Awesome video! Thank you so much for taking the time to make this incredibly detailed training. You hooked me with this video. I am a serious candidate for your academy!
Thanks Jannis - This was great but wished you had spent just another 5 minutes and integrate the Google Calendar piece. Will be signing up if you can send me the link. Thanks for going over the functions as I could not really find anything on this. For another tutorial, it would be nice to know how to do add a knowledge base without using another tool or add-on. By the way, the resources are not in the Hub.
I really appreciate the input! I've published the resource slightly after it was released (It's live now). To make up for it, I've also added a little bonus to it that includes a bonus blueprint that includes a Google Calendar integration within the function call scenario. You will find everything via the following URL: hub.integraticus.com/building-an-ai-phone-assistant-in-2-hours-vapi-x-make-tutorial/
when i create the second scenario webhook and copy past it in the webhook response of the 1st scenario i save it but it’s doesn’t work 😢 how can i resolve it ????
@@sediknaili456 Run the call once manually via the "Run" button inside of make and check whether or not data arrives and what. There are many points of error so the more details you can provide the better.
@@jannismoore Thank you for your feedback. In fact, I did like you and created the new webhook. I copied its link and put it in the webhook response of the first scenario. I start manual triggering and make the call as well. The first scenario triggers without error, but the second scenario keeps running and does not receive data from the first scenario, I think. I haven’t activated the phone number yet. I make the call on VAPI, but I haven’t bought a number yet.
We implement dozens every week. I’m not sure what exactly keeps you from believing this isn’t really a thing for actual businesses, but you’re most welcome to share your concerns.
@@jannismoore I never said I believe in anything. I just want to see real results in business to test the product. Not sure what the big deal is there :D
Thanks for the awesome tut!! I have the problem that, every time I call the bot, it says 'couldn't fetch the assistant'. But in the postman execution is everything working fine. Do you have any idea how to solve/debug that?
ruclips.net/video/zdWS9sAd6PQ/видео.htmlfeature=shared :) You want to see what info is sent back within the webhook and then use that with Vapi’s “Create Assistant” endpoint. You’ll see more details within it
Awesome video for create an assistant with Vapi a big thanks to you for that you are such a genius !! I recuperate your blueprint for google calendar and all works but i just stuck with the filters "busy", i change my parameters and account of calendar to mine but the assistant always repeat it's full and busy even if it's not, could you have a tips for that ? I know it's the filter because when i remove my personal account the assistant take all the meeting but cumulate them... Anyway an amazing work you did on that vidéo and deserve so much more view for explaining so good everything in a complete way !
Hey, I'd check the dates that are actually used as an input for the free/busy module. Might be that they're running in the wrong year (happens when you don't define the current timestamp in the system prompt).
Hello Jannis, First of all I would like to provide my Big thanks to you for making detailed video on this topic. Good Job. I need help in fixing issue where in second scenario the Webhook terminates as soon as Voice agent collects "Name" value. Function is not able to stay active to collect other parameters. I seek you advice in fixing this issue.
Hey Rahul, I suggest to do a trial run within the make.com scenario by running it manually. You will then see a little bubble at the top right of the module that breaks. If you click on it, you will see more details about the errors that are happening.
Thank you for your videos and testing this incredible system, I have a question, does it work for the Brazilian Portuguese language? and the second question is would it be possible for me to connect with a Brazilian number (+55)?
Hi Jannis, how can we connect the bot to the restaurant's POS system to handle calls and send orders directly to the kitchen? Thank you for the great content.
Hey Paulo, this mostly depends on the POS system you use and how they allow external services to communicate with it. In most cases, they have some sort of API or Webhook integration, which you can check within their documentation. Depending on the endpoints they offer (The different features for communication), it requires a different setup. Feel free to share some more details about it or send me a message via integraticus.com
One way I found to slightly improve this build was to create a separate scenario for capturing the first name. The reason being that the user may not necessarily reserve a table when calling and may only have FAQs. So I split the name capturing off from the reserve table scenario, created a new scenario to add the first name to the leads google sheet, added a captureFirstName function to my Vapi agent to capture the first name, and updated my prompt to explicitly call that captureFirstName function. The function name and description weren't enough for Vapi agent wasn't able to infer it needed to call function when the context arose - I had to prompt it with clear instructions when to call the function.
