Twilio Voice Setup

Connect a Twilio voice number so an AI agent answers inbound calls — transcribing the caller, generating a reply, and speaking it back over a real-time audio stream. CallMissed stores your Twilio credentials per tenant and serves the TwiML that bridges the call to its streaming pipeline.

Prerequisites

• A Twilio account (a trial account works for testing).
• A voice-capable phone number purchased in the Twilio Console (Phone Numbers → Manage → Buy a number, with the Voice capability).
• A CallMissed account with the owner or admin role.

Get your Twilio credentials

From the Twilio Console home page, copy:

• Account SID — starts with AC….
• Auth Token — click to reveal it under Account Info.
• Phone Number — your purchased number in E.164 format (for example +14155550123).

Save credentials in CallMissed

Create a voice bot

Create a bot with type: "inbound_call" and a system prompt for the agent's persona:

curl -X POST https://api.callmissed.com/api/v1/bots \
  -H "Authorization: Bearer cm_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Reception Agent",
    "type": "inbound_call",
    "system_prompt": "You are the front-desk agent for Acme Clinic. Be concise and friendly."
  }'

Point your number at CallMissed

In the Twilio Console, open your number (Phone Numbers → Manage → Active numbers → your number). Under Voice Configuration → A call comes in, set:

• Webhook, HTTP POST, URL:

https://api.callmissed.com/api/v1/webhooks/twilio/voice

Save. Twilio will now POST to CallMissed on every inbound call, and CallMissed handles the call with its real-time voice AI pipeline.

Test the call

Call your Twilio number. The real-time path is:

1. 1

   Caller

   Dials your Twilio number

2. 2

   Twilio

   POSTs to ; CallMissed returns TwiML opening a media stream

3. 3

   STT (saaras:v3)

   Transcribes the caller's audio in real time

4. 4

   LLM

   Generates the reply from the bot's system prompt + conversation history

5. 5

   TTS (bulbul:v3)

   Synthesizes speech — playback starts before generation finishes

6. 6

   Caller

   Hears the AI agent respond

Tip: For browser/mobile WebRTC agents (no phone number required) use the Voice Agent and Voice Sessions API instead. See the Voice Calling guide for the full telephony protocol.