This message was deleted.

This message was deleted.

I found a demo (Link Demo) of live streaming via RTMP that runs in a web browser. In case I use Flutter, how do I do for the live stream feature. Is there a demo example with flutter?

has renamed the channel from "general" to "announcements"

Hey folks, just made some changes to our LiveKit Community Slack to try to keep things a little more organized 😄 The main channels, which everyone joins by default, are now: 👋 #C05JNAD1960 (all new users will start here) 📢 #C01KZ61HZRR — News about SDK releases and our blog posts. Formerly #general. Only admins can post here. 📱 #C01KVTJH6BX — get help with LiveKit ☁️ #C048FRL1N2C — get help with LiveKit Cloud These channels are opt-in and interest-based: 🎉 #C05L395US9L — share the projects you’ve built with LiveKit! post your links here! self-promote! 🤓 #C05L9RAB1JP — general WebRTC discussion goes here ⌨️ #C025KM0S1CK — our open-source development happens here 🦀 #C04G4GE0RGX — info and discussion about our Rust SDK Developer Preview

Hey all, we've just added another data center to LiveKit Cloud in Australia (Sydney)! This should provide improved quality and better connection times in the region for your users.

Hey all, just a heads up that most of the LiveKit team is gathered together for our annual company trip. This year it's in Hong Kong! Our responses this week may be slower than usual, but we will try our best to help y'all through any issues. 🙏

For those that are using JS SDK, please update to v1.14. Due to a bug in Safari 17, screenshares created using the default options would appear low-resolution to other users.

LiveKit Cloud now has a US East 1 and US East 2 datacenter! This will provide additional capacity and resiliency for this region.

This message was deleted.

This message was deleted.

Howdy! For those that are transitioning from Twilio, we've created an example to illustrate how straightforward the migration process is. LiveKit has a similar set of constructs as Twilio Video: Room, Participant, TrackPublication, and Track, making it quite simple to map them over. You also have the option to either use LiveKit Cloud or self-host. Check out our migration example. If you have any questions, feel free to reach out to us in the #C01KVTJH6BX We're here to assist!

This message was deleted.

This message was deleted.

<!channel> 🚨*Important Update: Upgrade LiveKit SDK for Chrome 124 Compatibility* 🚨 We've got an urgent update for everyone building browser-based apps. With Chrome 124 releasing on April 16th, there's a breaking change in the

setCodecPreferences

API that affects our SDKs. Here's what you need to do: Upgrade your LiveKit Client SDK to these versions before April 10th to avoid any breakage: • Web: v2.0.10 or v1.15.13 • Flutter: v2.0.3 • Unity Web: v1.5.1 • React: v2.0.5 Please prioritize this update to ensure your applications continue to work seamlessly with this new version of Chrome. If you encounter any issues or have questions, please let us know in the 🧵 . Thanks for acting swiftly on this! -The LiveKit Team

📣 We have recently merged a substantial change into the

main

branch for Agents. There are breaking API changes across the board: • speech-to-text • text-to-speech • vad • agents 🥳 Enhancements • job isolation. Every agent will run in its own process. This drastically improves the number of agents that can exist on a single server • load balancing and orchestration. Agents will now be distributed properly across multiple workers. LiveKit handles this load balancing for you and employs a “fill-first” strategy. By default, capacity is determined by cpu load but this behavior can be overidden • an interface for LLMs • misc improvements to STT, TTS, and VAD apis + implementations ⚠️ WARNING: READ THIS Unfortunately, many of our setup.py files had incorrect constraints defined. Specifically

>=

was used in many of the dependency constraints, including those for agents. This means, without making any changes to your code, a new build can break your functionality. We will be cutting the new release on M*onday (4/15)* so if you’re using agents in production, you’ll want to either make the necessary upgrades to your code or pin

