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.

Attached Snap for your refrances https://cdn.discordapp.com/attachments/1443160233961848903/1443160234225958995/image.png?ex=69280f34&is=6926bdb4&hm=3e6aa38950e5d4b565feb6b02fddbcfebc9ba353ec15085c0e61b3a5bbeccf3c&

Hey everyone, I could use some help with the GoHighLevel integration. I’ve fully connected GHL to Vapi (green checkmark under Settings → Integrations), and I’ve verified: I’m using a location-level API key My calendars in GHL are active, bookable, have open availability, and I can book using the public links The correct calendar IDs are set inside all the Vapi tools All calendar check + calendar create tools are toggled on for my assistant Despite all that, my Vapi assistant still reports no availability, or fails to actually book a time, even though the calendars clearly have open slots. In the Vapi call logs, the calendar tools sometimes return empty availability or unexpected errors—even though the corresponding GHL calendars show free times. My question: Is there anything additional required for the GHL calendar tools to read availability or create events beyond: connecting GHL through Integrations, adding the location-level API key, and mapping the correct calendar IDs in the tools? Also, is there anything that could prevent availability from being returned even when the GHL booking page shows free slots? Any guidance would be super appreciated! Thanks!

Hi, Outbound calls via api https://api.vapi.ai/call are queuing and work ok when calling Australian numbers, but no call is ever received when trying New Zealand numbers. Vapi API logs show OK with queued, but in the call logs you can see errror: "An error occurred in this call: call.start.error-get-transport" Twilio logs don't show any fails or errors either for the calls that don't work.

Org ID: 62c50b68-c08c-4ab3-bbe4-6c52392d0e66

Bot ID: 4f05c4e1-b487-4aec-92f8-c5cc29736b8c

Phone ID: ddea8baf-7d2c-429e-92b5-8cee93be94d0

Sample call IDs that failed:

019abdb2-02a4-7991-92ca-9d3562463819

019abda7-2085-7773-92de-19900f7ff464

019abda3-907d-799a-b12a-7d4be700f58e

Sample call IDs that succeeded (to Aus numbers):

019abdb1-bb57-7dd3-8fd6-c191824d6043

019abda3-41c7-7aa3-91de-9f88d7d9b094

Any help greatly appreciated.

https://discord.com/channels/1211482211119796234/1401909002442641588/1401909002442641588 @snikulin reopening ticket here

I'm not sure how this happens but when I enter my twilio phone number into vappy says it's being used by another organization

Building VoicePharma AI for Quebec pharmacies - need to discuss Loi 25 compliance partnership. Loi 25 (Quebec's GDPR) requirements for healthcare: - Canadian data residency for PHI - AI/recording disclosure + consent - Right to human transfer anytime - Healthcare-grade security Key Questions: 1. Can VAPI guarantee Canadian data residency for calls, transcriptions, recordings? 2. Do you offer BAA/healthcare compliance tier? 3. Can I store recordings in Canada or handle them myself? 4. Any Quebec/Canadian healthcare customers to connect with? Market Opportunity: - 1,900+ independent Quebec pharmacies - Legal French service requirement - Zero competitors with fr-CA + Loi 25 compliance Current Setup: Robin (fr-CA-ThierryNeural, Azure transcriber fr-CA) Use case: Rx refills, nurse bookings, pharmacist consultations Looking to partner with VAPI to break into Quebec healthcare. Happy to connect with compliance/enterprise team. Talha | talha@theaiclubhouse.com

Is this functionality even working ? with clean assistant and added files to model it never uses them. Adding prompts to reference knowledge base always results in : Cannot read properties of undefined (reading 'message')

This started today. Or I noticed it today anyway but the authentication is not working. I goes through its cycle but won't authenticate. I tried in Incognito browser as well. A few days ago it worked fin with the same agency different sub account but now nothings working . Thanks!

I havea sip proxy/server, it's possible to connecte vapi on my VOIP server ? i dont understand how it's work thanks for your help

I am serioulsy frustrated with this platform and the bugs with it... I am trying to call an api tool that has path parameter Example [GET] https://api.test.com/{{someVar}}/resource now, this variable is passed in to the squad and squad is using an agent that uses this tool.... the damn path parameter is just not getting filled... I tested this with Agent, it works... i test it with Workflow it works... but it doesnt work with squad... Worklist is not recommend to use by Vapi... and Agent is bloated... that the hell do i do here?