@@jannismoore A full walkthrough on how to setup google free/busy calendar api, check for availabity, book the time, and even reschedule (if they were to call back and say they want to reschedule, or if we call them and they say they cant make it but want to reschedule). Ideally for an outbound and inbound call scenario
@@jannismoore A full walkthrough on how to setup google free/busy calendar api, check for availabity, book the time, and even reschedule (if they were to call back and say they want to reschedule, or if we call them and they say they cant make it but want to reschedule). Ideally for an outbound and inbound call scenario
Hi! Thanks for the video its asome! I have a question if I wanna make this in a different language, may I have to use that language in the Json file and also when I'm doing the prompting?
Impressive stuff" Having an issue getting the transient assistant to work, prompt is fine and got all the variables setup but the initial vapi server url / webhook => webhook response is confusing me... Can you make a tutorial please on how to get the vapi/make handshake to work? Thanks bud and keep it up
Good point. There are a couple of entry points for creating the transient-based assistant. Vapi actually released an updated version of their documentation that explains the different possibilities of the server URL very clearly. I suggest checking out this URL: docs.vapi.ai/server-url/setting-server-urls If that still doesn't help, feel free to share some more details here
Can you do a video on handling errors? In my experience, the AI agents in VAPI will tell me that an outbound call was successful, when in fact it was not. This creates the terrible scenario where the caller thinks an action was successful when it was not. Imagine showing up to your birthday celebration only to find out there was no reservation made!
I have a video on how to debug Vapi errors: ruclips.net/video/u-8xdblVY_4/видео.html Unfortunately this won't be much of the help for the issue you describe as that's mostly related to the right prompting. If the assistant does something but it hasn't booked the call, the instructions weren't clear enough.
Hey Jannis! Vapi has changed the UI recently and the entire functions section has been replaced with Tools, Can you tell us a quick little fix for that?
Hey Jannis, amazing video! Learned so much from this! One issue I am having though is with triggering the end of call sequence. I too have the router condition in make set as message: type == end-of-call-report. I have also made sure that in both of my webhook responses (one for having name and one for not having name), I have the serverUrl set correctly (pointing to the Get Vapi Assistant webhook), have serverMessages array correctly including "end-of-call-report", have endCallFunctionEnabled set to true, and have a valid endCallMessage. However, I am never able to get the sequence to trigger when ending the call. I have tried re-running the Get Vapi Assistant scenario mid-call after the agent has already been retrieved and the scenario terminated the first time thinking this might help. Yet when the scenario is running again and I end the call, still nothing happens. Any troubleshooting ideas here?
Nevermind, I guess I had to triple check the serverURL link was pointing to the correct webhook. I was missing a character 🤦♂Got everything working! Also got the Google calendar integration working too!
Hi Janis awesome video thanks! My second "Reserve Table" function scenario is not being triggered. The first scenario works and a number is being added to the google sheets. But the second scenario just hangs. No idea why. Any thoughts on trouble shooting how to trigger the second function scenario? Thanks!
@@jannismoore Thank you Jannis I did watch this video and it's fantastic. I am not actually experiencing an error, it's just that the second scenario / webhook is not being triggered. Do you have a discord or skool? Would be keen to explore this further.
Great video man, this was really helpful. Just wanted to make a request if you could do a tutorial video for food ordering and appointment booking for Attorneys and doctor please
Hi Jannis, I have an issue mapping field in google sheet. The problem is when I run the scenario, there is no functionCall showing up, even though JSON file is without errors. What do you suggest? Any help, btw great tutorials.
@@jannismoore Thanks Jannis. I tried my best to figure out how to create a hotel AI receptionist using tools, we wrapped functions inside "tools" tag in JSON, but for some reason we cant make it show up in Make. Cant wait for that new video, as we are obviously missing something.
There's no direct limitation from Vapi, but there is some on Twilio. In general, I recommend not running more than 50 calls per second as otherwise Twilio rate-limits your calls. With 100 calls, you can simply batch the calls using make.com (This is a setting when you do it using a Google Sheet table)
Hi thanks a bunch for the lessons. I am running into an issue with my last webhook and getting this message can you help me debug it: Webhooks Initialization Warning Response can't be processed when scenario is not executed immediately on data arrival. Origin Make
I enjoyed your video and it was very informative. I like the functionality, but I was surprised as to the low quality AI speech. Is there a reason the bot sounded that robotic?
