Pinned
LiveKit
424 posts
Open source framework and cloud platform for building voice, video, and physical AI agents.
livekit.com
- Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in
00:00 - OpenAI’s Realtime API is here! We created 4 new resources to help you start building with the same stack OpenAI uses for Advanced Voice in ChatGPT. Bookmark this thread for when you get Realtime API access:
- You can now deploy AI voice agents to LiveKit Cloud. We handle: • Stateful load balancing • Capacity management • Draining and instant rollbacks • Operational observability
00:00 - Agents 1.2 for Python is now released! This includes our new test framework, observability w/ OpenTelemetry traces, half-duplex support (swapping a realtime model's voice w/ your own TTS), significant improvements to end of turn model (now with Hindi) and more! Let's dig in ...
- Introducing LiveKit Inference — a new cloud service that gives you access to the most popular voice AI models with just your LiveKit API key. We manage rate limits for you, report on usage, and consolidate billing. All LiveKit Cloud plans now include free monthly inference
00:00 - We’re excited to announce LiveKit has raised $22.5M to build infrastructure for realtime voice and video-driven AI applications! 🤖🎙📹 We’re proud to partner with amazing investors including Altimeter, @Redpoint, @JeffDean, @eladgil, @AravSrinivas & @amasad .
- We know you're been waiting a long time for this: Agents 1.0 for Javascript is now officially released! Let's dive into some of the most important features of this major release.
00:00 - Check out the live demo here: groq.livekit.io As usual, all of the code that powers this demo is open source! github.com/livekit-exampl…I use @GroqInc LLM + transcription a lot, but now they have support for TTS models! Even better—it's available immediately as a LiveKit Agents plugin. The model sounds great, and we've got an open source demo that you can try out yourself if you want to hear it on your own.
00:00 - When AI is as smart as a human, we’ll interact with it like we do with each other. Human interaction is real-time and multimodal: We use → 👀👂👄 AI uses → 📹 🎙️🔈 Today we're launching a stack for building real-time multimodal AI apps.
- Say ‘hello’ to KITT — AI that you and your group can meet with over a video call. KITT combines ChatGPT with WebRTC. Check it out:
00:00 - The LiveKit Agents @cartesia plugin now supports streaming and continuations. tldr is now you can start generating speech before your LLM finishes generating text Here's a little app where you can try it: cartesia-assistant.vercel.app
- Introducing three new features to help you build better voice agents: 🤖 Agent Builder—guided build in minutes 📞 Phone Numbers—buy directly, no SIP setup 👀 Agent Observability—debug in one place Learn more 👇





