“Voice makes AI feel less like a tool and more like a natural part of the experience…LiveKit gives us the scalable foundation to bring those voice experiences to life at enterprise scale, without sacrificing flexibility.” Jonathan von Rüden, @SAP's Chief AI Officer.

Oh! Want to see how I did it?? 👀

Voice cloning is now available on LiveKit Inference. We’re launching with @inworld_ai and @cartesia. Clone a voice once and use it across multiple TTS providers, with automatic fallback to the same voice if a provider fails mid-call. Free to create and available on all paid plans today.

We shipped Agent Console, a realtime debugging surface for voice agents. Talk to your agent and see the entire pipeline live, from audio and latency to tool calls, transcripts, and participant state. Available now in the LiveKit Cloud dashboard.

How can a voice agent tell when you’re actually interrupting it? VAD is too sensitive—laughs, “mm-hmm,” or a sneeze shouldn’t stop the agent. We trained an audio model for adaptive interruption handling so agents can distinguish real interruptions from noise.

Our @DeepgramAI plugin now supports mid-stream control messages for Flux, so you can update keyterms in real time as conversational context evolves, without disconnecting and reconnecting. Watch me add a keyterm in real time for my name, which every STT always gets wrong!

RT @livekit: Grok's Text to Speech API is now available in LiveKit Inference. Natural, expressive voices with low-latency streaming. Multi…

Built a skill that lets you run your own voice agents w/ any model on your Rabbit r1, including models running locally on your home hardware. ‘npx skills add ShayneP/rabbit-r1-livekit-skill’ Then just tell Claude or Codex what you want and scan the QR code at the end.

Partnered with @livekit to help bring this shader to voice agents. Cool project!

Introducing Agents UI, an open-source @shadcn component library for building polished React frontends for your voice agents. Audio visualizers. Media controls. Session management tools. Chat transcripts. All wired to LiveKit Agents. Install via the shadcn CLI and own the code.

AI avatar LiveKit Agents demo: a healthcare intake assistant powered by @Anam__ai that guides someone through a form. LiveKit is the developer platform for real-time voice, video, and AI agents, with WebRTC transport plus the tooling to build, run, and observe agents in production. Try it for yourself and let us know what you think: livekit-anam.vercel.app

Come join us at our next Physical AI Meetup, where we'll be discussing the challenges of deploying robots in homes with @tonyzzhao from @sundayrobotics, @itsdanielho from @1x_tech, and @kaandogrusoz from @weaverobotics! 🤖🤖🤖 luma.com/physical-ai-meetup-…

We learn to speak before we learn to read. Voice is the most natural interface we have. We just raised a $100M to make building voice AI as easy as a web app.

TTS-1.5 by @inworld_ai is out, and that means I get to build another interactive demo! There's no better voice provider for this kind of game, the price is ridiculously low and the voices have tons of character. Check out the demo where I play an interactive voice-first RPG.

Pretty amazing what you can build on a $30 ESP32 smart watch. Using @livekit ESP32 SDK & @xAI's new voice models!

Happy holidays from LiveKit! 2025 was incredible. We launched: - Agent Builder - Phone Numbers - Observability - Agents on Cloud - Node.js Agents - Inference - and more.. Plus an amazing DevDay with 200 developers. Grateful for this community. Here's to building more in 2026!

We partnered with @EspressifSystem to ship a full-featured LiveKit SDK for ESP32 microcontrollers, optimized for realtime media on resource constrained devices. From wearable assistants to AI video avatar intercoms to smart security cameras, there are so many things you can now build on tiny hardware. blog.livekit.io/livekit-sdk-…

This is a big deal. Most of the voice AI community says that speech-to-speech models aren’t ready for production use cases. Two reasons: 1. Reliability (more hallucinations) 2. Cost (s2s models are expensive) On (1), Grok’s Voice Agent API is already running at large scale across Grok’s apps, in Tesla vehicles, and in call centers. There’s more work to do, of course, but progress is being made quickly. On (2), you get SOTA performance for $0.05/minute, which meets or beats aggregate cascade model (STT LLM TTS) pricing. Excited to partner with @xai on this launch — you can build a custom Grok Voice Agent with workflows, tool calling, the whole shebang, in a few lines of @livekit code. The future of speech-to-speech is bright!

Excited to launch our updated end-of-turn detection model! 39% average error rate improvement across 14 languages, and much smarter handling of structured data like phone numbers & emails.

Join us for LiveKit DevDay, happening Nov 18 in San Francisco. Attend the keynote (3–4 PM) virtually or in person to see new product launches and hear the latest on voice AI. If you can’t make the keynote, LiveKit DevDay is an open house! Stop by anytime from 2–7 PM for hands-on demos and office hours. Register Now: luma.com/live-kit-dev-day