Guide AvailableWorkflow + HTTP Request

Using SendiMessage with Vapi

Vapi runs the AI phone call. SendiMessage handles what happens on text afterward: your backend sends a confirmation, link, or follow-up on a managed line, and the customer's reply returns as a signed webhook your workflow can act on.

There is no native Vapi connector — the integration is a standard API-plus-webhook pattern, wired through your own backend. That keeps the two systems cleanly separated: Vapi owns the voice interaction; SendiMessage owns the messaging transport.

Request This Setup Book an Integration Review

What this integration enables

Post-call confirmation

When Vapi fires its end-of-call-report webhook, your backend sends a written confirmation or link the customer can keep.

Reschedule by text

The customer replies to change a time; the reply arrives as a webhook and your workflow updates the booking.

Follow-up nudge

No answer on the call? Send a text follow-up on the same customer relationship.

Opt-out honored

A STOP reply sets durable opt-out state automatically; later sends to that number are blocked.

Architecture

Vapi call endsVapi fires its end-of-call-report webhook
Your backendReceives the Vapi event and decides whether to text
SendiMessage APIPOST /send-message — the follow-up is queued on your line
Customer receives the messageiMessage where supported, SMS fallback where configured
Customer repliesThe answer arrives on the same line and thread
Signed receive webhookSendiMessage posts the reply to your endpoint
Your workflow continuesConfirm, reschedule, or escalate — the loop stays in your application

Example request

Send after the call

// Your application (not SendiMessage) decides what to say.
const res = await fetch("https://api.sendimessage.com/v1/send-message", {
  method: "POST",
  headers: {
    "X-API-Key": process.env.SENDIMESSAGE_API_KEY,
    "X-API-Secret": process.env.SENDIMESSAGE_API_SECRET,
    "Content-Type": "application/json",
    // Idempotency-Key derived from your own record id keeps a
    // retried automation from double-texting the customer.
    "Idempotency-Key": callId,
  },
  body: JSON.stringify({ number: customer.phone, content: agentReply }),
});
const { message_handle } = await res.json(); // store this on your record

Runs in your backend when the call-ended event fires. Derive Idempotency-Key from the call id so a retry never double-sends.

Limitations and honest notes

iMessage delivery is available on supported messaging lines and destinations. Recipients without iMessage receive SMS when fallback is configured — never assume universal iMessage availability.
Messages are accepted asynchronously — the API returns status QUEUED and final status arrives via webhook or the message endpoints.
No official SDK for this ecosystem yet — the example uses plain HTTP against the REST API. Official SDKs are published for JavaScript/TypeScript (npm: sendimessage), Python (PyPI: sendimessage), PHP (Composer: sendimessage/sdk), and Go (github.com/sendimessage/sendimessage-go). Every SDK is dependency-free and covers the full public API surface.
SendiMessage does not integrate with Vapi natively; you wire the Vapi call-ended event to your backend, and your backend calls SendiMessage.
SendiMessage sends and receives messages — it does not run the AI voice call, transcription, or model. Those stay in your stack.

Security considerations

Do not place SendiMessage API credentials directly in browser code. Send requests through your own server route or backend.
Keep your API key server-side, in environment variables or a secrets manager — never in client code, CRM front-end scripts, or repositories.
Verify the signature header on every incoming webhook before trusting the event.
Scope keys per environment and rotate them if they are ever exposed.

Frequently asked questions

Is this an official Vapi integration?

No. SendiMessage is an independent product and is not affiliated with, endorsed by, or sponsored by Vapi. Vapi is a trademark of its respective owner and is referenced here only to describe an integration pattern. The connection is implemented through the SendiMessage REST API and webhooks from your own backend.

Where does the AI logic live?

In your application and Vapi. SendiMessage provides the messaging line, delivery, and inbound replies — not the reasoning.

Voice AI Post-Call Follow-UpGuide Available

AI & Voice AIAfter any AI phone call, send a text follow-up and handle the reply — platform-neutral.

AI Agent WorkflowsGuide Available

AI & Voice AIFive reusable end-to-end patterns for wiring an AI agent to real customer messaging.

AI Agent MessagingAPI Integration Guide

Use CasesGive your AI agent a real phone presence: send, receive, and continue conversations over iMessage and SMS.

Appointment Reminder MessagingAPI Integration Guide

Use CasesConnect scheduling systems to reminders that actually arrive.