Try @Grok vision

We've got instant support for the new rime models, just change the model and speaker in your Agent TTS config!

MCP 🤝 AI Voice Agents Combine LiveKit Agents, OpenAI , AssemblyAI, and Supabase's MCP server to create a talking AI assistant to interact with your Supabase database! Check it out 👇 assemblyai.com/blog/mcp-voice…

While I'm waiting for Llama API access, you can already use it with LiveKit!

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at

I'm super pumped about this one—we partnered with Tavus on a plugin to simplify the process of building realtime AI avatars. There's a crazy amount of complexity to realtime procedural video generation that we just handle. In two lines of code—add an avatar to any agent.

Want to build AI voice agents that respond in a flash? At Daytona.io Builders SF May '25, I'm explaining WebRTC for quick audio, AI model setups (pipeline vs omni), & nailing smooth conversational flow. Come learn how it's done! lu.ma/qgp611my

Now you can (vibe)code during the day 😎 Introducing light mode for LK docs

This happened. Don't miss out livekit.io/join-slack

This year has been all about reasoning — faster inference, more capable agents, and real-time decision-making. Last week I joined dsa, CEO of LiveKit (powering voice for OpenAI, Character AI, xAI), to ask: What does reasoning look like in real-time voice AI — and how does

I built a voice shopping assistant that can be used on every Shopify store in a DAY—that's how good new storefront MCP support from Shopify Developers is 🤯 Wired up w/ LiveKit + Cartesia. Turn detection, interruption handling, all audio over WebRTC. Code and architecture in 🧵

Ink-Whisper is fast! Cartesia released a new STT model yesterday, and it's as fast as you'd expect. Streamed transcription finishes in <100ms—before you can say the next sentence. I used it to build a live teleprompter that follows along with what you're saying. Code in 🧵

Cue the lights 😎 Whether you prefer a brighter workspace or just need a break from the dark, you can now switch to light mode in LiveKit Cloud.

🚀 Deploying a real-time AI voice agent with ~500ms latency — globally. We just dropped a full breakdown of how to assemble a low-latency speech pipeline using STT, LLMs, and TTS, optimized for production use. Here’s how we did it with LiveKit 🧵

We just made state-of-the-art TTS 20x more affordable. $5 per million characters. And we're open sourcing the training and modeling code (built on Llama). Because scaling voice AI shouldn't break your budget. Technical Details → Inworld.ai/blog/introduci… Why and how we did it

#AmazonNova Sonic now integrates with LiveKit’s WebRTC infrastructure 🚀🎉⚡ This integration streamlines the development of voice-first AI application by removing the complexity of managing real-time audio infrastructure. #AWS #generativeAI 👉 go.aws/4lhtJ4P

Did you know you can access Inworld AI TTS via LiveKit's agents framework plugin? Now, you can create previously unimaginable, real-time voice experiences such as multiplayer games, agentic NPCs, customer-facing avatars, live training simulations, and more. It’s studio