Give Your Chat Agent a Voice
summary
Claims that an ElevenLabs Voice Engine wraps any existing agent in a few lines and handles turn taking, speech to text, text to speech, and interruption detection are demonstrated with concrete tech: uses Scribe for STT and V3 for TTS, a server SDK that proxies sessions, and a client SDK plus Shadcn UI components. A live demo shows a working support agent converted to voice with one prompt converts agent to voice, including emotion-aware interruption detection, and the wrapper preserves existing tool calling.
AI-written summary · about
chapters (9)
- 0:00Introduction to voice-first chat agents
- 0:20The shift from text-based to voice-based interactions
- 1:43Evolution of agent architecture and challenges of rebuilding
- 2:47Introducing the ElevenLabs Voice Engine
- 3:32Overview of the server and client SDKs
- 4:36UI components and deployment demo
- 5:56Summary of voice engine integration paradigms
- 6:37Predictions for the future of AI agents
- 7:00Q&A: Handling tool calling and integrations
related talks
12mReal-time voice agents with ElevenLabs and AI SDK
17mBuilding Effective Voice Agents
01h 02m[Full Workshop] Building Conversational AI Agents
10mBuilding Conversational AI Agents at Scale
01h 26mBuilding voice agents with OpenAI
10mEmbracing the Voice Revolution
33mDesigning Voice Agents for Real Conversations
17mAI Voice agents for the Business and Phone Channels