WeAreDevelopers LIVE Oct 14, 2025

Minimal infrastructure for Real‑Time Phone Agents: transcripts in, responses out

Chris Heilmann , Daniel Cranney , Marius Obert , Staff Evangelist At Twilio

Skip the massive architectural hurdles of voice AI. Deploy real-time, context-aware phone agents in under 100 lines of TypeScript with Twilio Conversation Relay.

Pause
Mute Enter Fullscreen
#1 about 2 min

Minimal infrastructure for real-time phone agents

An overview of the minimal components required to build an AI agent accessible via standard phone calls.

#2 about 3 min

Comparing voice and text interaction speeds

Voice inputs offer a hands-free alternative while requiring consideration of cognitive load and synchronous processing limitations.

#3 about 3 min

Challenges of managing voice architecture and latency

Building a voice interface requires careful orchestration of speech recognition, interruption detection, and language model pipelines.

#4 about 3 min

Abstracting complexity with Twilio Conversation Relay

Twilio Conversation Relay manages speech-to-text, text-to-speech, and latency optimizations while decoupling core application logic.

#5 about 8 min

Building a WebSocket server with Deno

A Deno-based WebSocket server parses TwiML instructions, configuring voice models and handling initial connection headers.

#6 about 3 min

Connecting a Twilio phone number to the webhook

Purchasing a local phone number and linking its programmatic routing directly to the deployed web server.

#7 about 6 min

Integrating OpenAI for real-time streaming responses

Streaming large language model outputs minimizes latency by speaking words immediately as language chunks arrive rather than waiting for complete sentences.

#8 about 5 min

Maintaining conversation history and preserving context

Session memory stores historical conversation threads and maps unique request IDs across concurrent connection streams.

Matching moments

2:13 min

Building real-time phone agents with minimal infrastructure

Chris Heilmann +2 · LIVE

4:16 min

Addressing latency and architecture in voice agents

Chris Heilmann +2 · LIVE

1:10 min

Architecting a web real-time communication stack for agents

Nathaniel Okenwa Nathaniel Okenwa · World Congress 2025

42 sec

Delivering dynamic voice interactions via ElevenLabs

Alexandra Mihai Alexandra Mihai +2 · Europe 2026 Virtual

1:18 min

Introduction to real-time communication programming interfaces

Nathaniel Okenwa Nathaniel Okenwa · World Congress 2025

8:23 min

Building a Deno server for Twilio integrations

Chris Heilmann +2 · LIVE

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 24, 2026 · 11:00–11:30

Stage 2

From Stateless to Stateful: Real-Time Voice & Messaging Agents with Twilio and AWS

Rishab Kumar

Staff Developer Evangelist @ Twilio

Rishab Kumar
Open session

World Congress 2026 North America

September 25, 2026 · 12:30–14:30

Stage 8

Build a Voice AI Agent with Twilio Agent Connect and Gemini Flash

Rishab Kumar

Staff Developer Evangelist @ Twilio

Rishab Kumar
Open session

World Congress 2026 North America

September 24, 2026 · 11:20–11:25

Outdoor Stage

Finding the Edges: Testing, Evaluating, and Monitoring Voice AI Agents Before Your Users Do

Matt Wyman

CEO at Okareo

Matt Wyman
Open session

World Congress 2026 North America

September 24, 2026 · 16:10–16:40

Stage 5

From Software Agents to Physical Devices: Inside the Agentic Hardware Stack

Michael Yuan, Vivian Hu

Michael Yuan
Vivian Hu
Open session

World Congress 2026 North America

September 24, 2026 · 13:30–14:00

Stage 5

The Pedagogy of AI: Agents, Agency, and a World Beyond Coding Tutorials

Alex Goldman, Andrew MacLean

Alex Goldman
Andrew MacLean
Open session

World Congress 2026 North America

September 24, 2026 · 14:10–14:40

Stage 1

Anatomy of an AI Request: Where Latency and Cost Are Really Born

Dan Fu

VP of Kernels at Together AI

Dan Fu