Build a Voice Agent That Holds a Live Call on Telnyx Edge Compute

Telnyx has published a code example demonstrating a voice agent built on its Edge Compute platform that can hold a live phone call. The agent answers inbound calls, streams transcription, uses Telnyx AI Inference to generate replies, and speaks them via text-to-speech, looping back to listening. The implementation uses a VoiceAgent actor keyed by call_control_id and leverages the Agent SDK's Agent class for state management and zero-credential AI inference.

Getting an AI agent to answer a phone call is only the beginning. The harder part is keeping the call going. This example builds a voice agent on Telnyx Edge Compute that answers an inbound call, speaks a greeting, listens with streaming transcription, sends the caller's speech to Telnyx AI Inference, speaks the reply with TTS, and then goes back to listening. Code: https://github.com/team-telnyx/telnyx-code-examples/tree/main/edge-voice-agent-holds-call https://github.com/team-telnyx/telnyx-code-examples/tree/main/edge-voice-agent-holds-call The core flow is: php call.initiated - answer call.answered - speak greeting call.speak.ended - start transcription call.transcription final - stop transcription - run LLM turn - speak reply call.speak.ended - listen again call.hangup - persist final call state Each live call gets a VoiceAgent actor keyed by call control id . That actor stores: POST /webhooks/voice receives Call Control webhooks GET /debug/call?call control id=<call id inspects actor state POST /debug/respond tests an LLM turn without a live call GET /health/liveness and GET /health/readiness support health checksThe VoiceAgent extends the Agent SDK Agent class from @telnyx/edge-runtime . It uses: this.messages.add to store caller and assistant turns this.messages.toOpenAI to format history for the model this.setState and this.getState for durable call state this.env.TELNYX.ai.openai.chat.createCompletion for zero-credential inference through the telnyx bindingThe model call looks like this: js const completion = await this.env.TELNYX.ai.openai.chat.createCompletion { model, messages: { role: "system", content: SYSTEM PROMPT }, ...history , max tokens: 200, temperature: 0.5, } ; The webhook handler speaks the returned text through Call Control TTS. The sample uses Call Control streaming transcription because the app owns the conversation loop. The caller speaks. Telnyx sends a final transcript. The app stops transcription, runs the LLM turn, speaks the reply, and starts transcription again after TTS ends. That gives you room to add your own logic: npm install telnyx-edge ship Set the Call Control API key as an Edge secret: telnyx-edge secret set TELNYX API KEY your telnyx api key Point your Call Control application webhook to: https://edge-voice-agent-holds-call-<id .telnyxcompute.com/webhooks/voice Then call the Telnyx number assigned to that Call Control application. Before shipping this pattern for real callers, I would add: But even as a starter, this is a useful reference for building a voice agent that can actually stay on the call. Resources: