Vapi is the Voice AI platform for developers.

Vapi AI

I’ve ran into the issue quite a few times where my assistant keeps sending a request to my API endpoint before the call ends. Does this issue stem from the prompt? Or something in the settings I have to tweak?

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

<@451806721011220481>
It sounds like there might be an issue with how the assistant is handling the timing of the API requests. This could be due to the way the prompts are structured or a setting that needs adjustment. To better assist you, could you provide more details about when the assistant is triggering the API requests? Is it supposed to wait for a specific event or user input before sending the request? Additionally, knowing if there are any conditions or triggers set within your code that might be causing premature requests would be helpful.

<@451806721011220481> please share the call id.

please try chaning your voice provider, to cartesia because HGreg is captured as Aish and then later somehow recognised as end of call phrase.