----------------------------- **While I generate an answer, here are some sources that might be helpful**: * [Launch Screen Assets]() * [Orchestration Models]() * [Glossary]() * [Web Calling]() -----------------------------

### Answer The issue you're experiencing with the agent stumbling over words or repeating sentences may be related to the

responseDelaySeconds

and

llmRequestDelaySeconds

settings in your assistant's configuration. These settings determine the timing of how quickly Vapi responds after user input and how long it waits after detecting a possible end of user speech before making a request to the LLM. You might consider adjusting these settings to see if it helps resolve the issue. Here's how the parameters work: - `responseDelaySeconds`: This sets the minimum number of seconds to wait after user speech before the assistant begins speaking. - `llmRequestDelaySeconds`: This sets the minimum number of seconds to wait after punctuation before sending a request to the LLM. If these delays are set too low, it might cause the assistant to respond prematurely or interpret quick, consecutive user inputs as separate commands, leading to repetition or overlapping speech. Here's an example of how you might adjust these settings:

json
{
  "responseDelaySeconds": 0.5,  // Increase if the assistant responds too quickly
  "llmRequestDelaySeconds": 0.2  // Increase if the assistant starts processing LLM requests prematurely
}

This adjustment can be made via the API or the Vapi dashboard under your assistant's configuration settings [(1)]() . If you continue to experience issues, it could be beneficial to look into the transcriber settings and ensure that it is correctly interpreting user speech, as errors here could also lead to repeated or garbled outputs. Make sure your transcriber is accurately configured with an appropriate model and settings for your use case.

@Saien | Exousia AI I'm sorry to hear that you're experiencing issues with the agent's speech. To address this, we might need to look into the specific configurations or settings you're using with GPT-4o. Could you please provide more details about how you have integrated GPT-4o with VAPI? This information will help me assist you more effectively.

You can continue this conversation by mentioning me in the message.

@Vapi the 'ask for help' button isn't working

----------------------------- **While I generate an answer, here are some sources that might be helpful**: * [Prompting Guide]() * [Inbound Support Example]() * [Voice Widget Example]() * [Call Forwarding]() -----------------------------

### Answer It seems like there might be an issue with the UI component on the platform you're using. Unfortunately, without specific details about how Vapi's UI elements like the 'ask for help' button are integrated and function within your environment, I can't provide a tailored solution. If you're encountering UI issues, it could be related to how the widget or assistant is embedded or how event listeners are set up for button interactions within your system. You might need to review the integration code and ensure that all elements are correctly configured and that the JavaScript managing these interactions is functioning as expected [(1)]() . For further assistance, you might want to inspect the browser's console for any error messages or warnings that could indicate what might be going wrong when the button is clicked. If the issue persists, checking the implementation against the Vapi documentation could help identify any discrepancies [(2)]() .

Definitely a major issue here

I noticed that this ticket says 'solved' but I'm still experiencing this issue

Hi, which channel will you make the post regarding this?

@Saien | Exousia AI check your interenet

I’ll send you an example in a bit

Here's the example: d4ea1560-4469-4dd3-b122-df23b79ba448 01:55

Okay this time it just completely stumbled: a535fab7-d804-4e43-b57f-fbf3288ce2fc 00:10

I think for this one, I should just remove the message the AI says during the function call via API (seems like it's only available for tools). update: I think I got it to be fine with some updated prompting but I'll confirm this later

But for this one, I don't think there's much I can do

So, for now marking it as complete.

Since we're only speaking on Tuesday, is there anything I can do in the meantime to resolve this?