==

your livekit dependencies in your

requirements.txt

. If you want to use the new packages to test (and migrate) before monday, the following versions can be installed:

livekit-agents==0.5.dev3
livekit-plugins-deepgram==0.3.dev0
livekit-plugins-elevenlabs==0.3.dev0
livekit-plugins-openai==0.3.dev0
livekit-plugins-silero==0.3.dev0
livekit-plugins-google==0.3.dev0
livekit-plugins-nltk==0.4.dev0

After Monday they will be full releases. i.e.

livekit-agents~=0.5

<!channel> Hey LiveKit devs, today we’re announcing our Series A: https://twitter.com/dsa/status/1798027280872321117 David and I want to express our deepest gratitude to everyone here. Without your energy and support, we wouldn’t have reached this milestone. These last few years, helping you all build amazing projects and products have been the most fulfilling of our careers. We’re looking forward to many more years of working for and with you! 🙏💜 Russ & @dry-elephant-14928

Howdy! We are excited to announce a major release of the Agent Framework today! Version 0.8.x includes several significant updates the team has been working hard on: • Significant improvements to VoiceAssistant’s reliability and interruption handling • Revamped support for LLM function calling • 20x (you read that right!) reduction in compute requirements, primarily due to improvements to VAD You can try the latest demo here or by calling +1 (650) 680-4883 This release does come with a few breaking API changes. We’ve outlined the changes in this migration guide. Happy building!

Hi everyone! We noticed that some of the channels were getting a little bit noisy, so we've revamped the community structure a little bit to better reflect the topics that people discussing here in Slack. We're still going to be providing support where we can, the only difference is that instead of every request getting dumped into a single "helpdesk" channel, you can ask your questions in the relevant community channels. This way, you can stay up to date on the topics that you care about most, rather than sifting through all of the messages in one or two channels!

👋 We're always striving to improve LiveKit, and that means gathering valuable feedback from our developer community. We're looking for volunteers excited to test new features and help shape the future of LiveKit. Right now, we're working on features to make getting started with voice agents on LiveKit much easier. If you: • Have a LiveKit Cloud account • Are building with or have tried out LiveKit Agents • Are willing to participate and screenshare in a user session Sign up for our research list here: https://forms.gle/KtNNXTq2hjnUp9dz8

Hey all, we've just dropped a new release of Agents (0.9.1) packing some significant improvements. In it you'll find: • Rework of audio publishing/buffering to reduce audible glitches • Introducing

lk.agent.state

attribute to allow client to detect state of VoiceAssistant:

speaking

,

listening

, etc • Fixed a rare case where Agent wouldn't reconnect to room after being disconnected • Exposing additional control for VoiceAssistant ◦ `min_endpointing_delay`: control over how quickly the agent should respond when the user pauses (longer delay reduces agent interruptions) ◦ `before_llm_cb`: ability to control what is being sent to the LLM ◦ `before_tts_cb`: ability to modify text before it's sent to TTS Additionally, we've launched a set of new JS components (2.6.0) for quickly building voice agent frontends. With it, you can now build an agent using

useVoiceAssistant

hook and a

BarVisualizer

component. Check out the simple example we've put together!

<!channel> 🚀 Exciting news! We are thrilled to announce our partnership with OpenAI for the new multimodal Realtime API! (likes and retweets are appreciated!). The new integration allows you to create voice agents using the same stack as Advanced Voice Mode, while also leveraging LiveKit’s ecosystem of open-source tools. As part of this launch, we’re also releasing a developer preview of Agents for Node.js—a highly requested feature from many of you. 🔧 Give it a try and share your feedback! We’re excited to see the amazing things you create with these new tools.

Happy Friday! For those of you building with the Python SDK, we've just shipped a set of new reference docs which includes covers

livekit.agents

,

livekit.api

,

livekit.plugins

,

livekit.protocol

and

livekit.rtc

. Please give them a go and reach out with any feedback! https://docs.livekit.io/python/livekit/

🚢

livekit-agents

0.10.2 release 🚢 Heads up, there's a new version of

livekit-agents

available! v0.10.2 includes the following updates: • Added

VAD.update_options

to the Silero plugin, which you can use to update the VAD options after the VAD object has been created. • Included various fixes related to address cases where

VoicePipelineAgent

was getting stuck. • Included some additional VAD-related fixes. Please reach out if you run into any issues or have any other feedback!

