Build a Live Call Transcription Agent on Telnyx Edge Compute

Call recordings are useful, but they are usually passive.

This example turns a live phone call into something your app can use right away.

The edge-call-transcription-agent

example answers an inbound call on Telnyx Edge Compute, starts streaming transcription, stores final transcript segments in an Agent SDK actor, summarizes the call after hangup with Telnyx AI Inference, persists the record, and sends the summary by SMS.

Code: https://github.com/team-telnyx/telnyx-code-examples/tree/main/edge-call-transcription-agent

The app is a TypeScript Edge Compute function with two Agent SDK actors:

TranscribeAgent

• one actor per callTranscriptRegistry

• one shared actor for listing stored transcriptsThe call flow:

call.initiated
  -> record call state
  -> answer call

call.answered
  -> speak greeting

call.speak.ended
  -> start inbound transcription

call.transcription
  -> append transcript segment

call.hangup
  -> summarize
  -> store
  -> SMS summary

POST /webhooks/voice

receives Telnyx Call Control eventsGET /

serves a lightweight dashboardGET /transcripts

lists recent stored transcriptsGET /transcripts/:call_control_id

fetches one transcriptGET /debug/state?call_control_id=...

shows live actor stateGET /health/liveness

and GET /health/readiness

are health checksStreaming transcription arrives as many events.

The app needs to remember:

An actor per call makes that state easy to hold.

The source maps each call_control_id

to one TranscribeAgent

, so the transcript can build up across webhook events.

After hangup, the actor queues a finalize pipeline:

summarize -> store -> notify

The summary uses Telnyx AI Inference through the Edge Compute binding:

this.env.TELNYX.ai.openai.chat.createCompletion({
  model,
  messages: [
    { role: "system", content: SUMMARY_SYSTEM_PROMPT },
    { role: "user", content: transcript },
  ],
  max_tokens: 200,
  temperature: 0.3,
});

The default model is:

zai-org/GLM-5.2

The prompt asks for a concise SMS-friendly summary under 320 characters.

Once the summary is ready, the app sends it over Telnyx Messaging:

this.env.TELNYX.messages.send({
  from: this.env.SMS_FROM,
  to: this.env.SMS_TO,
  text: state.summary,
});

Use placeholders in examples and configure real numbers only as private runtime values:

SMS_FROM=<TELNYX_SMS_FROM>
SMS_TO=<SUMMARY_RECIPIENT>
git clone https://github.com/team-telnyx/telnyx-code-examples.git
cd telnyx-code-examples/edge-call-transcription-agent
npm install

Set secrets:

telnyx-edge secret set TELNYX_API_KEY <YOUR_TELNYX_API_KEY>
telnyx-edge secret set SMS_FROM <TELNYX_SMS_FROM>
telnyx-edge secret set SMS_TO <SUMMARY_RECIPIENT>

Deploy:

telnyx-edge ship

Point your Call Control app webhook to:

https://edge-call-transcription-agent-<id>.telnyxcompute.com/webhooks/voice

Then call the Telnyx number assigned to the Call Control application.

Before using this with real callers, add:

The useful pattern is simple: live call events, durable state, AI summary, and post-call notification in one edge app.

Resources: