Today is a day I’ll never forget. I grew up in Cupertino. My dad was a tech founder in the 80s/90s. I was in YC S07. LiveKit is my 5th company. The first 4 didn’t work out. I’ve had a lot of advantages — it still took 20 years to get here. Founders: keep taking shots.

Your whole voice stack, free for a year on LiveKit. $10K in Cloud credits + a year of Scale + $7K in partner inference credits ($1K each: @googlegemma, @DeepgramAI, @inworld , @rimelabs , @FishAudio, @AssemblyAI, @GradiumAI.) One workspace. No provider keys. Apply now: livekit.com/startups

GPT-Live-1 @openaidevs is now supported in LiveKit Agents. It's full-duplex, so it listens and speaks at the same time instead of taking turns, and it hands reasoning and tool calls off to a backend model so a slow lookup doesn't leave your agent sitting in dead air. Same `AgentSession` API. New plugin: `GPTLiveModel`. Get started: docs.livekit.io/agents/model…

LiveKit Connectors are generally available today. They bring calls from @twilio Programmable Voice and @WhatsApp Business Calling into a LiveKit room as a regular participant, so your agent can answer there with no SIP trunk to provision and nothing new to host. Read the full article: livekit.com/blog/introducing…

Realtime TTS-2 is GA today, now the #1 model on Artificial Analysis and fastest TTS in the world of its class. The research preview got far more usage than expected. That experience went back into research and today's GA model represents the biggest leap in Inworld's history.

LiveKit in the wild 👀

Introducing Pemba The first robot to attempt Everest This fall powered by @livekit, with support from @AskVenice , @eastworlds_io and Reflex

Per-minute metering is an artifact of the telecom industry. Per-second is agent-native.

Protect sensitive data without giving up voice agent observability. LiveKit PII Redaction automatically removes personal information from transcripts and recordings before it is stored. It is included with LiveKit Agent Observability at no additional cost. Read more: bit.ly/4gJ1ex7

1/ Today we're launching Expressive mode in LiveKit Agents. Most voice agents deliver every sentence in that same, upbeat register we all know and hate (including bad news). Expressive mode makes your agent sound like it registers what the caller is actually feeling.

Here's our take on benchmarks for voice: they're hard to get right, but critical if you're building humanlike AI. Our live benchmarks page is up now: pass rate on real agent scenarios, latency including the worst-case (p99) moments, side-by-side conversation comparison between models over time. Feedback welcome! livekit.com/benchmarks

Waymo pick up and drop off is so bad.

WARP is coming to LiveKit soon!

The YC Office Hours Simulator was a huge success!  These were physical booths at Startup School where attendees could talk to AI avatars of the @ycombinator Partners. We interviewed over 100 attendees about their experience. Here's a recap 👇️ 1️⃣ The #1 complaint = people wished they could talk longer! Most conversations were 10min (the enforced time limit). There was a line of people waiting to talk to the avatars for the entire two-day conference 2️⃣ Some people wished the avatars were meaner or harsher. This was interesting! 3️⃣ Many people took notes (pen & paper, @meetgranola, or typing furiously) and said the conversation was genuinely helpful. Several folks waited in line for a 2nd or 3rd conversation :)  4️⃣ People said the avatar aspect felt different than a chatbot. The "face-to-face" interaction helped them feel a stronger connection, pay more attention, and open up more. A few people even said they forgot it was AI!  5️⃣ The magic moment = when people realized the avatars knew who they were and what they were working on (based on their conference application) 🪄 The "brains" for Office Hours Simulator was trained on hundreds of hours of real office hours. It truly simulated how each Partner talks and the types of questions they like to ask.  Built by the one-and-only @snowmaker and YC software team (so impressive) 👏 Powered by: @lemonslice (live avatars), @elevenlabs @ElevenLabsDevs (voice AI), @livekit (webRTC infra), @deepgramai (voice AI), @ployai (animations), Hamming AI (testing), and many other great companies.

Mom: what do you think of Claude Tag? Me: haven't gotten a chance to use it. I just heard @jack has a new thing in this direction, actually. Mom: yeah Buzz, i know. 💀

LiveKit Unity SDK 2.0.0 is out of Developer Preview. Bring real-time voice, video, and AI into your Unity game. Build voice chat, live streaming, robot teleoperation, and voice AI agents as NPCs that listen, respond, and react. Give it a try today and let us know what you think.

Every millisecond counts for voice agents. Introducing Gemma 4 31B on LiveKit Inference! Optimized for real-time voice agents: - 354ms time to first audio - 192ms time to first token - Beats GPT-4.1 in agentic tool use (31B achieves 76.9% on tau2bench) Fast, capable, and efficient!

🤯

Until now, it was impossible to synchronize video frames with other sensor data such as LiDAR, IMU, joint states, etc. streamed over WebRTC with microsecond level precision. Introducing Video Frame Metadata in LiveKit. Stamp every frame with your ground-truth timestamp, frame ID, and metadata. livekit.com/blog/frame-metad…

Some great lessons in building a performant real-world voice AI application.

Everyone's asking what AI can do for their job. We asked if it could teach a 6-year-old. Introducing Ello 2.0: reading, math & more for ages 4-9. Free tier for all. If we want AI to force-multiply humanity, let's start with teaching our youngest.