!

Latest Update: GPT-4.1, GPT-4o, GPT-Image-2, Batch Processing, Function Calling, 13 TTS Voices & More!

---

Quick Summary

Feature	Status
New Language Models	GPT-4.1, GPT-4.1-mini, GPT-4.1-nano, GPT-5.4, GPT-5.4-mini
Reasoning Models	o3, o3-mini, o4-mini
Image Models	GPT-Image-2, GPT-Image-1.5, GPT-Image-1, GPT-Image-1-mini
TTS Voices	13 voices (7 new: Ash, Ballad, Coral, Marin, Sage, Verse, Cedar)
TTS Models	GPT-4o-mini-tts
Embedding Models	Text-Embedding-3-Large
Moderation	Omni-Moderation-Latest
Image Edit	Edit, Variation, Inpaint
Batch Processing	Create, Retrieve, List, Cancel
Function Calling	Define, Execute, Auto-execute

---

Visual Blocks Gallery

GPTVision1 - Vision Response

GPTUtils1 - Dialogs & Utilities

GPTThreads1 - Thread Management

GPTText1 - Text Response & JSON Decode

GPTSpeech1 - Speech Generation (13 Voices!)

GPTModerate1 - Content Moderation

GPTMessages1 - Message Management

GPTImageEdit1 - Image Editing (NEW!)

GPTImage1 - Image Generation

GPTFunctionCalling1 - Function Calling (NEW!)

GPTFineTuning1 - Fine Tuning

GPTEmbedding1 - Text Embedding

GPTBatch1 - Batch Processing (NEW!)

---

New Features Overview

1. New Models

• GPT-4.1 Family: GPT-4.1, GPT-4.1-mini, GPT-4.1-nano
• GPT-5.4 Family: GPT-5.4, GPT-5.4-mini
• Reasoning Models: o3, o3-mini, o4-mini
• Image Models: GPT-Image-2, GPT-Image-1.5, GPT-Image-1, GPT-Image-1-mini
• TTS Models: GPT-4o-mini-tts
• Embedding: Text-Embedding-3-Large

2. Image Edit

EditImage(apiKey, imagePath, prompt, operation, model, size, n, maskPath)
GenerateVariation(apiKey, imagePath, model, size, n)
InpaintImage(apiKey, imagePath, maskPath, prompt, model, size, n)

3. Batch Processing

CreateBatchJob(apiKey, inputFileId, endpoint, completionWindow, customId)
RetrieveBatchJob(apiKey, batchId)
ListBatchJobs(apiKey, limit, after)
CancelBatchJob(apiKey, batchId)
CheckBatchStatus(apiKey, batchId)
CreateBatchInput(customId, endpoint, model, prompt, systemMessage)

4. Function Calling

DefineFunction(name, description, parametersJson)
DefineSimpleFunction(name, description, paramName, paramType, paramDescription, required)
SendPromptWithFunctions(prompt, model, systemMsg, temperature, maxTokens, topP, frequencyPenalty, apiKey, autoExecute)
ClearFunctions()
GetFunctionsList()
ExecuteFunction(functionName, argumentsJson, apiKey, model)

5. New TTS Voices

Voice	Style
Alloy	Neutral
Ash	NEW - Clear & Young
Ballad	NEW - Melodic
Coral	NEW - Warm
Echo	Neutral
Fable	Neutral
Marin	NEW - Calm
Nova	Neutral
Onyx	Neutral
Sage	NEW - Wise
Shimmer	Neutral
Verse	NEW - Poetic
Cedar	NEW - Earthy

Total: 13 Voices Available!

---

Quick Comparison

Feature	v10	v11 (Latest)
Language Models	3	12
Reasoning Models	0	3
Image Models	1	4
TTS Voices	6	13
TTS Models	2	4
Embedding Models	2	3
Omni-Moderation
Image Edit
Batch Processing
Function Calling

---

Download

Version	Features	Download	Size
Latest (v11)	All features + New Models	com.bosonshiggs.chatgpt.aix	93.1 KB

---

Quick Setup

1. Download the latest AIX file
2. Import into Kodular Creator
3. Add your OpenAI API Key
4. Start building!

Example: SendPrompt("Hello!", "gpt-4.1", "You are helpful", 0.7, 1000, 1.0, 0.0, apiKey)

---

All Available Methods

Text & Chat

• SendPrompt - Send text to ChatGPT
• JsonDecode - Extract JSON values

Image

• GenerateImage - Create images
• EditImage - Edit existing images
• GenerateVariation - Create variations
• InpaintImage - Replace masked areas

Threads

• CreateThread, RetrieveThread, ModifyThread, DeleteThread

Messages

• CreateMessage, RetrieveMessage, ModifyMessage, ListMessages

Speech

• GenerateSpeech - Text-to-Speech with 13 voices

Vision

• SendVisionRequest - Analyze images

Fine-Tuning

• UploadTrainingFile, StartFineTuningJob

Embeddings

• GenerateEmbedding

Batch

• CreateBatchJob, RetrieveBatchJob, ListBatchJobs, CancelBatchJob, CheckBatchStatus, CreateBatchInput

Function Calling

• DefineFunction, DefineSimpleFunction, SendPromptWithFunctions, ClearFunctions, GetFunctionsList, ExecuteFunction

Moderation

• ModerateContent

Utilities

• ShowNativeAudioPlayerDialog, ShowTextInputDialog, ShowListDialog

---

Events

Event	When Triggered
ResponseReceived	Text response received
ImageGenerationCompleted	Image generated
ImageEditCompleted	Image edited
SpeechGenerated	Speech generated
VisionResponseReceived	Vision analysis complete
ContentModerationCompleted	Moderation complete
BatchJobCreated	Batch job created
BatchJobRetrieved	Batch job retrieved
BatchJobsListed	Jobs listed
BatchJobCancelled	Job cancelled
FunctionCalled	Function requested by AI
FunctionExecuted	Function executed
FunctionCallCompleted	Function call complete
ThreadCreated / ThreadRetrieved	Thread operations
MessageCreated / MessageRetrieved	Message operations
FileUploaded / FineTuningJobStarted	Fine-tuning operations
EmbeddingGenerated	Embedding generated
TextEntered / ListItemSelected	Dialog interactions
ReportError	Error occurred

---

Support

Click here to support development

Support: Telegram | GitHub

---

Summary

Version 11 brings:

• 9 New Language Models
• 3 Reasoning Models
• 4 Image Models
• 7 New TTS Voices (Total: 13)
• Omni-Moderation
• Text-Embedding-3-Large
• Image Edit & Inpaint
• Batch Processing
• Function Calling
• Better Performance & Stability

Download now and start building amazing AI-powered apps!

---

Last Updated: July 2026