Overview

This developer-led walkthrough connects SMS Voice v2 API with SNS and SQS to an existing Voiceflow Chat agent. Your server receives customer texts, selects the intended agent session, sends the text to Voiceflow, then delivers the answer through AWS End User Messaging. You host and maintain the relay; a provider send action alone does not establish this conversation path.

Managed alternative: Voiceflow SMS hosts the two-way channel for connected Twilio numbers. This page teaches the AWS End User Messaging relay.

Before you begin

Prepare the agent, provider account and relay host.

An AWS End User Messaging SMS origination number supporting two-way SMS in its country, the required registrations, production SMS access or a verified sandbox recipient, and an operator able to create SNS/SQS resources and IAM policies.

Examples use 🇺🇸 US +14155550100 as the business number and +12025550123 as the customer. Replace these fictional numbers with your controlled, eligible numbers. Use the provider’s required international representation at its boundary; the relay stores normalized E.164.

This sample handles incoming-first text support, one provider and one business number per deployment. It returns text traces, suppresses the launch greeting, and sends one answer of at most 640 UTF-16 units. It does not implement MMS, rich controls or human agent hand-off. Review Chat agents before extending those behaviors.

Host the relay

Install the server and connect its persistent store and credentials.

1

Download the runnable relay

Download the SMS relay archive and unpack it on the host:

The archive includes the server, provider adapters, SQLite worker, pinned dependency lock, Docker/HTTPS configuration and offline tests. The README owns the shared operations and recovery commands.

2

Configure the agent and secrets

Edit .env: set PROVIDER=aws, SMS_DOMAIN to your domain, PUBLIC_ORIGIN to its HTTPS origin without a trailing slash, and SMS_FROM to the owned E.164 business number. Set VF_PROJECT_ID, VF_ENVIRONMENT and VF_API_KEY to the published test Chat Environment and its runtime key. These are server secrets, never browser inputs.

Generate two separate random values with the following command, putting one in IDENTITY_SECRET and the other in WEBHOOK_SECRET. Set ROUTE_GENERATION=1.

Keep IDENTITY_SECRET stable so sender identity and local opt-out records survive restarts. Add this provider’s variables:

Remove the unused Telnyx entries from .env.example when selecting another provider. AWS SDK credentials, when needed, follow the credential-chain instructions in the provider setup below.

3

Prepare the host before provider setup

Point the domain’s DNS at the host and allow the HTTPS ports prepared above. Leave the worker stopped while you create the AWS topic, queue, configuration set and IAM identity below, then fill their real values in .env. Startup validates them; placeholder values do not establish a connection. AWS receives through SQS, so no public incoming/status callback URL is registered. Keep the persistent sms-data volume and one worker.

Connect AWS End User Messaging

Save the provider’s incoming route and prepare outgoing replies.

1

Create the two-way SNS topic

Create a standard SNS topic in the number’s Region. Its policy must permit the sms-voice.amazonaws.com service to sns:Publish for your AWS account and this origination resource. Follow the AWS two-way topic policy. Keep this topic dedicated to incoming SMS.

2

Subscribe a durable SQS queue

Create a standard SQS queue and a dead-letter queue, with a redrive policy after five failed receives. Subscribe the queue to the SNS topic; leave Raw message delivery disabled so the worker can check TopicArn. In the queue policy allow only sns.amazonaws.com to sqs:SendMessage, with aws:SourceArn equal to this topic ARN. Record the queue URL. Do not grant other publishers permission to write SMS-shaped queue messages.

3

Enable two-way SMS on the number

Open AWS End User Messaging → Configurations → Phone numbers, select the controlled number, then Two-way SMS → Edit settings → Enable two-way message. Choose the SNS topic and its topic-policy authorization, then Save changes. Set the saved topic ARN in AWS_SNS_TOPIC_ARN.

4

Give the worker its own IAM identity

On EC2, attach the dedicated instance role and enable IMDSv2 access from the relay container. This Compose network adds a hop: a metadata response hop limit of 1 can prevent credential retrieval. In the instance’s metadata options, require IMDSv2, enable the metadata endpoint and set a response hop limit that supports the container (2 in AWS’s container guidance). Check the host firewall permits that access.

Alternatively, supply dedicated AWS credentials in .env. The SDK credential chain recognizes AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and, for temporary credentials, AWS_SESSION_TOKEN. Grant sqs:ReceiveMessage, sqs:DeleteMessage and sqs:GetQueueAttributes on only this queue, and sms-voice:SendTextMessage on the origination resources required by your account. Do not place credentials in the downloaded code.

5

Configure delivery records

Create an SMS configuration set and an event destination for delivery/failure events, such as CloudWatch Logs with its required delivery role. Save the set’s name in AWS_CONFIGURATION_SET. This delivery destination is separate from the incoming SNS topic. The worker will long-poll SQS and delete each queue message only after the inbound job is committed.

6

Start and verify the worker

Fill every AWS value in .env from the resources just created. Start the worker and confirm HTTPS health:

Point the domain’s DNS at the host, then run:

Replace YOUR_SMS_DOMAIN with SMS_DOMAIN. Caddy obtains TLS and proxies to the private relay port. Expect {"ok":true} from health. Keep the sms-data volume: it stores message IDs, session keys, pending replies and suppression records. Do not scale this SQLite example to several processes.

