Hi VAPI team, We have 2 weird call logs that I can still see the recording is usual but the analisys and data extract and transcription is all empty. callIds: a3b7b68d-846a-490d-9212-584961a38ddb 126a3d33-dcfb-44d9-a3e0-b6cb5509064d 1 more thing, when the event return endReason, can we consider that at that moment, the call is ended even the event of completed has not been sent yet? Thank you. Vinh.

Increasing

silenceTimeoutSeconds

, lowering

confidenceThreshold

, ensuring assistant responses are played, and checking audio permissions and browser compatibility..

hi thank you for your feedback. here are more sample callId, the customer voice is pretty clear when I listen to, but AI did not answer. af495ac3-14b4-4f1d-9dfb-dffb8472397d c81446cd-6861-4f4d-9e94-8e867a2778c2 4aa98b92-a005-4b72-a59d-fc99c745d4e9 be59b2bc-85ce-4227-bfb1-e52fc5680db6 I think there should be at least the log should have the 1st message when the bot talking? Please help take a look. And where can I configure this " ensuring assistant responses are played" ?

Hey Vinh, Thanks for reaching out! We're currently swamped with a bunch of tickets and it's taking us longer than usual to get back to everyone. I know waiting isn't fun, but we want to make sure we give your issue the attention it deserves rather than rushing through it. We'll circle back with you soon to get this sorted out.

hi @Shubham Bajaj yeah thank you. here is another callId this morning: 4e02fe64-cd43-4f27-bd14-01fd641283a7 you can see the sound is loud enough, I also set the assistant to answer in case it detect if there is no response from the customer. but when u are listening to the recording, it sounds like to me VAPI cannot detect the customer's voice/transcription, that's why it doesn't response until it speak the Idle Messages. there are many calls like that which made our customers confuse :(.

Hey Vinh, 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!

hi any updates?

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

yes I till need support on this ticket

Could you try using "assistant-speaks-first" instead of using the "assistant-speaks-first-with-model-generated-message" for assistant's firstMessageMode? I would like to see the logs for a call with that setting as well.

hey let us try

How different? If you need to include variables like {{customer.name}} or similar you can replace those. You can also do the same with assistantOverrides.variableValues to pass something specific to the user before the call starts. All of these configurations can use

assistant-speaks-first

I think we have an assistant that configured assistant-speaks-first, let me find if there is any sample.