Hy everyone! I'm running a free workshop on Friday Nov 1st (this Friday) showing how to build a fullstack Advanced Voice web app with the OpenAI Realtime API. It's an hour long, will be interactive (as time permits) and we'll start from the basics and build all the way from 0 to a finished app that talks with users using Advanced Voice. Backend will be Python, frontend will be in React — but once you're finished it's very easy to switch either piece out for a different technology. There's only a few spots left, but I figured I'd post here in case anyone here who hasn't started building yet wanted a live crash course. Here's the registration link: https://forms.gle/SAQjdnQXFLoEsLXt7 Hope to see some of you on Friday!

🚢

livekit-agents

0.11.0 release 🚢 We've just released

livekit-agents

0.11.0 which is full of treats! Inside you’ll find the much-requested addition of more detailed timing metrics as each stage of the

VoicePipelineAgent

and much more. Highlights: • Introduced detailed time metrics (time to first byte/token of STT/LLM/TTS, duration) and usage metrics, including an example for calculating the cost of a conversation. • Added

TTS.update_options

- useful for making runtime changes, such as changing voices. • Added the ability to get the human and agent transcript for the

MultimodalAgent

class. • Fixed CPU load calculation using the system usage instead of the cgroup usage, addressing autoscaling issues for some developers. Check out the full changelog for livekit-agents and each plugin for a detailed rundown of all updates. A huge thanks to @martin-purplefish, @Tanesan, @longcw, @jayeshp19, @hari-truviz, and @samirsalman for your excellent contributions!

🚢 🚢 🚢 We’re excited to introduce a new data channel feature called RPC! You can now register a custom method on one participant then invoke it remotely from another participant in the room and await a response. This is perfect for forwarding LLM function calls from an agent, for instance to query data like geolocation that’s available only in the browser. You can also use it to easily give your agent the ability to directly manipulate the user’s UI and display notifications, visual effects, or request specific user input. The possibilities are endless, and we’re excited to see what you all build with it! RPC is available now for JS (

livekit-client@2.6.0

), Python (

livekit==0.18.0

), Node (

@livekit/rtc-node@0.11.0

), and Rust (

livekit = "0.7.0"

). Updates for the mobile SDKs are coming over the next few weeks. Check out the full docs for a complete overview and examples.

🚢 agents-js 0.4.3 release 🚢 Check out the latest version of LiveKit Agents for Node.js (0.4.3) for a drop of new features: • Introducing support for

VoicePipelineAgent

🚀 • Silero VAD, ElevenLabs TTS, Deepgram STT, OpenAI LLM 🪄 • Various fixes 🛠️ Note: We are aware of a bug concerning users of tsx under certain conditions. See this issue for more details and a fix.

We have a new channel for those of you that are working with OpenAI's Realtime API: #C0816MD6LCR

🚢

livekit-agents@0.11.2

release 🚢 Hello LiveKit community! Go and grab

livekit-agents@0.11.2

for some new additions to the OpenAI plugin along a handful of bug fixes: ◦ New features in

livekit-plugins-openai@0.10.16

▪︎ Added usage metrics for the OpenAI Realtime API, which provides more visibility into the input/output token usage when using

MultimodalAgent

with this API. ▪︎ The

chat_ctx

is now synchronized with the OpenAI Realtime API - transcripts from the model are written back to the

chat_ctx

while the realtime session is updated based on input from

chat_ctx

. • Fix to correctly follow the

min_endpointing_delay

configuration • Fix for

agent_speech_committed

not being called in certain scenarios Please refer to the changelog for a full rundown of all updates - and thanks to @jayeshp19, @martin-purplefish, and @longcw for your contributions!