Call ID: 019ab6e2-6a26-7ee4-ac7c-f273b25e750b There is an issue in this call where I noticed the AI agent would call the same tool twice at the same time, resulting in an error. I know the tool it is calling (Supabase Edge Function) is error free. Why is the tool getting called twice at the same time? Is there a way to prevent this? https://cdn.discordapp.com/attachments/1443658174413541446/1443658174631776406/image.png?ex=6929def2&is=69288d72&hm=ecab08dffd9067490393bfe933dc3a153eb4d7f0b51b87f4babb5715cc7cb66d& https://cdn.discordapp.com/attachments/1443658174413541446/1443658175093014631/image.png?ex=6929def2&is=69288d72&hm=1291cb81cb59cdbf84793ae2db1797a51fe877298665791e8c152d82c28ab368&

My scenario triggered 3 or more times when I make a change in my google sheet.

this issue im facing i was building this ai mock interview prep tool by watching the youtube video and im currently stuck with this error in VAPI please help me https://cdn.discordapp.com/attachments/1443616611767418900/1443616612275060837/WhatsApp_Image_2025-11-27_at_19.44.48_0fad3036.jpg?ex=6929b83d&is=692866bd&hm=64e55d63c40f7087ff33588af23c491170e74dd579054dc784fdb45a7ffa7276&

i am using the transfer call tool named " transfer_call_tool_demo" but my calls are not transfered at all. details:- SIP Call-Id: cfc8872f-463d-123f-d895-0ec7040a32ad vapi call id 019ac5a1-b3ce-7444-87b2-033e22baa1d1 I have selected the transfer mode as warm transfer but it is executing as cold transfer (refer screenshot) https://cdn.discordapp.com/attachments/1443608577066532944/1443608577389498440/Screenshot_2025-11-27_195312.png?ex=6929b0c1&is=69285f41&hm=416aa7e1beed37e5d67208cf974bb5c247c26544b9cc5865f95f8b66c84bb11a&

hello, i keep having this problem when using the vapi knowledge tool. the query tool is configured correctly- it has descriptions and knowledge bases with uploaded files, the assistant has that tool assigned, and the prompt specifies that that tool should be called when asking specific questions. any feedback please? https://cdn.discordapp.com/attachments/1443601265102950472/1443601265409003561/Screenshot_2025-11-27_at_15.51.05.png?ex=6929a9f2&is=69285872&hm=14953b33590505007b668a0e0953e128274437aebf3fc4b335038bde7d3ff9f4&

When adding a new endcall node and set a message my node server.credentialId gets "" and I can't save it. Same when I'm editing an exisiting endcall node message I can't save it anymore because of this error.

Hi everyone, I’m having an issue with outbound calls and hoping someone can help or share insights. On 25–26 Nov 2025, almost all calls made through Vapi using our Telnyx SIP numbers were answered by a “bot”, but the recipients didn’t actually receive any calls. I tested with my own number — I didn’t get anything, but Vapi logs show the call was “bot-answered” for about 6 minutes, and it charged around $0.40. What’s strange is: Everything worked normally before that It only happens with Telnyx SIP numbers Our Twilio number works fine Has anyone experienced something like this? Could this be a Telnyx routing issue or something on the Vapi side?

I have an old phone number from Telnyx and for some reason the caller ID for my new number keeps using the old one. I recreated the SIP trunk connection twice now What causes the issue, why is my caller ID still the old number?

We have noticed that for the last one month, Call recordings for most of our calls are missing. We have integrated S3 for storage on VAPI. Some calls have all recordings, some has only stereo, some has mono and none for some calls. Call id - 019ab494-b876-711c-bf06-fd1507b8aafa - Has no recordings data Call id - 019ab4e4-9e98-722d-84ba-05c7a82cfb30 - Has stereo Due to this issue, Call recording url is missing from VAPI /call/:callid endpoint response. We have not changed any config or code from our side since last 2 months. Please provide some solution for the above issue. Also is there a way to retrieve the missing call recordings.

Dear Team, Campaigns wont support transient assistants or squads? I dont see it in documentation.

