# Slow Stream when Assistant Instructions exceed 9,000 characters

**URL:** <https://community.openai.com/t/slow-stream-when-assistant-instructions-exceed-9-000-characters/851660>\
**Category:** Bugs\
**Tags:** gpt-4, api, assistants-api\
**Created:** [July 3, 2024, 4:21am UTC](https://community.openai.com/t/slow-stream-when-assistant-instructions-exceed-9-000-characters/851660 "2024-07-03T04:21:49Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jblake](https://avatars.discourse-cdn.com/v4/letter/j/d26b3c/32.png) [@jblake](https://community.openai.com/u/jblake)\
**Post date:** [July 3, 2024, 4:21am UTC](https://community.openai.com/t/slow-stream-when-assistant-instructions-exceed-9-000-characters/851660/1 "2024-07-03T04:21:49Z")

</div>

When adding more than 9k characters there is a significant decrease in performance when returning as a Stream.  
Why does every event come back with redundant data such as the Assistants instructions or every past message? Seems excessive.

“request”: {  
“url”: “[https://api.openai.com/v1/assistants](https://api.openai.com/v1/assistants)”,  
“body”: {  
“model”: “gpt-4o”,  
“name”: “text\_91733”,  
“description”: “text\_91733”,  
“instructions”: "Hello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper API and get an audio response, but I noticed that this is the slowest part of the process. It takes around 2-3 seconds to process. Is there a way (like stream chat and stream audio) to make this iteration process faster with the API?\nHello! I am using CreateTranscriptionTextAsync to make STT - TTS with Whisper "  
}  
}