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

[_Ahmed ((Mr. Koder)‬‏)]

I have already added this feature in this topic of MIT app inventor
But I don’t update this topic here in kodular yet

[Paid] 🌟 ChatGPT extension to create fantastic conversations with ChatGPT

[Obiettivo_A (Mzu)]

I guess websearch requires an extension update. I already purchased, can you send me the update?

[_Ahmed ((Mr. Koder)‬‏)]

PM Me please

[_Ahmed ((Mr. Koder)‬‏)]

Two new fantastic features added to the ChatGPT extension

Now this extension is the most advanced extension in the whole community that creates chat conversation with chat GPT models via chat GPT API

1. Web search

Allow models to search the web for the latest information before generating a response.

@_Ahmed

​The SendStreamedMessage function is designed to send a series of prompts to the OpenAI Chat Completions API and receive responses in a streaming manner. This version of the function includes an option to enable or disable web search capabilities and incorporates enhanced error handling to manage potential issues during the API request and response processing.​

Function Parameters:

• id (int): A unique identifier for the message stream, used to track and manage the streaming process.​
• prompts (YailList): A list of dictionaries, each containing a ‘role’ and ‘content’ key, representing the sequence of messages in the conversation.​
• model (String): The code representing the desired OpenAI model to be used for generating responses, but in case of “enableWebSearch”= true you can only use one of these models * gpt-4o-search-preview or gpt-4o-mini-search-preview.​
• apiKey (String): The API key for authenticating requests to the OpenAI API.​
• maxTokens (int): The maximum number of tokens to generate in the response.​
• temperature (double): Controls the creativity of the response; higher values result in more creative outputs.​
• enableWebSearch (boolean): Determines whether to enable web search capabilities during the response generation.

2. Structured Outputs

Ensure responses adhere to a JSON schema.

@_Ahmed

---

The RequestCustomStructuredOutput function allows you to send a prompt to an OpenAI model and receive a response structured according to a custom JSON schema. This ensures that the model’s output adheres to a specific format, facilitating easier parsing and integration into applications.​

• apiKey (String): Your OpenAI API key for authentication.​
• modelName (String): The identifier of the OpenAI model to use (e.g., “gpt-4o-2024-08-06”).​OpenAI
• systemInstruction (String): Instructions provided to the model to set context or behavior.​
• userRequest (String): The user’s input or query that the model will respond to.​
• customSchema (String): A JSON-formatted string defining the desired structure of the model’s output. you can get your customized Schema from here

The RequestCustomStructuredOutputVision function

Description:
Sends a prompt to an OpenAI model using both text and image inputs. This function accepts a custom JSON schema to structure the output and supports image sources provided as URLs or local file paths (which are encoded in Base64).

Parameters:

• apiKey (String): Your OpenAI API key.
• modelName (String): The identifier of the model (e.g., “gpt-4o-2024-08-06”).
• systemInstruction (String): Instructions to set the context for the model.
• userRequest (String): The main text prompt from the user.
• customSchema (String): A JSON-formatted string defining the expected structure of the model’s response.
• imageSources (YailList): A list of image source strings. Each item can be either a URL (starting with “http://” or “https://”) or a local file path.
  Events:

• RespondedToCustomStructuredOutput(String response): Triggered when the model returns a response adhering to the custom schema. The response parameter contains the structured data as a JSON string.​

• CustomStructuredOutputError(String errorMessage): Triggered when an error occurs during the request. The errorMessage parameter provides details about the issue.​

Considerations:

• Schema Validation: Ensure that the customSchema parameter is a valid JSON schema. An invalid schema may result in errors or unexpected behavior.​
• Model Compatibility: Verify that the specified modelName supports structured outputs. For instance, models like gpt-4o-2024-08-06 are designed to adhere strictly to provided schemas.

[techxsarthak (Sarthak Gupta)]

@_Ahmed

this extension is the most advanced

And ChatGPT is api is the most costly api

---

Tools, Extensions and Newsletters powered by @techxsarthak
Browse my extensions here. Subscribe to my MIT AI2 newsletter for free here.

