🚢 Agents for Python 0.12.15 + Agents for Node.js 0.7.0 Releases 🚢 We’ve recently dropped some new updates to both the Python and Node.js distributions of the Agents framework, so be sure to grab the latest for your platform of choice, including: Agents for Python 0.12.15 • Improved performance of OpenAI TTS by switching to use Opus encoding (#1494) • Improved exception logging (#1490) • Fix interrupting nested speech from

before_llm_cb

(#1504) • Add cache tokens in

CompletionUsage

dataclass (#1478) Agents for Node.js 0.7.0 • Introduces support for Turn Detector model (#225) • Replace transcription forwarder with synchronizer (#301) • Gracefully fail on StreamAdapter errors (#299) • Skip TTS on empty LLM output (#293) • Clearer timeout handling for drain (#277) • Fix feeding null LLM input (#296)

🚨 Action Required 🚨 Managing package requirements prior to Agents for Python 1.0 release We’re nearing the release of Agents for Python v1.0 which will contain some breaking changes for agents that have been built with versions prior to v1.0. We’ll be publishing a detailed migration guide soon in order to help you navigate these changes as you upgrade your agents to use the new v1.0 package. Since v1.0 contains changes that will need to be made to your agents, we strongly recommend that you proactively manage your upgrades to the Agents for Python packages (

livekit-agents

and all associated plugins) to ensure that you don’t upgrade until you’re ready. For instance, if you’re using a pip requirements file, you can add a version constraint to each package to restrict to only versions earlier than v1.0:

livekit-agents>=0.12.6,<1.0.0

We’ll share some more details on v1.0 soon - if you have any questions in the meantime, please reach out as we’re here to help!

🚀 Analytics v2 for LiveKit Cloud is here!!! 🚀 We rebuilt our analytics from the ground up to support scale at any size for any use case. Agents, streaming, and now telephony metrics! Some other things to 👀 when you're checking the new dashboard: • Faster load times: Background data processing and streaming updates makes everything load a lot faster. • Streamlined navigation: Breadcrumb system, redesigned layout, and improved search for quick session and participant insights. • New insights: Connection minutes, quality metrics, latency stats, and 🎉 telephony call logs 🎉 . • Enhanced controls: Filter, slice, and share dashboard states easily with URL params and live updates. We built these updates directly from your feedback. Check out the announcement and let us know what you think. More feedback = better features 😄 https://x.com/livekit/status/1902010421264937246

🚀 Krisp support in Python! You can now apply enhanced noise cancellation directly inside your agent or other Python app. This is available to all LiveKit Cloud projects at no extra cost. This has a few distinct benefits over client-side integrations: • Support for Krisp's Background Voice Cancellation (BVC) model - filter not just noise but also background speakers that would otherwise confuse turn detection and transcription processes in voice agents. • Universal client support - This filter works on audio coming from anywhere, including native apps, web, telephony, and even our Unity SDK • Simpler integration for multi-platform apps - integrate the filter in just one spot instead of adding the package to Swift, Android, Flutter, and JS apps Integration couldn't be simpler:

agent = VoicePipelineAgent(
    # .. STT/TTS/LLM/etc ..,
    noise_cancellation=noise_cancellation.BVC()
)

The package and documentation are available on PyPI. Node.js support is in the works and will be ready soon. Give it a try and let us know what you think! https://pypi.org/project/livekit-plugins-noise-cancellation/

A few folks in the community have suggested the idea of open office hours and I think it sounds like a good idea. Next Thursday at 9am US Pacific/12pm US Eastern I will host an open office hour livestream where folks can raise their hand and ask questions and get answers. I will share a link here for the call 10mins before the call.

