V
VAPI
Vapi helps developers build, test, and deploy voice agents at scale. We enable everything in between the raw models and production, including telephony, test suites, and real-time analytics.
JoinV
VAPI
Vapi helps developers build, test, and deploy voice agents at scale. We enable everything in between the raw models and production, including telephony, test suites, and real-time analytics.
JoinNot able to set tool to async
curl -Method Post "https://api.vapi.ai/tool"
-Headers @{
"Content-Type" = "application/json"
"Authorization" = "my-auth-id"
} ...Agent not picking up variables
Hi VAPI team,
I'm trying to make this agent reads the First message with 1 variable
"Hi, thank you for calling {{orgName}}" ...
call.start.error-get-transport
Hello Please Help !
I am getting issue when I call customers through twillo number
the issue : "call.start.error-get-transport"
...
Bug report: Custom LLM appends /chat/completions to whatever URL you specify
When using custom LLM implementation, whatever URL you provide will end up as URL + "/chat/completions".
VAPI should not alter this URL you should use the URL as is without modification....
call.start.error-get-transport
Hi team,
I'm setting up an outbound calling flow with a Twilio phone number connected to VAPI, but every outbound call fails instantly with this error:
call.start.error-get-transport...
Webhook not working when I make outbound call.
So I use make to make certain calls outbound and when I do the data from the call doesn’t send to the url in the messaging - server url it used to work but no longer. So I use an https request in make to use vapi to make a call but after a call I never see the webhook or server irk sending the data. Also in the webhook section of vapi it gives me one day and the screen is t scrollable, how can I test when your system won’t give me data anymore, if I make a manual outbound call in your system...
All ORGs disappeared from our account yesterday (17:00 GMT)
We are unable to view any of our orgs in the VAPI dashboard. More importantly we are also unable to make any calls via these orgs. We keep getting "unauthenticated" errors. All fo these ORGs have been making calls up to this point. Some of the ORGs have been in place for more than 6 months without issue. What has happened!? I have emailed support but heard nothing back! This is critical for us.
Server URL Call-Ended
Configuring my serverURL using a custom webhook via make, but it triggered every second of the call. How do I change this so it only triggers my webhook for the Call-Ended event?
Does Custom LLM support streaming?
I'd like to send an initial "working on it" message back to the user, then call our LLM to generate text. Is this possible? It looks liek you have to return the entire response
Urgent: I can't sign in. It's not a wrong password issue
Hello, I need urgent support. When I attempt to login, the CTA keeps loading and resets. I urgently need to access the system, please help. My ID is diat@remoteoffice.io
Is there any way to play some holdtime music while vapi agent is waiting for a tool to return data?
Is there any way to play some hold time music so that the customer who is waiting doesnt disconnect since there would be silence while the agent is waiting for the data.
Random weird noise after tool
My callid 019adaf3-c04f-7ff3-a41a-acd5d33b7125 played random weird noise at 4:03 second mark. I noticed the agent had called my make.com webhook which returned fetcherror but why did the agent voice go all haywire? It should be able to still continue conversation ?
Warm Transfer Issue
I need help with sending a custom “reason” message during a warm transfer using the Transfer Call tool in Vapi.
Right now, the warm transfer works only when I hard-code the reason inside the tool itself. Instead, I want the assistant to first ask the caller for the reason, then pass that collected reason to the destination number before connecting the call.
Is there a way to dynamically send this custom reason from the assistant to the warm transfer?...
How do you track / improve call quality?
How do you track / improve call quality? We have over 80% fail rate
simultaneous outbound calls
Hello Vapi Support Team,
I would like to know if there is a native setting in Vapi to:
- Limit the number of simultaneous outbound calls (for example, launching calls 3 at a time only),...
do we need to do any verifications to make outbound calls? like 10k calls?
do i need to do any verifications to make ai outbound calls?
Very slow and robotic voices
Dear folks, I often have the problem of “very slow and robotic voices” here. After a certain point, the voice becomes completely distorted. there is no clear pattern when this happens. Sometimes 10 calls everyhing is fine and sometimes I have 5 calls in a row where this happens.
Model used: GPT5 oder 5.1
Transscriber: Deepgram or AssemblyAI is used as the transcriber. The agents’ language is German.
Voices: 11labs or Cartesia...
Issue with VAPI agent constantly saying unable to check calendar and actually book appointments
Hey so I’ve connected my GHl to Vapi, put the 4 tools on to the agent, given the calendar ID from GHl into the calendar tools and put the recommend part of the prompt from the integration support, but anytime my agent calls it constantly says unable to access the calendar or says it’s booked calls at random times but never does, I’m not sure the contact part is working now with no real way to know
Here’s some of my call IDs
019ae03b-5e50-7555-be85-12968f76fcfe...