I used azure for the example. It’s not the most natural-sounding, but I like it for covering multilingual conversations. It’s always a game between latency and quality so if you value quality more, I suggest to stick to the 11labs voices.
$2 per minute is way too pricy for any ai calling platform. Vapi charges you an average of $0.13 per minute, and in any case, even the priciest platforms won’t go over $0.65.
Hi Jannis. I am trying to configure call forward using multiple numbers with the “forwardingPhoneNumbers” function. Should this function be included in the initial webhook that included the AI assistant configuration? We would like to use VAPI to route calls back to our old phone system with voicemail boxes. Thank you!
Hi Jannis, I'm trying to follow your tutorial (which is great btw). But I can't get any further than 24 minutes in as Vapi seems to be depreciating Functions in favour of tools. And even with that, it doesn't seem to follow the flow of your tutorial. In fact when I get to the third page for create a tool, "What is this tool for?" - no matter what I do, the CREATE option stays grayed out.
Hi Jannis, I love your videos! A quick issue: I went step by step and it keeps saying I have to connect the assistant on Make. On timestamp: 46:15 you copied a webhook URL and added it to the json script. Was that needed? I wasn't clear. Did you just add the webhook or something else. Cannot get that to work to go further. Keeps saying I have to connect the assistant ID to the number? But I am following you to do it dynamic--not static. Any help appreciated. Cheers.
So I have an inbound call setup that works like this. It has data it requests from another server and then feeds it into the webhook response. I get an error sometimes from Vapi that says "timeout exceeded 7500 miliseconds" which I'm assuming happens because there's too much data to be processed and it doesn't get done in less than 7.5 seconds. Is this something you've experienced and do you have any tips on dealing with this?
I don't have that usually, but it always makes sense to lower the execution time. 7.5 seconds is really long, so you might want to implement some caching mechanisms
At timestamp 40:18 where you add the webhook URL. I was just looking at this. Setting the URL here means that you can only run one assistant - is there another way using any of the other server URL spots ?
Hey, I have a problem with 'not getting an assistant' response over and over. I have no idea what I did wrong and would you mind checking my code and see what I did wrong?
With code you mean you're using custom code for doing it? If you don't get any response, you might want to watch one of my "Custom LLM" videos for Vapi
Hey Jannis, I am getting this error on the "If it doesn't exist" google sheet: RuntimeError 403: PERMISSION_DENIED - The caller does not have permission Origin Google Sheets For context, if I ignore the error I am still not able to fetch the assistant. How should I troubleshoot this?
@@tommychryst that means there is something wrong with the assistant JSON. I did a debugging bud that also explains that in depth so I suggest checking it out. To give you a tldr: you can run the scenario ones within make and then check the HTTP module response - this one includes details about why the call failed. You can access this with the bubble that appear on the top right of the integration after it ran
If they have a predefined integration on make.com or Zapier, you can use those. Otherwise you still have an option to build your own if they have an API available. Calendly, for example, is one of the few services that does not have an API endpoint to schedule meetings, so in that case you need to become creative with browser automations.
The reason your functions did not transfer over is that you forgot to press save for each function. Once you save a function you can then create another property.
Yeah I noticed that too. They’ve changed the functions layout twice in the last two weeks, which was kind of unexpected. Let’s hope it stays like the one we have now.
Oh never mind its in a different spot, its at the bottom left next in the little box with the question mark I just found Documentation and API Documentation
In the First Google Calendar Error Validation failed for 2 parameter(s). - Missing value of required parameter 'timeMin'. - Missing value of required parameter 'timeMax'. What Min and Max values are being requested ? Just another question, do you want techical issues here or on the Discord Server ?
Min and Max both come from the function call variable that was set during the tutorial (The specific time). If it says it's empty, I suggest to check whether or not the webhook URL was actually included into the right function serverURL field, and if the request was actually a function call in the first place. When you press "Run" and then cause the function to fire, you can see all of the details the function sent along with and if it was a function call in the first place.
so you said in your flow that it would book the appointments in google calendar. i went the whole hour and 20 min and you did not even mentioned again. You debugged so much that maybe you forgot. you only built the assistant, but with no fetching in any calendar.