[_Ahmed ((Mr. Koder)‬‏)]

Does your extension has the ability to create continuous chat context or streaming support?

A

@techxsarthak

And ChatGPT is api is the most costly api

I have already developed Gemini extension which has a very big quote in the free plan with fantastic and advanced features .

It’s a very good alternative!

[PAID] emini Extension to interact with the Gemini-pro and PaLM 2 models from oogle

[Gemini] The Gemini extension for AI2 allows you to interact with the Google Gemini-Pro and Gemini-Pro-Vesion models and these models that Bard is based on to generate text and control a stream of text generation. Features of the Gemini Extension for AI2: Text Generation with Gemini API: Leverage the power of Google Gemini API for advanced text generation within your AI2 applications. Includes support for various Gemini models. Streaming Text Generation: Experience real-time tex…

[techxsarthak (Sarthak Gupta)]

@_Ahmed

Does your extension has the ability to create continuous chat context or streaming support?

I didn’t say anything about your extension or my extension
I just commented about my views on ChatGPT API

@_Ahmed

Does your extension has the ability to create continuous chat context or streaming support?

As per your question, I have added many of these features into groqtext which will be released in a day or two

@_Ahmed

I have already developed Gemini extension which has a very big quote in the free plan with fantastic and advanced features .

Great Work

[Freemium] GroqText: DeepSeek, Llama, Gemma, Mixtral and Qwen in your app with a single extension (with free tokens daily)

[ezgif-6-95a00689cb] [GroqText] Introduction Integrate a large number of AI Models in your app through the groq api Includes a generous free plan with daily rate limit (without credit card) Includes 2b, 8b and 70b parameter models AI Models Supported (Google, Meta and Mixtral) gemma2-9b-it llama3-8b-8192 llama3-70b-8192 llama-guard-3-8b llama-3.1-8b-instant llama-3.1-70b-versatile llama-3.2-1b-preview* llama-3.2-3b-preview* llama-3.3-70b-versatile llama-3.3-70b-specdec mixtral-8x7b-32768 G…

GroqText supports 15+ models of different context lengths and fine tuned for different tasks. It also supports distilled models meaning Qwen trained on DeepSeek.
For vision based questions I have made

[PAID] 👁️ GroqVision Extension: Integrate LLAMA-3.2-90B/11B Parameter Vision Models in your app

[ezgif-6-95a00689cb] [GroqText (1)] Introduction Integrate AI Vision Models into your app Includes a generous free plan with daily rate limit (without credit card) Includes 11b and 90b parameter models Features of Groq Inference Lightning fast AI Models Supports Open Source AI Vision Models- LLama Best Free Plan that gives 500k tokens* daily for free to use in production AI Models Supported (Llama) llama-3.2-11b-vision-preview llama-3.2-90b-vision-preview Groq AI Free Plan limits Th…

---

Tools, Extensions and Newsletters powered by @techxsarthak
Browse my extensions here. Subscribe to my MIT AI2 newsletter for free here.

[_Ahmed ((Mr. Koder)‬‏)]

@techxsarthak

I didn’t say anything about your extension or my extension

I am just asking to know the features, I don’t mean to be the who you imagine form asking my question

@techxsarthak

As per your question, I have added many of these features into groqtext which will be released in a day or two

Cool ! I am waiting for this great update!

[techxsarthak (Sarthak Gupta)]

@_Ahmed

Cool ! I am waiting for this great update!