🤖 Python Agents 1.0 RC Hey everyone! We've just rolled out a big update for Python Agents! Thanks to all your feedback over the past year, we've made the framework cleaner and more flexible. Here's what's new: ✨ Multi-Agent Support ◦ Break down complex workflows into simpler tasks. 🔄 Unified AgentSession Class ◦ We've merged VoicePipelineAgent and MultimodalAgent into a single AgentSession. ◦ Handles both pipelined models and the Realtime API. ⚙️ Flexible IO and overides ◦ Flexible IO system to take input/direct output as you wish ◦ pre/post-process each part of the pipeline 📡 Improved Text Stream Handling ◦ Text input/output are now fully integrated as first-class features. 🎛️ API Updates ◦ `generate_reply`: Generate dynamic responses from LLMs. ◦ `say`: Respond with static text or pre-synthesized audio. ◦ `interrupt`: Interrupt your agent whenever needed. 🐞 Lots of Bug Fixes Check out the examples in the repo and the new docs site! To try it out:

pip install "livekit-agents[openai,silero,deepgram,cartesia]~=1.0rc"

Let us know what you think!

Reminder that in one hour we will have an open office hour (LiveStream). You will be able to raise your hand and ask questions. We will have several folks form the LiveKit staff on hand to answer the questions. (I will add additional details in the thread)

🚀 LiveKit Agents 1.0 is here! The wait is over — we’ve shipped a major upgrade to our open-source framework for building voice AI agents. Agents 1.0 introduces support for structured workflows, making it dramatically easier to build closed-loop agents for scheduling, support, and automation use cases. Key updates include: • Unified AgentSession interface for all agent types, real-time or pipeline • Modular pipeline nodes for easier customization • Synchronized captioning • Multilingual semantic turn detection • Streamlined function tool definitions (function_tool) • Fine-grained control over STT → LLM → TTS flows We’re also kicking off a closed beta for Cloud Agents, our fully-managed hosting platform for deploying agents at scale. 📚 Explore what’s new → https://docs.livekit.io/agents 🔄 Migration guide → https://docs.livekit.io/agents/start/v0-migration/ ⚡ Examples → https://github.com/livekit/agents/tree/main/examples/voice_agents 📝 Blog post → https://blog.livekit.io/livekits-series-b/ 🤖 Cloud agents beta signup → here 💬 Let us know what you’re building — and if you’re excited, please reshare the blog post or give it a boost on social! Every bit helps 🙌

Come Joins Us. Devs building in voice and video AI, we’ve got something special cooked up for next week — on 4/30, we’re doing a fireside chat with @juberti in SF. Justin is a legend. He created the WebRTC protocol, led dev for Google Meet and Stadia, started @FixieAI, and is now the Head of... https://x.com/livekit/status/1914335043549368761

Hi everyone! We just created a brand new #C08QMJD9J9G channel for everyone that's using LiveKit for robotics, machines, and other embedded platforms! Please drop in and say hi. We'd love to hear what you're working and how we can make LiveKit even better for your use case! 🦾🤖🚗

Hey LK community, @flaky-sundown-18688 and I worked with Andrew Ng on a free short course (< 1h) about building AI voice agents. We a cover some things we hope will be helpful/interesting: • the architecture of an AI voice agent • voice AI network protocols (HTTP vs. WebSocket vs. WebRTC) • building a basic voice agent with STT ⇒ LLM ⇒ TTS • optimizing latency with semantic VAD, interruption handling, and streaming requests • digging into performance metrics across your voice pipeline If you take the course and have any questions or feedback, DM one of us or post in this thread! 🙏 Links Andrew’s post: https://x.com/AndrewYNg/status/1920161212312268988 Course: https://www.deeplearning.ai/short-courses/building-ai-voice-agents-for-production/?utm_campaign=livekit-launch&amp;utm_medium=partner&amp;utm_source=livekit

Tavus Avatars!!! https://x.com/shayneparlo/status/1920562746069852339 https://blog.livekit.io/bringing-ai-avatars-to-voice-agents/

Now you can code during the day! 😎 We’re excited to announce light mode for LiveKit Docs 🎉 This has been one of the most requested features from our community, and we’re thrilled to make it happen. Thanks to all of you who kept it on our radar with your feedback! And this is just the beginning, we’re planning improvements to make light mode even better, and expand it to other surfaces soon. Give it a try and enjoy a fresh look for your daytime coding sessions

