Hello, We’ve been frequently receiving the following error in recent days. As you can see in the attached image, our backend is responding in under 1.6 seconds. However, we are getting the assistant-error event even before our backend sends its response. Could you please take a look? Here are some call IDs for reference: - 022fe55e-5113-48d2-aced-65170806fa56 Thank you, https://cdn.discordapp.com/attachments/1392183471748808857/1392183472038084659/image.png?ex=686e9b65&is=686d49e5&hm=48ca084e13164a100894245a599a54b7d9cc9bb3045ba4467fac23a57165b6b6&

Hey, thanks for the info. We're looking into this and will get back to you with an update soon.

Thank you

Lopping in @shubham @kyle

thank you Praveen

Hi @David Jurado , I've sent you the call logs for these three call_ids, along with the assistant-request response and its duration. Please take a look at your server; logs it's not responding in the required time. For fair consideration, you can share your side of the logs as well.

hello @Shubham Bajaj As you can see in the images, we've included the logs from our backend showing how we receive the status-update request with assistant-request-returned-error. In both cases, the time difference between the first assistant-request event and the status-update is less than 7.5 seconds.

Hey David Jurado, I wanted to let you know that we're managing a high volume of support requests at the moment, so our response time might be a bit slower than usual. I truly appreciate your understanding and will get back to you as soon as possible!  Thanks again for your patience!

Thank you

Hey David, I’m really sorry for the delay. It’s taking longer than we expected, but our team is looking into it and will get back to you with an update soon.

thank you!

Hi, First off, we want to sincerely apologize for the delay in getting back to you. We understand how frustrating it is to wait - especially when you're counting on us - and we owe you a clear explanation of what’s been happening and how we’re addressing it. Over the past few weeks, we've seen a significant increase in support requests. While this reflects exciting growth, it has also stretched our small team and exposed some real challenges in scaling our support operations. To improve your experience, we’ve taken a step back to reassess our approach. Here’s what we’re implementing: - Smarter Support Through Automation: We’re investing in our AI support systems to help you resolve issues more efficiently. Soon, our support bot will offer expanded capabilities, making it easier to access accurate, instant help—particularly for common or repetitive queries. - Expanding the Support Team: To meet growing demand, we’re adding 2–3 new team members focused on managing support volume and improving response times. - Prioritized SLAs for High-Usage Accounts: We’re introducing service level improvements for users who are growing with us: - Accounts with usage over 1,000 minutes/month will receive prioritized support. - For all general inquiries, we’re establishing a standardized 48-hour response time. We’re confident these steps will lead to faster, more reliable support and help us better serve you as you grow with us. Also, in case you still need help with this ongoing ticket, do let us know, and we will help you get this resolved as soon as possible. Thank you for your continued patience and for being part of our journey. Warm regards, Vapi Team

hello, we still need help with this ticket. Thank you

If you are running these servers in Europe and doing the tests locally, you will have a lower latency naturally. Since Vapi servers are mostly located in the US, that distance alone will add some latency. Please try adjusting the timeout to at least 15000ms to see if it helps and if not we can work from there

Hello, our system is currently in production, hosted on a Google Cloud server in Europe. I don’t understand how we can adjust the timeout to at least 15,000ms. We are sending you the response in 2 seconds, and the latency between Europe and the US is low. Is there any parameter in the assistant to configure this? These are phone calls, not web calls.

Here is the documentation for configuring the server.timeoutSeconds property of your assistant -->

ok thank you, but it is a assistant-request. Is it work for this case?

Sorry for the delayed response. We recently deployed an update last night that could help with this issue. Could you please try a couple test calls and see if it improves?

here are two examples 4b03edac-dfb5-4e22-9525-6d28ebc77c0b, ad60061c-9650-418d-9cc9-a91d2d2fb847

We sincerely apologize for the delay in getting back to you. Your request has been waiting longer than we would ever want, and we understand how frustrating that can be. Over the past weeks, we’ve reorganized our support operations internally to handle requests more effectively. Alongside this, we are implementing new policies and procedures designed to speed up response times and improve overall support quality. If you are still experiencing issues with your original request, please let us know so we can continue where we last left off and resolve it as quickly as possible. We appreciate your patience as these improvements take effect, and we’re committed to providing you with the level of service you deserve.

hello, we still need support with this issue. Thank you

We apologize this issue is still dragging along. Because of our data retention policy could you please send a recent call id so we can review the logs? Hopefully the response time is still low for your server like it was last time.

it's ok, you can close this ticket