Vapi is lagging on the call, agent cuts out. Is there something we need to do on our end?

Hello, as we all know, GPT 5 has been pretty bad for vapi, but how are the two new 5.1 models? Are they any good? I'm also curious to know if the latency times are correct, 5.1 instant is just as fast as plain 5.1. It also has the exact same specs. Any noticable difference there?

I've previously been using 'experimental' warm transfer but it doesnt work 100% of the time. So I'm trying the TWIML method. I have it working speaking a message "this is a call from company, the customer is called..." and at this point I want it to say the customer name. I've used {{customer.name}} but it reads out "customer name". Is this possible and if so how? The same with call transcript/summary. On the other call transfer methods the options to create the summary plan are there, but it doesn't show on the TWIML configuration.

I'm trying to figure out why, for the transcript, the LLM output is sent to the speech-to-text. Why not just directly send me the LLM output? Is this a setting I can configure? We're building out a third-party web widget that's pulling in the transcript, and it's taking it from the speech-to-text. It would be better to just give us the exact LLM output, and I can't figure out how to just get that exactly, the actual LLM output. So I could put that into my transcript for the user.

I am using the VAPI Dashboard on MACBOOK in Browser CHATGPT ATLAS and it is lagging like crazy.

Everybody's seen all of the post. With this error I've tried everything that you've mentioned. Created the new API keys, cleared the cache, did a hard reset. Still nothing. I see multiple people with this error and it's gone unresolved. Can anybody help here?

Is it possible to update the assistant system prompt during a call? Do dynamic variables get updated every turn of the conversation? Thanks!

Hello! I'm following the Live Call Control docs at https://docs.vapi.ai/calls/call-features , but I don't see any monitor object being returned after I create the call. Am I missing something? Or perhaps I'm not on the right Vapi tier?

Details: I am creating a recruitment bot using Gemini-Flash 2.5 and VAPI. During the conversation, it keeps breaking with the error shown in the attachment. It has been two days and I still haven’t been able to resolve it. With Gemini-Flash 2.0, it works well. Call ID: 019abb65-1aa5-788e-b615-f786b2e7a538 time: 1764081022769 Response Expected: Next set of question Error: Please see attached. Console error is pasted below: could not emit {action: 'error', errorMsg: 'Meeting has ended', error: {…}, callClientId: '17640821643690.5208472250220907'}action: "error"callClientId: "17640821643690.5208472250220907"error: details: undefinedmsg: "Meeting has ended"type: "ejected"[[Prototype]]: ObjecterrorMsg: "Meeting has ended"[[Prototype]]: Object Error: Unhandled error. (undefined) at Y.emit (index.js:38:16915) at gu.emit (index.js:38:44170) at r. (index.js:38:48219) at i.emit (index.js:2:4192) at r.value (index.js:30:33247) at r.value (index.js:30:27805) at o (index.js:22:16504) https://cdn.discordapp.com/attachments/1442895592731705437/1442895593084031078/vapi.png?ex=692718bd&is=6925c73d&hm=4d13dd553594e131de6b53bb40f7a5d91168ad7a490e2239ed15931fdd785e7a&

Hey everyone, I have connected a Twilio number in Vapi and am receiving incoming calls, but the call log still shows the inbound call with Assistant = “No Assistant Assigned” even though the assistant is set in the phone number settings. Info: Org: Twilio number: +41 43 505 10 54 Assistant name: Demo Inbound settings in the dashboard: Inbound phone number = +41435051054, Assistant = Demo Twilio: “A call comes in” → Webhook https://api.vapi.ai/twilio/inbound_call (HTTP status 201 in the Twilio call log) In Vapi calls, I see my call as Type = Inbound, but the ASSISTANT column says “No Assistant Assigned.” When I test the same assistant directly via “Web Call” in the dashboard, everything works (call log then correctly shows Assistant = Demo). Can you please check whether there are multiple PhoneNumber objects for my Twilio number, or why the inbound handler does not link the number to the assistant even though it is set in the inbound settings? Relevant call IDs from your log: 019a87ae-ea68-7773-aa33-fc1adeafe44b Thank you & best regards, Silvio https://cdn.discordapp.com/attachments/1442893938225713234/1442893938565578772/4a986c99-908c-44d4-97f8-51673d6c4493.png?ex=69271732&is=6925c5b2&hm=60e978bdb50d9ddffafde2e12f4f651ddb546e369f8da8bf6db4eefb97d50142&