Question: I'm implementing call transfer functionality for inbound calls using the assistant-request webhook. When I include a transferCall tool in my assistant configuration response, the call fails with "Couldn't get assistant" error. Without the tool, the assistant works perfectly. My Setup: - Using assistant-request webhook to dynamically create assistants for inbound calls - Assistant configuration works fine WITHOUT tools - Adding transferCall tool causes immediate failure Current Implementation (FAILING): { assistant: { name: "assistant", firstMessage: "Hello...", model: { provider: "openai", model: "gpt-4o", temperature: 0.5, messages: [ { role: "system", content: "You are an assistant. If the caller asks to speak to a human, use the transferCall function to transfer them." } ], tools: [ { type: "transferCall", destinations: [ { type: "number", number: "+1xxxxxxxxxx" } ] } ] }, voice: { ... }, transcriber: { ... }, endCallFunctionEnabled: true, clientMessages: ["transcript", "hang", "function-call", "speech-update", "metadata", "transfer-update", "conversation-update"], serverMessages: ["end-of-call-report", "status-update", "hang"], phoneCallProviderBypassEnabled: false } } What I've tried: 1. Adding function, parameters, and messages fields to the tool → Still fails 2. Setting phoneCallProviderBypassEnabled: false → Still fails 3. Removing "function-call" from serverMessages → Still fails 4. Various tool structure combinations based on docs → All fail 5. Minimal structure (just type and destinations) → Still fails

I'm trying to get the end-of-call-report webhook to fire but it's not coming through to my server. I've set up the serverUrl in the Advanced tab and enabled the message type in serverMessages. Other events like transcript and conversation-update work fine. Just the end-of-call-report never arrives. Has anyone else run into this? Is there a specific order these need to be configured or does the call need to end in a certain way for the report to send?

Hi - has anyone used transient assistants in a way which avoids exposing the prompts & config to the web browser? For example - Ambr uses VAPI in a way where you can just go to dev tools and see what prompts are driving it. For many uses cases including mine it is not appropriate to leak the prompts in the way. And yet we need transient assistants (I assume) because the details of the configuration and prompts will differ on each use case. How can you change core prompts for voice agents on each use, without exposing prompts to the web browser?

My GHL connection is not working! https://cdn.discordapp.com/attachments/1443410806082371725/1443410806367715562/Screenshot_2025-11-27_061326.png?ex=6928f891&is=6927a711&hm=8613b26eaa1908d5ffae74dcceca7242abdece99599c41ec93d1b517f4a1b405&

I am trying to use an MCP Tool with both Oauth and Bearer token Credentials. When I configure Oauth I can see the token endpoint is called on the server to obtain an access token. However, neither the bearer token or access token are presented to the MCP server when the Tool is invoked from an Assistant. I can see the VAPI MCP client / POST: 2025/11/26 14:24:22 Request Body: {"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{"tools":{},"prompts":{},"resources":{}},"clientInfo":{"name":"vapi-mcp-client","version":"1.0.0"}},"jsonrpc":"2.0","id":0} This results in a 401 with the "Www-Authenticate:[Bearer realm="mcp" resource_metadata=https://mudflap-pete.ngrok.io/.well-known/oauth-protected-resource]" response header which should tell the client to proceed with token The assistant is https://dashboard.vapi.ai/assistants/426f0625-c597-47af-9fe6-e139b5df43b4

Is there a way to get the customer’s phone number in the assistant’s built-in analysis prompt? I tried using

{{phoneNumber}}

but it didn't work.

Is there any way to use Structured Data inside the Structured Output?

Hi Team, ListenURL and ControlURL have stopped coming in get call output. I am sure everyone who uses this would be facing this issue. Thanks, Karun

im not able to make the google calendar work with vapi , can someone help

Call ID: 019ac138-e4c0-7556-baeb-ea9dd6a7d7f8 Org ID: 14d31e07-98c4-4f99-aefd-4d35ed5baa80 Can we figure out why voicemails are not being left? I have : voicemailDetection: { provider: 'vapi', }, When making the calls

Hey guys, i having an issue when integrating my custom transcriber Yandex, to Vapi. The problem, Yandex apparently doesn't support 2 channels, it is mono. So i am splitting two channels into two individual STT streaming session to Yandex. I am not sure if this is the right approach. Plus, Yandex doesn't even provide SDK for streaming, it onyl offers v2 gRPS streaming single channel and v3. This is means that i am entitled to control the channels. I couldn't figure out, how to stop the spill over of audio. What I mean by that: when assistant is speaking it is audio is continiously is being trancsribed, but at that moment if customer starts speaking as well, my server can't distinguish it, so yandex will send a one giant mixed transcript. Well, the expected behavior for me is, agent should stop if user interrupts the agent, well since my TTS also going to be Yandex, i can cut the TTS and silence agent channel, whenever i detect energy increase in customer channel, but that doesn't stop the Vapi agent's LLM, this can lead to inconsistency between the understanding of the user and agent. Please any of guys have a solution to this, help me!