Hey LK devs 👋 Late last week, we crossed 10,000 members in this community. This Slack started in late 2020 with just a few close friends who’d heard we were working on a new project. Back then, LiveKit was an open source WebRTC engine for building video apps during the pandemic. Today we’re an AI infrastructure company with 50+ teammates across 14 countries. LiveKit software runs on billions of devices, and on some days, the LiveKit Cloud network sees as many concurrent sessions as Fortnite. Pretty wild. But none of this could have happened without you. Every question, suggestion, bug report, GitHub issue, PR, demo, and feature request — it’s all made LiveKit better. The time, energy, and patience you’ve poured into exploring and building with LiveKit is what keeps us going. From the whole core team: thank you. For the last four years — and for whatever we build together next. Cheers 🥂

Light mode in Cloud just dropped 😎 You asked, we delivered. Whether you prefer a brighter workspace or just need a break from the dark, you can switch it up anytime in User settings. Twitter https://x.com/livekit/status/1933548983403630890 LinkedIn https://www.linkedin.com/feed/update/urn:li:activity:7339315527611211776

Agents 1.2 🎉 Lots of features folks have been asking for. Also see #C0940P9MZR9 https://x.com/livekit/status/1946308428898402808

You can now deploy AI voice and video agents to LiveKit Cloud 🎉 We handle: • Stateful load balancing • Capacity management • Draining and instant rollbacks • Operational observability ⌨️ Get started with the docs: https://docs.livekit.io/agents/ops/deployment/ 📘 Learn more on our blog: https://blog.livekit.io/deploy-and-scale-agents-on-livekit-cloud/ ❤️ Like and share on social media: X and LinkedIn

Hey there, livekit devs! Agents JS 1.0 has finally landed 🎉, and we’re stoked to share it with you! We know some of you have been waiting a lonnnng time for this. Thanks for your patience! This release is jam-packed, bringing all the shiny features from Python 1.0 into the JS world: • Agent control with

generateReply

and

say

• Multi-agent workflows with handoffs • Integrated text-mode and transcriptions, compatible with all frontend clients • Full control over the pipeline via pipeline nodes • Metrics and events Ready to dive in? Check out the migration guide and quickstart to hit the ground running. Wanna give the dev team a virtual high-five? Give us a ⭐ on Github!

Hi everyone - we hope you're enjoying the new LiveKit Agents 1.0 for Node.js release! Now that the 1.x versions of LiveKit Agents for both Python and Node.js are stable and serving production workloads, we are planning to wind down support for v0.x versions of these SDKs. To streamline the agents documentation we will be dropping v0.x starting next week. Existing links will redirect to the latest documentation for v1.x. The v0-v1>migration guides will remain on the site for a while longer. This is a change only to documentation and not community support. Any existing v0.x agents will continue to work, as they are still built on a supported versions of the underlying LiveKit SDK.

Hi everyone-- We've just added a new #C09GBJY83C7 channel for documentation site bugs reports and feedback. Our Developer Products team will monitor this channel and investigate reported issues.

Introducing LiveKit Inference: A unified model interface for voice AI https://blog.livekit.io/introducing-livekit-inference/

If you have questions about the inference services be sure to check out the #C09J2AYGN0M channel

LiveKit CLI version requirements Heads up that starting this Friday, 10/10/25, you'll need to keep your LiveKit CLI up-to-date to manage agent deployments to LiveKit Cloud. This ensures that the CLI remains compatible with upstream breaking changes as the deployment API evolves to support new features. The current minimum supported version is 2.6.2. For upgrade instructions, visit the documentation: https://docs.livekit.io/home/cli/#updates Other features of LiveKit CLI are not affected. Let us know if you have any questions!