Once you’re inside of the scenario, you can click on the three dots at the bottom of the screen and then click on import blueprint. There you can add the blueprint you downloaded from within the resource hub
You can set a number of words the caller (human) has to say to interrupt the assistant. Let’s say you set it to 2, then the caller must say two words until the assistant stops talking
Because it's the easiest way to return a transient-based assistant that you can give dynamic values. IF you can live with no dynamic adjustments within your prompt, you can simply use the visual interface that Vapi provides.
I see the server url is set at the Account level of Vapi - does that mean you need to create a different account for each transient assistant created? ruclips.net/video/RMOHpWAPan8/видео.html
No, you can have multiple assistants per account. You can simply set up a filter within the Make.com Webhook trigger module where you check against the ID of the phone number that you want to allow through
It's a terrible pain to follow your tutorial with that constant zooming and scrolling. Those of us who are new are more lost like this. thank you anyway.
There is no one-size-fits-all solution and therefore no fixed pricing, but if you got a rough idea, feel free to drop me a message via our contact form with some key aspects of what you're looking for, and we will come back to you with more details: integraticus.com/contact
Killing it bro
Thank you so much for this! Awesome material💪❤️
Awesome video! Thank you so much for taking the time to make this incredibly detailed training. You hooked me with this video. I am a serious candidate for your academy!
The VAPI King himself 👑
Amazing tutorial, watched to the end - max value elicited.
My favorite part of the video is when you were debugging.. that helped me quite a bit, thanks.
I appreciate this channel, i just found it and havent even reach 20mins...
Sehr nicer Input Jannis, Grüße aus Deutschland!
Looks sick brother!
Thanks Jannis - This was great but wished you had spent just another 5 minutes and integrate the Google Calendar piece. Will be signing up if you can send me the link. Thanks for going over the functions as I could not really find anything on this. For another tutorial, it would be nice to know how to do add a knowledge base without using another tool or add-on. By the way, the resources are not in the Hub.
I really appreciate the input! I've published the resource slightly after it was released (It's live now).
To make up for it, I've also added a little bonus to it that includes a bonus blueprint that includes a Google Calendar integration within the function call scenario. You will find everything via the following URL: hub.integraticus.com/building-an-ai-phone-assistant-in-2-hours-vapi-x-make-tutorial/
@@jannismoore many thanks Jannis - really appreciate it. Just got things downloaded and saved - will pay with it today and let you know how it goes.
when i create the second scenario webhook and copy past it in the webhook response of the 1st scenario i save it but it’s doesn’t work 😢 how can i resolve it ????
@@sediknaili456 Run the call once manually via the "Run" button inside of make and check whether or not data arrives and what. There are many points of error so the more details you can provide the better.
@@jannismoore Thank you for your feedback. In fact, I did like you and created the new webhook. I copied its link and put it in the webhook response of the first scenario. I start manual triggering and make the call as well. The first scenario triggers without error, but the second scenario keeps running and does not receive data from the first scenario, I think. I haven’t activated the phone number yet. I make the call on VAPI, but I haven’t bought a number yet.
Awesome content! Thank you so much for this tutorial. Do you provide a community group? I really want to join if there is one
we have all the tech in the world
but show me real business with this implementation
:)
We implement dozens every week.
I’m not sure what exactly keeps you from believing this isn’t really a thing for actual businesses, but you’re most welcome to share your concerns.
@@jannismoore I never said I believe in anything. I just want to see real results in business to test the product. Not sure what the big deal is there :D
Thanks for the awesome tut!! I have the problem that, every time I call the bot, it says 'couldn't fetch the assistant'. But in the postman execution is everything working fine. Do you have any idea how to solve/debug that?
ruclips.net/video/zdWS9sAd6PQ/видео.htmlfeature=shared :)
You want to see what info is sent back within the webhook and then use that with Vapi’s “Create Assistant” endpoint. You’ll see more details within it
Love it. Good job. Amazing video❤
Your ROCK brother!🔥🪨🔥
Awesome video for create an assistant with Vapi a big thanks to you for that you are such a genius !! I recuperate your blueprint for google calendar and all works but i just stuck with the filters "busy", i change my parameters and account of calendar to mine but the assistant always repeat it's full and busy even if it's not, could you have a tips for that ? I know it's the filter because when i remove my personal account the assistant take all the meeting but cumulate them... Anyway an amazing work you did on that vidéo and deserve so much more view for explaining so good everything in a complete way !
