Give Your Chat Agent a Voice — Luke Harries, ElevenLabs

AI Engineer · Intermediate ·🤖 AI Agents & Automation ·1w ago
Chat agents dominated 2025. Every product either went AI-first or got left behind. But text-in, text-out is already starting to feel dated. Voice is faster, more accessible, and opens up interaction paradigms that chat just can't touch — phone lines, Zoom calls, screen readers, ambient interfaces. In this talk, Luke Harries from ElevenLabs argues that the next upgrade for every chat agent isn't better prompts or smarter RAG. It's a voice layer. The problem is most teams have already built and tuned their chat agents. They don't want to throw that out. This session shows how ElevenLabs' Voice Engine wraps any existing agent in a few lines — handling turn-taking, speech-to-text, text-to-speech, and emotion-aware interruption detection — without touching the underlying logic. There's a live demo of converting a working chat support agent to voice in a single prompt, plus a look at the client and server SDKs, Shadcn-based UI components, and how tool calling still works through the wrapper. Speaker info: - https://www.linkedin.com/in/luke-harries
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

I Wrote a book for AI Scrum Masters. Here’s What’s Inside and Why I Built It.
Learn about a new book for AI Scrum Masters and its content, and understand how it can help in managing AI projects
Medium · Programming
Enterprise AI Architecture Trends in 2026: Multi-Agent Systems vs Single AI
Learn about the latest trends in Enterprise AI architecture, including the debate between multi-agent systems and single AI models
Medium · AI
AMRs in Indian warehouses: How 3PL and e-commerce firms can make automation work
Learn how Autonomous Mobile Robots (AMRs) can improve warehouse efficiency in India's growing e-commerce and logistics sector
Dev.to AI
SEARCH
Learn how AiFinPay SDK empowers AI agents with seamless financial integration, and how to apply it in your projects
Dev.to AI
Up next
How do I use custom user data with AL2023 Amazon EKS nodes?
Amazon Web Services
Watch →