Custom LLM/TTS/STT Integration with Vapi
# supports
Sanandh
05/30/2025, 8:33 PMI'm looking to build a voice agent over telephony using Vapi. Currently, the telephony is handled via Twilio. I'm planning to use the TypeScript SDK to build the server.
I want to know if it's possible to use custom LLM, TTS, or STT models instead of the default options listed in Vapi's documentation. If so, how can I integrate those custom models into the workflow?
Thanks
s
Sanandh
06/02/2025, 4:37 AMThanks.
Sanandh
06/02/2025, 4:39 AMIs it possible to use just the Vapi TTS functionality? Our team really loved Neha's voice and we'd like to integrate it into our existing workflow.
c
Chiranjeet Mishra
06/03/2025, 1:13 AMWe are an orchestration platform, and we don't support exclusive services to use our TTS. You have to use our AIA systems.
Chiranjeet Mishra
06/03/2025, 1:13 AMAI Assistants\*
s
Sanandh
06/03/2025, 4:57 AMGot it, Thanks
c
Chiranjeet Mishra
06/03/2025, 8:00 AMPlease reach out to us if you have any other questions
s
Sanandh
06/03/2025, 10:32 AMYeah
Sanandh
06/03/2025, 10:33 AMI was wondering if there’s an example repo or tutorial available that demonstrates how to handle inbound and outbound calls using the TypeScript server SDK and Twilio.
Sanandh
06/03/2025, 3:10 PMAccording to the documentation, I should be able to make an outbound call to any number using Twilio as the provider through the server SDK (TS) with
client.calls.createSanandh
06/04/2025, 4:51 AMI also wanted to ask how I can obtain an Indian phone number. Since Twilio doesn’t support Indian numbers, do you support integration with Plivo or any other provider that offers Indian numbers?
c
Chiranjeet Mishra
06/04/2025, 5:23 AMHey,
You will need to get in touch with ([huzefa@vivadigitally.com](huzefa@vivadigitally.com)) [vivadigitally.com](http://vivadigitally.com), or any other telephony provider that offers a SIP trunk. They will be able to help with the number, and then you can read this guide about integrating it.
Note: This guide uses the Twilio SIP trunk as an example, but the procedure is pretty much the same for other telephony providers as well.
s
Sanandh
06/04/2025, 5:26 AMOkay understood.
Sanandh
06/04/2025, 5:27 AMCould you guide me on how to handle inbound calls using my server?
c
Chiranjeet Mishra
06/04/2025, 9:22 PMHey, can you please clarify what you mean by "to handle inbound calls using your server"? I couldn't understand.
s
Sanandh
06/11/2025, 1:00 PMHi, I'm receiving the tool-calls webhook correctly on my server and sending back a properly formatted response with HTTP 200, as specified in the documentation. However, I’m not seeing any response content reflected in the logs—only that a tool call was triggered, but not the actual result from the response.
I’ve also observed this behavior while interacting with the agent. For example, when I say, "I'm looking for a 3BHK flat in Bangalore," the tool gets invoked, and the model replies with, "I got a few options," but doesn't provide any further details—which should have come from the tool's response.
c
Chiranjeet Mishra
06/12/2025, 4:14 PMHey! To help track down this issue, could you share:
- The call ID
- When exactly this happened (the timestamp)
This would really help us figure out what went wrong!
s
Sanandh
06/13/2025, 4:41 AM- c8d2ed5e-83e7-43ef-9c06-1e195ecbf95f
- 12:53:19:035
c
Chiranjeet Mishra
06/16/2025, 6:34 PMHey, can you set async to false?
s
Sanandh
07/07/2025, 9:05 AMOkay
Sanandh
07/07/2025, 9:05 AMDoes the response generated by the OpenAI LLM go through a moderation check to detect any harmful or unsafe content?
c
Chiranjeet Mishra
07/07/2025, 10:38 PMHey Sanadh, it's not us, but OpenAI does content moderation.
14 Views