Hey, I'd check the dates that are actually used as an input for the free/busy module. Might be that they're running in the wrong year (happens when you don't define the current timestamp in the system prompt).
Great video!
Excellent work !!!
great work dude. so, I'm just half way through... This doesn't use the function in vapi, correct? Because they are unfortunately being deprecated.
This setup used custom functions on a per-assistant basis, but yes, they're deprecated. I'll make a new video about the new updates soon
Excellent!
Hello Jannis, First of all I would like to provide my Big thanks to you for making detailed video on this topic. Good Job. I need help in fixing issue where in second scenario the Webhook terminates as soon as Voice agent collects "Name" value. Function is not able to stay active to collect other parameters. I seek you advice in fixing this issue.
Hey Rahul, I suggest to do a trial run within the make.com scenario by running it manually. You will then see a little bubble at the top right of the module that breaks. If you click on it, you will see more details about the errors that are happening.
Thank you for your videos and testing this incredible system, I have a question, does it work for the Brazilian Portuguese language? and the second question is would it be possible for me to connect with a Brazilian number (+55)?
yes, and yes. For the Brazilian number you can use Twilio directly and import your number. for Portuguese you can use Azure as an example.
Hi Jannis, how can we connect the bot to the restaurant's POS system to handle calls and send orders directly to the kitchen? Thank you for the great content.
Hey Paulo, this mostly depends on the POS system you use and how they allow external services to communicate with it.
In most cases, they have some sort of API or Webhook integration, which you can check within their documentation.
Depending on the endpoints they offer (The different features for communication), it requires a different setup.
Feel free to share some more details about it or send me a message via integraticus.com
One way I found to slightly improve this build was to create a separate scenario for capturing the first name. The reason being that the user may not necessarily reserve a table when calling and may only have FAQs. So I split the name capturing off from the reserve table scenario, created a new scenario to add the first name to the leads google sheet, added a captureFirstName function to my Vapi agent to capture the first name, and updated my prompt to explicitly call that captureFirstName function. The function name and description weren't enough for Vapi agent wasn't able to infer it needed to call function when the context arose - I had to prompt it with clear instructions when to call the function.
Love it. Adding it to the prompt is great and I guess now it's even easier classifying that after the call (Using the new analytics features)
Call comes to Vapi then to Make from Make goes everywhere else 🎉🎉 can you also add your URL for data gathering on top of maker?
Of course you can. :)
Jannis. Hope you had a nice birthday 🎂 😮😅 Can you do a video about Squads? Or is make COM easier.
Please do a tutorial with Google Calendar availability. 🔥🔥🔥🔥
Added to my list! You only want the availability covered or as well the scheduling and cancellations?
@@jannismoore A full walkthrough on how to setup google free/busy calendar api, check for availabity, book the time, and even reschedule (if they were to call back and say they want to reschedule, or if we call them and they say they cant make it but want to reschedule). Ideally for an outbound and inbound call scenario
@@jannismoore A full walkthrough on how to setup google free/busy calendar api, check for availabity, book the time, and even reschedule (if they were to call back and say they want to reschedule, or if we call them and they say they cant make it but want to reschedule). Ideally for an outbound and inbound call scenario
@@HelloWorld-ii2uh Yes please
@@HelloWorld-ii2uh I got you! Will be released next week
Hi! Thanks for the video its asome! I have a question if I wanna make this in a different language, may I have to use that language in the Json file and also when I'm doing the prompting?
Yes that's correct
Impressive stuff" Having an issue getting the transient assistant to work, prompt is fine and got all the variables setup but the initial vapi server url / webhook => webhook response is confusing me... Can you make a tutorial please on how to get the vapi/make handshake to work? Thanks bud and keep it up
Good point. There are a couple of entry points for creating the transient-based assistant. Vapi actually released an updated version of their documentation that explains the different possibilities of the server URL very clearly. I suggest checking out this URL: docs.vapi.ai/server-url/setting-server-urls
If that still doesn't help, feel free to share some more details here
Can you do a video on handling errors? In my experience, the AI agents in VAPI will tell me that an outbound call was successful, when in fact it was not. This creates the terrible scenario where the caller thinks an action was successful when it was not. Imagine showing up to your birthday celebration only to find out there was no reservation made!