I configured Vapi with my own sip trunk (asterisk based). When I create an outbound call with vapi.. I get a call_id in return. I'd like to match that call in asterisk, but I cannot find a way to do it. VAPI seems to send a Call-Sid header but it's a different value than the call_id I get when creating the object.

I have a warm transfer set up. It introduces the customer to an advisor, with the customer name and a brief summary of the call. It should then finish the transfer with "transferring you to {{customer.name}} now" so that the last thing the advisor hears is the customer's name. However this doesn't work, it simply says "transferring you to now". Can you tell me what is wrong? { "function": { "name": "scheduleCallbackTransfer" }, "destinations": [ { "type": "number", "number": "+441234567", "transferPlan": { "mode": "warm-transfer-experimental", "transferAssistant": { "firstMessage": "Hi, I have a customer on the line. Can I take your name please?", "firstMessageMode": "assistant-speaks-first", "maxDurationSeconds": 90, "silenceTimeoutSeconds": 30, "model": { "provider": "openai", "model": "gpt-4o", "messages": [ { "role": "system", "content": "You are a transfer assistant. After the greeting, say: 'This is a lead from Company Name. The lead’s name is {{customer.name}}.' Then give a one-sentence summary of the call (e.g., debt level or issue, make sure you include the customer name). Wait for confirmation. Only if the advisor agrees, say: 'Transferring you to {{customer.name}} now.' and call the transferSuccessful tool. If the advisor is unavailable or declines, call transferCancel." } ], "tools": [ { "type": "transferSuccessful", "function": { "name": "transferSuccessful" }, "messages": [ { "type": "request-start", "content": "Transferring you to{{customer.name}} now." } ] }, { "type": "transferCancel", "function": { "name": "transferCancel" }, "messages": [ { "type": "request-complete", "content": "Returning to the assistant to schedule a callback."

Call-ID: 019ac00d-e0a2-7dd8-8f66-bd69662339bc Account email: amin+vapi@tavan.se I followed this call while is was running. It was a longer call (25-28min) and when it was ended this was the results. I do not want to loose the transcripts, voice-recording etc. Is it possible to get this?

In the dashboard, I can see usage by minutes whereas topup is using credits. How would I know how many credits I have used based on the minutes?

Hello team I am facing issue in every assistant in webhook getting end of call report two times which is causing issue for me Assistant id - 34c92e26-aa44-4038-933d-e7c678c8238f call id - 019abfe1-5034-711c-aa67-f1dfd5fefee1

Hello! After more than one month working without problems, now Deepgram Voices are not working and the calls are failing. This is a stable feature and breaking this functionality affects a lot of production workflows, of course, I am working in the Weekly cluster. Please, could you take a look and make sure this kind of errors doesn´t happen again? I send you two Call IDs in case you need it: 019abf2f-04e4-7dde-9123-4e0facc82cad 019abf32-ac24-7881-9e79-18e5ec623c30 Thanks! https://cdn.discordapp.com/attachments/1443187692497277098/1443187692815781898/image.png?ex=692828c7&is=6926d747&hm=616279795cf767e596aaa85e101779c095f385a384c9ec6f2e4b68b4d3dd2e9e& https://cdn.discordapp.com/attachments/1443187692497277098/1443187693595918456/image.png?ex=692828c7&is=6926d747&hm=93e4fb1ac7f5e6d84367e516995fd403e4347d7188df5e2750a0a3b92a904a37&

I tired to do 2 calls at the same time (make.com API Call), but only one goes through. I use a twilio imported number - so I think 10 calls should be possible at the same time. How can I make sure that I can do 2-10 calls at the same time? Thanks!

We are trying to understand the following error:

An error occurred in this call: call.start.error-get-transport

which only seems to occur when calling out to US numbers. This is using Twillio provider and there are no logs on their end for this seemingly. Sample Call ID: 019abf62-8bf8-711c-aa30-365ab1305709 Org ID: a266008d-460f-4c11-8a96-1fc935391154 Timestamp: 2025-11-26T08:58:17.976Z

Can someone from the vapi team help in this, everyday our organisation assistants and squads settings are been changed by someone either it's someone from your team who's doing all this or either there are too many bugs in your platform. Everyday the assistants llm stt tts models are being changed automatically and are being set to other same goes for the squads also there are overrides present there which we never setted there if we change them vapi is not letting it to save don't know is happening in the dashboard can someone from the team help in this.