Then run this read-only check inside the actual container:

Expect the confirmation without credentials being printed. A failure means the container’s credential chain, metadata access, queue Region or IAM permissions still need attention. This does not prove SendTextMessage permission or SMS delivery; test those below.

This path exposes no provider webhook: IAM authenticates SQS reads, the queue policy restricts SNS writes, and the worker checks the exact SNS TopicArn before decoding the message. SNS-to-SQS delivery needs no public webhook signature verification. Retain the envelope; enabling raw delivery would remove the TopicArn check.

Map messages and sessions

Keep the sender, agent release and reply direction consistent.

The server calls POST /v4/project/{projectID}/environment/{alias}/session with the runtime API key, then POST /v4/interact with the returned session token. The session and interact references own the full contracts. This route uses the Environment’s Published release; compiling a Draft alone does not release it. Transcripts identify these relay sessions as API conversations.

Test a customer conversation

Verify the real incoming text, agent session and delivered reply.

1

Run the offline checks

Before installing real provider credentials, run the archive’s tests with Node 22.13 or later:

These tests use synthetic provider events and mocked agent/sender responses. They check mappings, signatures, duplicate handling and restart behavior without sending a message. They do not establish live provider acceptance.

2

Send the known question and follow-up

From your separate phone, text “What are your collection hours?” to the AWS End User Messaging business number. Expect the prepared answer, for example “Northstar collection hours are 10 am to 6 pm.” Reply “Are you open at noon?” and check that the answer uses the same conversation. Inspect the intended project’s Transcripts. Confirm no launch greeting is sent separately.

3

Compare ingestion, sending and receipt

Inspect docker compose logs relay for the hashed job ID and phase:"accepted", then use the retained provider ID/reference to find the outgoing message. Confirm its sender is the business number, its recipient is the customer, and the phone receives one answer per turn.

Retain the send’s MessageId. Inspect the configuration set’s delivery/failure event in its CloudWatch destination and the phone. An SQS delete only proves local ingestion; it does not prove an agent answer or SMS delivery. SNS standard topics provide best-effort ordering and repeated events can occur.

4

Exercise continuity and recovery

Send a new question after restarting only the relay container; the stored session should continue. On a controlled recipient, test the configured STOP/START/HELP route and verify STOP prevents an agent send. Re-submit a captured authorized synthetic fixture only to a local/offline test receiver to check duplicate behavior; do not replay a production callback, which can trigger paid messages. Test a second customer to confirm their context remains separate.

The provider has the text but the relay has no job

Check the saved incoming route, callback authorization and payload family.

Inspect the relay’s SQS error log and dead-letter queue. Re-run the container credential/queue check, then verify the number’s Region, two-way SNS topic, queue subscription and restricted policies. Keep Raw message delivery disabled and confirm the envelope’s TopicArn equals AWS_SNS_TOPIC_ARN. A wrong or malformed envelope stays on the queue for retry and eventual dead-letter review. The public health endpoint does not establish SQS access; this transport has no provider HTTP callback or callback status code.

The relay records uncertain or held work

Resolve the original remote outcome before allowing another attempt.

Inspect the job with the README’s inspect command, the corresponding Transcript and provider log. An agent tool or send might have succeeded before its response was lost. The worker does not automatically retry this job and holds later messages for that conversation. Resolve the original outcome, then use the explicit recovery command; never clear the database to force a resend.

The provider accepts the reply but the phone gets nothing

Check delivery evidence, sender eligibility and recipient suppression.

Find the exact outgoing ID/reference in the provider log, inspect final delivery status and errors, and confirm the destination, sender registration, balance, country permissions and opt-out state. An accepted request is not a delivery receipt. If the account rewrites the sender, correct its two-way routing before launch.

Release and maintain the channel

Cut over the provider number and the published agent together.

1

Release the reviewed agent and relay

Publish the reviewed Chat Environment. Stop inbound routing temporarily or schedule the cutover, let queued work drain, and back up the persistent volume. Set the final VF_PROJECT_ID/VF_ENVIRONMENT and increase ROUTE_GENERATION to start fresh sessions on this deployment configuration. Recreate the relay container with docker compose up -d. The program refuses a route change while old queued jobs remain.

2

Verify the production route

Repeat the known question and follow-up through the final AWS End User Messaging number. Check the Published instructions, provider sender, destination and final delivery evidence. Keep the earlier route ready until this acceptance succeeds.

Update or disconnect the relay

Coordinate secrets, provider routing and the persistent message ledger.

Rotate a provider credential in .env, recreate the container and repeat the customer test. Rotate a webhook token/signing secret with the provider endpoint in the same change window. Keep IDENTITY_SECRET and the persistent volume stable; replacing them resets local sender identity and suppression history.

To stop this channel, disable the provider’s route/subscription first, then stop the worker after queued jobs drain. Restore the recorded prior provider route if required. Keep the volume/backup according to your data-retention policy; docker compose down -v deletes the message ledger and is not a recovery step. Number release and billing cancellation remain provider-account actions.

Use the up and down arrow keys to select a result, Enter to open it, and Escape to close the search.