I have a video on how to debug Vapi errors: ruclips.net/video/u-8xdblVY_4/видео.html
Unfortunately this won't be much of the help for the issue you describe as that's mostly related to the right prompting. If the assistant does something but it hasn't booked the call, the instructions weren't clear enough.
Great video. How do you handle fake robocalls, who may ring the number from time to time?
Never had that issue. You could use the transcripts to determine whether or not a call was legit or not
Hey Jannis!
Vapi has changed the UI recently and the entire functions section has been replaced with Tools, Can you tell us a quick little fix for that?
Will launch new Vapi content soon :)
Thank you so much for this video!!
You are so welcome!
Hey Jannis, amazing video! Learned so much from this! One issue I am having though is with triggering the end of call sequence. I too have the router condition in make set as message: type == end-of-call-report. I have also made sure that in both of my webhook responses (one for having name and one for not having name), I have the serverUrl set correctly (pointing to the Get Vapi Assistant webhook), have serverMessages array correctly including "end-of-call-report", have
endCallFunctionEnabled set to true, and have a valid endCallMessage. However, I am never able to get the sequence to trigger when ending the call. I have tried re-running the Get Vapi Assistant scenario mid-call after the agent has already been retrieved and the scenario terminated the first time thinking this might help. Yet when the scenario is running again and I end the call, still nothing happens. Any troubleshooting ideas here?
Nevermind, I guess I had to triple check the serverURL link was pointing to the correct webhook. I was missing a character 🤦♂Got everything working! Also got the Google calendar integration working too!
Hi Janis awesome video thanks! My second "Reserve Table" function scenario is not being triggered. The first scenario works and a number is being added to the google sheets. But the second scenario just hangs. No idea why. Any thoughts on trouble shooting how to trigger the second function scenario? Thanks!
I made a debugging video specifically for those cases - this should probably help you find the solution: ruclips.net/video/zdWS9sAd6PQ/видео.html
@@jannismoore Thank you Jannis I did watch this video and it's fantastic. I am not actually experiencing an error, it's just that the second scenario / webhook is not being triggered. Do you have a discord or skool? Would be keen to explore this further.
Great video man, this was really helpful.
Just wanted to make a request if you could do a tutorial video for food ordering and appointment booking for Attorneys and doctor please
Hey! Do you refer to simple food ordering by leveraging the transcript or by actually implementing a third-party CRM to submit the orders to?
@@jannismoore simple food ordering
how to add choices? Like would you have a standard table or sitting at the bar? Could you show that?
You can add that information to the system prompt
@@jannismoore thank you I try that
Hi Jannis, I have an issue mapping field in google sheet. The problem is when I run the scenario, there is no functionCall showing up, even though JSON file is without errors. What do you suggest? Any help, btw great tutorials.
Hey! Vapi deprecated function calls and replaced them with tool calls - I'm going to make a video about that soon :)
@@jannismoore Thanks Jannis. I tried my best to figure out how to create a hotel AI receptionist using tools, we wrapped functions inside "tools" tag in JSON, but for some reason we cant make it show up in Make. Cant wait for that new video, as we are obviously missing something.
Just amazing the knowledge high value - is there a limit for incoming calls? - let’s say 100 calls how you will set up limits and cycles?
There's no direct limitation from Vapi, but there is some on Twilio. In general, I recommend not running more than 50 calls per second as otherwise Twilio rate-limits your calls. With 100 calls, you can simply batch the calls using make.com (This is a setting when you do it using a Google Sheet table)
Thanks
Hi thanks a bunch for the lessons. I am running into an issue with my last webhook and getting this message can you help me debug it: Webhooks
Initialization
Warning
Response can't be processed when scenario is not executed immediately on data arrival.
Origin
Make
You basically have a trigger that is scheduled via some kind of interval.
I suggest resetting the trigger webhook. That should do the trick
I enjoyed your video and it was very informative. I like the functionality, but I was surprised as to the low quality AI speech. Is there a reason the bot sounded that robotic?
I used azure for the example. It’s not the most natural-sounding, but I like it for covering multilingual conversations.
It’s always a game between latency and quality so if you value quality more, I suggest to stick to the 11labs voices.
