LiveKit

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.

In NYC for AI Agent Conference? As an official partner of #AIAgentWeek, we're hosting a Voice AI speakeasy with @Cartesia at Madame George, a cocktail bar in Midtown. Join us on Tuesday, May 5 from 6-9pm. Space is limited, request an invite at the link below. luma.com/livekit-cartes…

Visit our guide to learn more about prompting Gemini 3.1 Flash TTS: livekit.com/blog/gemini-3.…

With the right prompting, Gemini 3.1 Flash TTS is one of the most expressive voice models ever. It also prompts differently than anything else we’ve tested. We built a guide on how to get the most out of it, including how to use "Director's Notes" for realism.

Catching 'Building Agents with Gemini' at #GoogleCloudNext? @codeSTACKr is co-presenting with the Google DeepMind team in the Startup Hub. He'll show how LiveKit's open source WebRTC infra and Agents SDK get a Gemini voice agent running on any device: phone, browser, or robot.

We're at #GoogleCloudNext in Las Vegas this week. Stop by the AI Garden in the Startup Hub and try our VIP concierge demo built on Gemini and LiveKit. Scan your badge for a personalized Next agenda and a keepsake video. @codeSTACKr is running the demo. Come say hi.

Here's the full article: livekit.com/blog/observer-…

We published a guide on how to do parallel processing inside an agent session, with policy violation checks and guardrails as the example. Check out the demo and read the full post for all of the code you need to apply this pattern to your voice agents.

Try the xAI x LiveKit integration today: docs.livekit.io/agents/integra…

xAI STT is live. You can now run a complete cascaded voice agent pipeline on xAI (STT + Grok + TTS) through LiveKit Inference with one API key, giving you more control, full visibility, and easy component swaps.

We did it! We built the fastest interactive avatar model Introducing LemonSlice-2.1 𝘍𝘭𝘢𝘴𝘩 ⚡ Here’s how we did it using @modal and @livekit 👇 (note: it was not easy)

Blog: livekit.com/blog/livekit-w…

Repo: github.com/livekit/liveki…

We launched livekit-wakeword, an open-source library that lets you train a custom wake word model from scratch with a single command. It handles synthetic data generation, augmentation, training, and ONNX export all in one shot.

10k stars on livekit/agents We released version 1.0 a year ago. Today, our customers are building agents for healthcare, finance, insurance, education, robotics, and more. It’s been amazing to see our community grow over the past year. Thank you to everyone building with us.

Give the Keyframe Labs avatar plugin a try and let us know what you think. Keyframe Plugin Docs: docs.livekit.io/agents/models/… Example repo: github.com/livekit-exampl…

We built a demo with Keyframe Labs avatars on the LiveKit Agents Framework. The avatar doesn't just lip-sync. It picks up on the emotional context of the conversation, and you can see it in its face when the mood changes. It can also hand off the conversation to a different agent without reconnecting. The new agent fires RPCs to update the UI in real time. LiveKit x Keyframe plugin and sample repo in the thread.

Read more in our blog: livekit.com/blog/agent-con…

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.

If you prefer to read, here's the full article: livekit.com/blog/understan…

"How do I decrease the latency of my voice agent?" is our #1 question. The answer depends on your pipeline bottlenecks. We recommend co-locating your agent with models, evaluating faster models, and practicing good tool hygiene. Check out our playbook for more tips.