My client has 10k leads that he want to call, so if we use any calling provider like VAPI RETELL OR ELEVENLABS do we need to do any kind of KYC there?

Hi everyone, I’m facing a blocking issue with a tool call + webhook flow and I hope someone can point me in the right direction. The problem is: My Vapi agent answers BEFORE the webhook response arrives from N8N, even though the tool is correctly triggered. Here is the sequence: The tool (Check_Availability) is triggered normally. N8N receives the toolCallId and starts processing the workflow. Before N8N finishes and sends back the JSON response, the agent already replies on its own with something generic like “The time is available” or simply continues the conversation. When N8N finally returns the correct JSON, Vapi logs show "result": "Success" instead of the actual message I returned. Here is the JSON I send back from the webhook: { "results": [ { "toolCallId": "call_7IAFqr0iUuzRxhoom52Qdiq5b", "result": "The requested time at 9 AM is not available, but 10 AM or 11 AM on the same day are available." } ] } • Using “Respond With: JSON” • No newlines • toolCallId is correct • Webhook returns instantly when tested manually • But during real calls, Vapi replies before receiving the webhook result My question is: Why is the agent not waiting for the webhook response, and how can I force Vapi to wait for the tool result before answering? Any idea what might cause this? Thanks a lot to anyone who can help!

Hey guys I have a person saying to build an AI outbound voice agent at a one time fees but they might use it to call people without consent although told them several times that it's not legal they said they want risk but also said it should sound like human and not mention it's AI, so as a developer do I also have some risk if they get caught or no risk if do it with proper contract by transferring full ownership and also they live in US and I live outside of US

Hi all, and thanks Azim for your great content and group. I've secured my first voice client and looking ahead. Retell allows 20 concurrent calls and 10 knowledge bases for free. As i continue to add clients, would it be better to create an account for each client, or pay for more concurrencies / knowledge bases as needed? thank you!

Hi all, I am very new to all this, but have been learning over the past week, and it has taken my interest profusely. I am trying to build an n8n workflow that works alongside Vapi AI and the scheduling program Cliniko for a clinic, as I have warm leads. It appears that when I try to test-run the workflow, it is assuming the patient is new and goes to create a new patient node almost instantly. I have tried on VAPI to add in tools/ functions that tell the AI not to call the workflow before gathering all the required info, but it didn't seem to work. I was just wondering if anyone can see a simple mistake or can provide me with any constructive criticism, as any help on this would be greatly appreciated. If any additional information of how it is currently set up is required in order to help. Let me know and I will see what I can do. Super excited to progress in this journey.