Hi! Is there an updated video for VAPI and GHL connection? I have been checking all of your videos but I can't seem to find one :(
I have one about GHL regarding authentication itself.
That one is still working and the latest way to go
@@jannismoore Would it be the "How to use the GoHighLevel API v2 | Complete Tutorial"?
Awesome video thank you, would the cost per minute of calls be cheaper if you use Twilio or would it still cost $2 per minute?
$2 per minute is way too pricy for any ai calling platform.
Vapi charges you an average of $0.13 per minute, and in any case, even the priciest platforms won’t go over $0.65.
@@jannismoore thanks Jannis just signed up for your Acdemey 🤙
Hi Jannis. I am trying to configure call forward using multiple numbers with the “forwardingPhoneNumbers” function. Should this function be included in the initial webhook that included the AI assistant configuration? We would like to use VAPI to route calls back to our old phone system with voicemail boxes. Thank you!
What a legend
how many clients do you have? still havent answered my qs man!
My Vapi dashboard looks different than yours, I dont have all those tools and documents on the left hand side, are their different versions?
Vapi changes things regularly - makes it harder to find things, but it's generally good knowing they innovate. :)
Hi Jannis, I'm trying to follow your tutorial (which is great btw). But I can't get any further than 24 minutes in as Vapi seems to be depreciating Functions in favour of tools. And even with that, it doesn't seem to follow the flow of your tutorial. In fact when I get to the third page for create a tool, "What is this tool for?" - no matter what I do, the CREATE option stays grayed out.
Hey hey, yeah Vapi startd to deprecate functions. I'll make a separate video on that soon
Hi Jannis, I love your videos! A quick issue: I went step by step and it keeps saying I have to connect the assistant on Make. On timestamp: 46:15 you copied a webhook URL and added it to the json script. Was that needed? I wasn't clear. Did you just add the webhook or something else. Cannot get that to work to go further. Keeps saying I have to connect the assistant ID to the number? But I am following you to do it dynamic--not static. Any help appreciated. Cheers.
Simply remove the assistant ID field and only define the "assistant" key instead. Otherwise it tries to take a static assistant from the db
@@jannismoore Thank you
Hello professor, is it possible to use N8N instead of using MAKE?
Of course it is :)
Hey again! I faced an issue, I set up the dynamic name, and my response body has it, but the Vapi doesn't say the name. Any suggestion? Thanks!!
Might be even a prompting issue in that case. Does it say the placeholder instead?
there is a gap before the name, can that be fixed
hey jannis in the last call did it fill the first name column with the alex ? and if not how to do that
Do you mean that you have issues filling in the last column?
Awesome bro !
Hi,
great video
do you think you can integrate whatsapp ? So people can call or they can text. But all transcript go inside whatsapp ?
WhatsApp has an API so I assume you can feed in the transcript to WhatsApp. You most likely need some custom code for that.
So I have an inbound call setup that works like this. It has data it requests from another server and then feeds it into the webhook response. I get an error sometimes from Vapi that says "timeout exceeded 7500 miliseconds" which I'm assuming happens because there's too much data to be processed and it doesn't get done in less than 7.5 seconds. Is this something you've experienced and do you have any tips on dealing with this?
I don't have that usually, but it always makes sense to lower the execution time. 7.5 seconds is really long, so you might want to implement some caching mechanisms
At timestamp 40:18 where you add the webhook URL. I was just looking at this. Setting the URL here means that you can only run one assistant - is there another way using any of the other server URL spots ?
If you set a URL there, all of your assistants will run through it.
You can also connect a URL to the phone number, as well as to the assistant.
@@jannismoore Ok - thanks. But then does that mean you have to have every assistant hook up to the same Make Scenario ?
Hey, I have a problem with 'not getting an assistant' response over and over. I have no idea what I did wrong and would you mind checking my code and see what I did wrong?
With code you mean you're using custom code for doing it?
If you don't get any response, you might want to watch one of my "Custom LLM" videos for Vapi
Could you have multiple phone numbers under 1 vapi account?
Yep definitely. You can have unlimited numbers basically. It's all up to you
I watched the video. I'm interested in the tool you will like to provide...
