Agent is repeating itself
# support
r
Hi. As of yesterday (or at least at the point we noticed it), our voice agent has been having issues with repeating itself. It is now happening rather consistently at least once within the call experience. Here is a sample from today: Call ID: 9d2a8e2f-7e8e-4ee3-8d96-86dbdfae35b6 This occurs at about the 9 minute mark: AI Nice dot nice So Mike logs into the VAPI interface. Nice. So Mike logs into the VAPI interface, which is the conversational AI platform. And then makes the model change for that specific phone number. Nice. So Mike logs into the Vappy interface, which is the conversational AI platform. And then makes the model change for that specific phone number he's testing on. After you make that change in VAPI Nice so Mike logs into the VAPI interface which is the conversational AI platform, and then makes the model change for that specific phone number he's testing on. After you make that change in VAPI, do you need to save it? Or does it take effect immediately? Nice. So Mike logs into the Vappy interface, which is the conversational AI platform. And then makes the model change for that specific phone number he's testing on. After you make that change in VAPI, do you need to save it does it take effect immediately? And then what's your next step? Here is the combo used for this call: Model - Claude Sonnet 4 Voice - OpenAI, Alloy Transcriber - Deepgram Nova 3
j
echo - seeing same issue with claude/deepgram nova 3/elevenlabs stack
c
Hey RVRWRK, I sincerely apologize for the delay in our responses this week. We experimented with some process adjustments that didn’t work as intended, and unfortunately, this caused some disruptions. That’s entirely my responsibility. Just a quick note—our team is unavailable on weekends. However, if something urgent or critical comes up, feel free to reach out to me directly, and I’ll assist you. The support issues will be resolved in the coming weeks, and starting Monday, you can expect more consistent and improved support. Thank you so much for your patience and for continuing to stick with us!
r
Ok. Thank you. We'll look for a direct reply to the reported issue at the start of the week.
c
Hey, thanks for sharing your details. Our team will look into it and get back to you soon with an update.
r
Ok - thanks Praveen -- please let me know. Specifically, I'd like to know which componet failed... we've been using the VAPI voice and havent had issue since switching, but we'd like to also leverage eleven labs / openaI voices if possible. my sense is that it was on the voice side... but i'd also like to know if the issue was elsewhere - on the openAI or Anthropic side of the prompting.
If something is misbehaving... I need to be able to swap it out quickly to not interrupt service while I wait for your support here. To be honest... support here is taking a really long time and we can't afford to wait. So, we at least need to know what we can adjust on our end in the meantime. As an FYI, everything we are currently doing is through the VAPI UI. We haven't dived into configing things programmitically yet.
c
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
r
Thanks for all the apologies about response time, but we really just need an answer to the question. We've been patient, but it's been almost two weeks and no one has directly addressed our question. We decided to move on from our last provider because the support response was so terrible. We're here now and we'd like to stay here growing with you.
By the way... we're over 1,000 minutes a month currently and we expect this will be accelerating over the next few months.
How do we apply / receive the "prioritized support"?
c
To receive prioritized support, you can upgrade your plan through your account settings. Once upgraded, you'll automatically gain access to prioritized support. If you need help with the upgrade process, just let me know.
2 Views