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

AI Engineer

ElevenLabs is previewing a new 'Voice Engine' product that lets developers add voice capabilities to existing chat agents without rebuilding them from scratch. The SDK wraps any existing chat agent with a voice layer handling speech-to-text (using their Scribe model), text-to-speech (V3), and advanced turn-taking with emotion/context awareness. Integration requires minimal code — a few lines for a client-side widget, plus server-side SDK support. The product also unlocks telephony and CSAS out of the box, and includes UI components styled after shadcn/Vercel. A coding agent skill will allow converting a chat agent to a voice agent in a single prompt.

Give Your Chat Agent a Voice — Luke Harries, ElevenLabs