Which one exactly? The ones mentioned are all available via my resource hub (Link in the description)
top top top
Hey Jannis, I am getting this error on the "If it doesn't exist" google sheet:
RuntimeError
403: PERMISSION_DENIED - The caller does not have permission
Origin
Google Sheets
For context, if I ignore the error I am still not able to fetch the assistant. How should I troubleshoot this?
Now the error is: "assistant-request-returned-invalid-assistant"
You should see more details of what’s wrong within the response data of make
@@jannismoore I figured out the google sheets error, but now it just says invalid assistant (no error on make)
@@tommychryst that means there is something wrong with the assistant JSON. I did a debugging bud that also explains that in depth so I suggest checking it out.
To give you a tldr: you can run the scenario ones within make and then check the HTTP module response - this one includes details about why the call failed. You can access this with the bubble that appear on the top right of the integration after it ran
But how do you integrate it with other calendar softwares that are not google calendar?
If they have a predefined integration on make.com or Zapier, you can use those. Otherwise you still have an option to build your own if they have an API available.
Calendly, for example, is one of the few services that does not have an API endpoint to schedule meetings, so in that case you need to become creative with browser automations.
The reason your functions did not transfer over is that you forgot to press save for each function. Once you save a function you can then create another property.
Yeah I noticed that too. They’ve changed the functions layout twice in the last two weeks, which was kind of unexpected. Let’s hope it stays like the one we have now.
Oh never mind its in a different spot, its at the bottom left next in the little box with the question mark I just found Documentation and API Documentation
is it possible to make the voice agent talk in turkish?
Yes you can. Look for the Azure voice Provider and search for Emel or Ahmed
@@jannismoore thanks
I think I love you ❤❤❤❤❤
In the First Google Calendar
Error
Validation failed for 2 parameter(s).
- Missing value of required parameter 'timeMin'.
- Missing value of required parameter 'timeMax'.
What Min and Max values are being requested ?
Just another question, do you want techical issues here or on the Discord Server ?
Min and Max both come from the function call variable that was set during the tutorial (The specific time). If it says it's empty, I suggest to check whether or not the webhook URL was actually included into the right function serverURL field, and if the request was actually a function call in the first place. When you press "Run" and then cause the function to fire, you can see all of the details the function sent along with and if it was a function call in the first place.
many thanks Janis. I will relook at it. It is a little confusing which we hook goes where.
so you said in your flow that it would book the appointments in google calendar. i went the whole hour and 20 min and you did not even mentioned again. You debugged so much that maybe you forgot. you only built the assistant, but with no fetching in any calendar.
I probably did. Nevertheless, I got an actual calendar booking one coming up soon. :)
45:44 You lost me here bro, what do I do with the blueprint where do I paste it
Once you’re inside of the scenario, you can click on the three dots at the bottom of the screen and then click on import blueprint.
There you can add the blueprint you downloaded from within the resource hub
does is handle interruption like humans?
You can set a number of words the caller (human) has to say to interrupt the assistant.
Let’s say you set it to 2, then the caller must say two words until the assistant stops talking
Why paste the whole code in the webhook response?
Because it's the easiest way to return a transient-based assistant that you can give dynamic values. IF you can live with no dynamic adjustments within your prompt, you can simply use the visual interface that Vapi provides.
@@jannismoore thanks. make the google calendar video!!
@@ILDFI Already added this to my list. I assume it'll be out next week.
I see the server url is set at the Account level of Vapi - does that mean you need to create a different account for each transient assistant created? ruclips.net/video/RMOHpWAPan8/видео.html
No, you can have multiple assistants per account. You can simply set up a filter within the Make.com Webhook trigger module where you check against the ID of the phone number that you want to allow through
@@jannismoore Oh wow! Thanks! The amount of information and quality of your videos is freaking outstanding btw.
It's not a same interface like the last 2 month
Nope, but updates will come soon :)
screen making me dizzy
That’s fixed in future videos :)
It's a terrible pain to follow your tutorial with that constant zooming and scrolling. Those of us who are new are more lost like this. thank you anyway.
Appreciate the feedback. Those zooms have been already optimized for newer videos.
If something is unclear, you're most welcome to ask.
Great video 🦾 how much you sell this service ?
There is no one-size-fits-all solution and therefore no fixed pricing, but if you got a rough idea, feel free to drop me a message via our contact form with some key aspects of what you're looking for, and we will come back to you with more details: integraticus.com/contact