Thanks for your interest

[_Ahmed ((Mr. Koder)‬‏)]

New update

The audion streamimg is here ! [now you can create interactive chats with voices with more contorl and fast smooth style ]

@_Ahmed

RequestAudioSpeech Function

Description: ​This function asynchronously requests audio speech synthesis from OpenAI’s Audio Speech API, utilizing specified parameters such as API key, model, input text, voice, optional instructions, folder path, and file name. The synthesized speech is saved as an MP3 file in the designated location.​

Parameters:

• apiKey (String): Your API key for accessing OpenAI’s Audio Speech API.​
• model (String): The model used for speech synthesis. Options include:​
  • tts-1: Optimized for real-time text-to-speech applications.
  • tts-1-hd: Optimized for higher-quality speech synthesis
  • gpt-4o-mini-tts: Built on GPT-4o mini, offering fast and powerful text-to-speech capabilities.
• textInput (String): The text to be synthesized into speech.​
• voice (String): The voice selection for audio generation. Supported voices are:​
• alloy​
• ash​
• ballad
• coral​
• echo​
• fable​
• onyx​
• nova​
• sage​
• shimmer​
• instructions (String, optional): You can provide specific instructions to potentially influence the tone, style, or delivery of the speech (e.g., “Speak in a cheerful and positive tone.”). Leave blank if not needed.
• folderPath (String): The directory path where the resulting MP3 file will be saved.​
• fileName (String): The name assigned to the saved MP3 file.

SpeechFileSaved Event

Description: This event is fired when the MP3 file has been successfully saved. It provides the file path as a parameter.

Parameters:

• filePath (String): The path where the MP3 file has been saved.

Usage: Handle this event to perform actions after the MP3 file has been successfully saved.

StreamAudioSpeech

Description

Streams audio speech synthesis from OpenAI in real-time and plays it directly through the device speaker. This function is optimized for low latency playback, starting audio almost immediately as it arrives.

It specifically uses the gpt-4o-mini-tts model and requests audio in PCM format, which is required for the direct playback mechanism. The function incorporates pre-buffering, frame alignment, boundary smoothing (cross-fading), and a final fade-out to minimize glitches and provide a smoother listening experience.

Use the separate StopStream block to halt playback manually.

Parameters

• apiKey (Type: Text)
  • Required. Your unique API key for accessing OpenAI services.
• textInput (Type: Text)
  • Required. The text content you want the AI to speak.
• voice (Type: Text)
  • Required. The desired voice for the speech synthesis. Valid options include: alloy, echo, fable, onyx, nova, shimmer. (Note: The underlying model might support more voices than the older TTS-1).
• instructions (Type: Text)
  • Optional. You can provide specific instructions to potentially influence the tone, style, or delivery of the speech (e.g., “Speak in a cheerful and positive tone.”). Leave blank if not needed.
• Note: The model and responseFormat are fixed internally by this function:
  • Model: gpt-4o-mini-tts
  • Response Format: pcm (Raw Pulse Code Modulation audio data)

SpeechSynthesisError Event

Description: This event is fired when an error occurs during the audio speech synthesis process. It provides an error message as a parameter.

Parameters:

• errorMessage (String): The error message describing the issue encountered.

Usage: Handle this event to capture and handle errors during the speech synthesis process.

How It Works (Simplified)

1. Request: Sends your text and parameters to OpenAI, specifically requesting a pcm audio stream from the gpt-4o-mini-tts model.
2. Pre-buffer: Receives the first small portion of audio data from OpenAI and holds it temporarily.
3. Initialize Player: Sets up the device’s low-level audio player (AudioTrack) configured for the specific PCM format (e.g., 44.1kHz, 16-bit Mono).
4. Write & Play: Writes the pre-buffered data to the player and immediately starts playback.
5. Stream Loop: Continuously receives subsequent small chunks of audio data from OpenAI.
6. Smooth & Play: For each incoming chunk:

• It checks if there’s a large, potentially audible jump (discontinuity) between the end of the last played chunk and the start of the new one.
• If a jump is detected, it applies a very short fade-in to the beginning of the new chunk to smooth the transition, reducing clicks/pops.
• It ensures only complete audio frames (pairs of bytes for 16-bit PCM) are sent to the player.
• The processed chunk is sent to the player to be heard.

7. Final Fade-Out: When the stream from OpenAI ends naturally, a short fade-out is applied to the very last segment of audio for a less abrupt ending.
8. Finish/Error/Stop: Triggers the appropriate event (FinishedAudioStream, AudioStreamError, or relies on StopStream triggering StoppedAudioStream).

Audio Generation: File Download vs. Real-time Stream