🚀 Official LiveKit Docs MCP Server --> https://docs.livekit.io/mcp This server gives LiveKit expertise to coding assistants like Cursor or Claude Code. It includes tools to browse and search the documentation, with more functionality coming soon. 1. Talk to it: Visit this live demo voice agent which has the new server installed. (Fun fact: Cursor built this agent from scratch, using this very MCP server!) 2. Install it: Click here to install it in Cursor, or run

claude mcp add --transport http livekit-docs <https://docs.livekit.io/mcp>

to install it in Claude Something extra While the MCP server adds expertise, a good AGENTS.md can add wisdom. So we've added a default AGENTS.md to both of our agent starter templates for Python and Node.js. Use these files so your coding assistant can build LiveKit Agents like a pro: --> https://github.com/livekit-examples/agent-starter-python --> https://github.com/livekit-examples/agent-starter-node If you have any feedback on the MCP server or the updated starter templates, please share it in the new #C09GBJY83C7 channel!

We just launched a new EU region for agents deployed to LiveKit Cloud! This means there are now two available regions: us-east and eu-central.. You must choose which region to deploy to at agent creation time. If you are using an older version of livekit-cli the decision of where the agent is placed is based on your nearest geo-region. In livekit-cli >= v2.12.7 you will be able to pass a flag on agent-create, or if none is passed, you'll be prompted to select a region. If you're using the https://github.com/livekit/deploy-action you can also set a region, otherwise the same dns rule will apply.

We’re hosting our first LiveKit DevDay, and would love for community members to attend! Join us to meet the team and fellow builders, and see what’s next for voice AI. At the event, you will learn about new product capabilities, experience live demos, and engage in deep dives with the engineers who build LiveKit. Event Highlights: • Keynotes from the founders • Product launches and demos • Office Hours with the Developer Success team • Happy Hour and networking Agenda: 2:00 PM – 3:00 PM: Check-in & Booth Demos 3:00 PM – 4:00 PM: Opening Keynote 4:00 PM – 7:00 PM: Demos, Deep Dives & Happy Hour If you can’t join us in person, we will have a livestream and virtual experience so that you can participate remotely. Stay tuned for more info after you register through the virtual option. Thank you for being a part of our wonderful community. We hope to see you there! Reserve your spot today at https://luma.com/live-kit-dev-day

https://livekit-users.slack.com/archives/C0940P9MZR9/p1762459205255079 Some bugs are still to be expected in this RC but we’re excited to share some of the features we are working on. To try it yourself, please install the specific version

1.3.0rc1

. This is the Python release python, JavaScript will follow shortly. • We have improved the console mode with a new look so you can more easily test your agent - try running any of our examples in

console

mode. • We have added a new SessionReport and on_session_end callback, giving you access to the whole chat history at the end of a session. You can see this in action in our drive-thru demo. • We have improved our turn detection model to work better for user inputs like email addresses and phone numbers. • Our new TaskGroup workflow lets you run multiple tasks concurrently. See this in action in our new SurveyAgent example, which will also demonstrate email capture. • We have added a new AgentHandoff class to give you better visibility into multi-agent setups. The session history will now contain entries of type

agent_handoff

# Agent on_enter
  handoff_items = [
      item for item in self.session.history.items if item.type == "agent_handoff"
  ]

• We have a new example showing how agents can navigate an IVR system, bank-ivr.

We hope you are excited about our upcoming LiveKit DevDay on November 18th. If you haven’t registered yet, there is still time at https://luma.com/live-kit-dev-day. Alongside the in-person event, the keynote will be livestreamed and we will be hosting a virtual event in this Slack community, please join the #C09RV65F6BX channel to: • Find out more about our new product releases as they are announced • Join the live Q&A • Give your feedback Anyone is welcome to join - the keynote will be livestreamed at 3pm PST on November 18th and members of the LiveKit team will be around on Slack during and after the event to answer your questions.

The LiveKit DevDay keynote live stream starts in 50 minutes at https://www.youtube.com/live/Ly8_qOgPoBk. Please join us there and also we'll be hosting Q&A with additional info in #C09RV65F6BX - see you there!

Thank you to everybody who attended DevDay last week, either in person or on the livestream. If you missed any of the announcements, you can see everything here: https://livekit.io/events/dev-day • Livestream recording • Blogs for our new feature releases: Agent Builder, LiveKit Phone Numbers, Agent Observability • Video demos for each of the new features • Self-serve demos with source code, videos, and live previews (where appropriate)