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.

Join

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.

Join

support

faq

fuzzy-lavender

12/4/2025

How do you track / improve call quality?

How do you track / improve call quality? We have over 80% fail rate

rival-black

12/4/2025

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),...

genetic-orange

12/4/2025

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?

yelping-magenta

12/4/2025

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...

sensitive-blue

12/4/2025

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...

fair-rose

12/4/2025

URGENT: Cant save any workflow with API Request

No matter what, even in a new, otherwise empty workflow it says: Save Failed / Failed to save workflow: each value in nodes.tool.server.cerdentialId must be a UUID. Even working systems i cant save any changes on....

exotic-emerald

12/4/2025

problems with connecting GHL MCP

I am having problems while connecting the gohighlevel to my vapi dahsboard, it takes me to the marketplace and makes me login to my ghl account then i select the sub-account then redirects me to the same integrations page and still not connected, is there somthing i missed?

stormy-gold

12/4/2025

Telnyx Latency IS CRAZY.. what went wrong?

Recently i bought a number from Telnyx, and just like Vonage and Twillio i added the number just by connecting the api and after wards importing the phone number from Telnyx. i went there and opened the destination countries.. created Outbound Voice Profile... and my phone number was connected to the right App.. but yet the conversation where really weird.. she's not picking up 60% of what i'm saying and there is HUGE LATENCY ISSUE for about 5-10 seconds!!! and i've changed the AnchorSite location to check if it's affecting latency and as well switched to latency based settings and nothing helped at all. Did someone had issues with Telnyx, is it an obligation to create the connection via SIP Trunking instead to solve this issue or what?...

rare-sapphire

12/4/2025

Outbound call failure

Hi, We can’t trigger outbound calls through http request (from Make). I’ve tried out Vonage phone numbers and Twillio phone numbers as well, I’ve been emailing with both, and the issue does not at the telephony provider’s side! ...

fascinating-indigo

12/4/2025

call.start.error.get-transport

Since mondey i have been getting this error it used to work fine i have tried checking twilio and everything seems good on their side also i have tried with different assistant and phone number but it still shows it The Call Id: 019ae3c9-e778-7aa9-8d1b-e38eb15e436b...

genetic-orange

12/4/2025

Mistake Vapi

Hello Hello, I need help, every time I do anything with vapi, I get an error or the page simply stops working and I have to restart it, it doesn't let me do anything, or add tools, or parameters. This is delaying my work and I don't understand why this is happening to me. Please I need help!!...

adverse-sapphire

12/4/2025

Inefficient algorithm for MiniMax TTS

Hi, The way VAPI handles TTS from minimax will hit the rate limit on almost all their plans within a very short time. I have been testing MiniMax with VAPI, and I can’t even get a call to last a few seconds without hitting the rate limit. The issue seems to be that VAPI is constantly hitting minimax for fragments of a sentence, and instead of just sending the entire sentence and streaming the result, it splits up the sentence into multiple parts that will then be streamed? Can this be changed in anyway? As it stands, it does 10+ requests in <4 seconds of call time, which is a little aggressive imo....

ugly-tan

12/4/2025

Metrics Page

When I select “Minutes” or “Hours” from the “Grouped By” dropdown on the metrics page, I’m getting the error below. Could you please take a look? Or am I missing something on my end?...

metropolitan-bronze

12/4/2025

GPT Realtime model failing to respond back to user with tool call response

When using the GPT realtime model connected to tools, I consistently found that the agent would execute a tool successfully and receive a response, but would just "hang" after responding with some variation of "Let me look that up for you". See attached image for transcript. I'm new to Vapi, so I'm wondering if this is a known bug? Or is there something extra I should be doing?...

exotic-emerald

12/4/2025

Which server message to listen to know when the assistant ends to speak

hey there — I'm working with Server Messages and wanted to know if there is a way to listen a particular event message that tells me when the last model output happens. I tried transcriptType="final" and model-output, and conversation-update but none of them seem to be reliable as they're being sent multiple times within the same AI turn. This is an example of model-output events: ```{ "message": {...

exotic-emerald

12/3/2025

Is there no more office hours?

This is the second time I'm joining office hours and seeing an empty room. Did you stop having office hours @Sahil @kyle

fascinating-indigo

12/3/2025

How can I override assistant voice when receiving inbound calls?

Here is the output I return:

{"assistantId":"ASSISTANT_ID","phoneNumberId":"PHONE_NUMBER_ID","assistantOverrides":{"variableValues":{"firstName":"George"},"voice":{"provider":"vapi","voiceId":"hana"}}}

It doesn't change any of the settings....

like-gold

12/3/2025

First Message not invoked when using custom tts server

Hi Vapi team, We are trying to test the use of custom tts servers and we have observed an issue where the initial welcome message configured on an agent is completely ignored, and the conversation only starts if the user initiates it. As far as we can tell from looking at your logs as well as ours, no attempt is made to contact our servers for that initial message, can you look into that? Example: https://dashboard.vapi.ai/calls/019ae457-39af-7339-bf0e-19c9f3043bd7...

sensitive-blue

12/3/2025

Over concurrecy limit. message.

Is there any option to decline inbound call instead of playing voice message when the channels limit reached? Currently VAPI plays the voice message "Over concurrecy limit." instead of just decline the call...

rival-black

12/3/2025

DTMF Tool Response Too Late — Call Ends Prematurely

@Duckie I’m encountering an issue where the DTMF tool is successfully triggered, but the response seems to arrive too late for the IVR system to process -resulting in the call being terminated before any connection is made. - DTMF is enabled in predefined functions. - I’m using the following prompt logic: [When navigating an IVR tree]...

Previous Next