Open source framework and cloud platform for building voice, video, and physical AI agents. https://xitter.twitterapi.xyz/t.co/OWLvFH82oN
š
Joined June 2021
- Tweets518
- Following36
- Followers11.5K
- Likes502
LiveKit retweeted
i've been testing gemini 4 carbon for a while now. i gave it a prd to build a "jarvis" voice assistant and it did it in 4.5hrs with no prompting from me.
i also had it fix bugs in another open source repo, and look for security vulnerabilities.
results in video, thoughts?
Introducing LiveKit Portal for ROS 2.
Securely connect your robots to remote operators, cloud GPUs, web apps, or other robots on different networks, without:
ā¢ Exposing DDS
ā¢ Changing your existing nodes
ā¢ Building your own transport layer
Check it out: livekit.com/blog/introducingā¦
Hereās how it works:
Portal connects your ROS graph to a LiveKit room. One YAML file decides what crosses the network: which topics, services, and video, in which direction, and how often.
1
246
Portal is open source, with Docker images and Debian packages for Humble, Jazzy, Kilted, and Lyrical. Use it with LiveKit Cloud or self-hosted.
Start with the Turtlesim tutorial: github.com/livekit/ros-portaā¦
146
Try @rimelabs's Prism speech-to-speech model in LiveKit Agents today.
Prism sends each reply as text and audio, so your agent can check each sentence with a decision model before the caller hears it.
livek.it/2qwRXcp
Proud to be a launch partner in the @FireworksAI_HQ Frontier Ecosystem, announced this week at Forge š·
Explore the ecosystem: fireworks.ai/partners
Build with @livekit + @FireworksAI_HQ : docs.livekit.io/agents/modelā¦
Have you tried AssemblyAI-tts-1 on LiveKit Inference yet?
@AssemblyAI built its first TTS model for voice agents and trained it on real phone conversations. It gets to first audio in about 90ms, offers 4,000+ voices, supports 6 languages, and includes word timestamps, all for $15 per 1M characters.
Itās one more choice in the lineup, so give it a try and see how it sounds with your agent > docs.livekit.io/agents/modelā¦
Building voice agents? @AssemblyAI's 2027 Voice Agent
Report survey asks: cascade, integrated, or delegated S2S, and is S2S production-ready yet?
First 200 qualified respondents get a $25 gift card + early findings. Open through Nov 13.
docs.google.com/forms/d/e/1Fā¦
Greg from Accounting has been āwrapping upā since 2009. Heās also a zombie and you can video call him right now to ask about that unpaid invoice you've been waiting on for years.
We teamed up with @tavus on Night of the Living Agents š» halloween.tavus.io
We ran @MistralAI's Voxtral 3 through LiveKit Simulations with the same agent, same scenarios, over real audio.
Check out the results. And start building today: livek.it/p9KmlCy
Want to talk to the dead this Halloween? š»
SĆ©ance lets you summon a spirit, hear its story in its own voice, and figure out how it really died. Built on LiveKit with @FishAudio Drama 3 voices.
Microphone required. Courage optional.
seance.demo.fish
8
998
Phonic-1 from @phonic_co is available in LiveKit Agents on Day 0.
It's #1 on the Artificial Analysis Speech to Speech Index and built for long calls with dozens of tool calls.
Try it out for your agents in one line of code: docs.livekit.io/agents/modelā¦
Introducing Phonic-1, the most advanced speech-to-speech model for agentic tasks ā from @phonic_co, the speech-to-speech model company.
Weāve had a breakout year and raised a $27.5M Series A led by @firstround with participation from @Lux_Capital, @felicis, and Definition.
Thereās a new TTS model on LiveKit Inference: assemblyai-tts-1, the first text-to-speech model from @AssemblyAI
At a glance:
ā¢ ~90ms to first audio
ā¢ 4,000+ voices
ā¢ English, Spanish, French, German, Italian, and Portuguese, with more on the way
ā¢ Word-level timestamps
ā¢ $15 per 1M characters
Add it to your agent, test it against the other TTS models on LiveKit Inference, and pick what sounds best for your callers.
Try it now: docs.livekit.io/agents/modelā¦
Try some of these š» š spoooooooky š» š faces from LiveKit and @tavus!
Post your best clip with #NightoftheLivingAgents for a chance to win free credits with Tavus and admission to the LiveKit Startup Program
We've teamed up with @livekit to make this Halloween a little spookier š»
Welcome to Night of the Living Agents: video-call monsters with faces by Tavus and voices by LiveKit.
Post a clip with #NightOfTheLivingAgents by Sunday night to win free credits:
halloween.tavus.io
Just in time for Halloween: summon a spirit and solve some mysterious deaths with LiveKit and @FishAudio Drama 3 š»
seance.demo.fish/
What if you could talk to the dead? š»
Our enginner @RaghhavAhuja built a spooky Halloween experiment with @livekit Ć Fish Audio Drama 3.
Summon a spirit, uncover its story, and maybe help it find peace.
Enter the sĆ©ance, if you dare. šÆļø
12
1,332
Check out how @Harper_Insure cut down average call times by 63% with their LiveKit voice agent!
Get started building your own agents at cloud.livekit.io
Since August, Harley, the voice agent we built on @livekit, has run 10,000+ insurance onboarding calls. Average call time is down 63%, and quotes take two or three seconds on hold, not a day or two.
My first engineering post @Harper_Insure, on how we built it: harperinsure.com/engineeringā¦
2
16
1,707
Want to run open-weights models behind your LiveKit agent? Our friends at @modal built a real-time video avatar on their serverless GPUs and wrote up exactly how they did it, Sticky Sessions included > modal.com/blog/livekit-modal
You can give your @livekit agent a video avatar with open-weight models running on Modal.
We used ours to clone @charles_irl, our GPU Enjoyer in Residence.
Combine LiveKit's programmable audio pipeline with @inworld's state-of-the-art TTS and natural-language steering for emotionally grounded, turn-based dialogue and instant feedback
Our @livekit partner story explores how Inworldās speech models and LiveKitās realtime infrastructure help developers build voice applications that can scale with their users.
Through Inworldās integration with the LiveKit Agents framework, developers can use pre-built or custom voices alongside their choice of LLM and speech recognition models, with LiveKit handling realtime communication across web and mobile apps.
The accompanying video takes a closer look at expressive delivery, including how TTS-2ās voice steering helped the team bring Expressive Mode to LiveKit Agents.
āInworld's TTS-2 marks a real step forward in emotionally expressive voice synthesis. When combined with the conversational intelligence of LiveKit agents, it enables interactions that feel genuinely human, responsive, nuanced, and alive in ways that feel natural.ā - David Zhao, CTO, LiveKit
Watch the video or read the full partner story for more on our work together: inworld.ai/customers/livekit
āIn todayās world, ālow codeā really just means ālow customization.āā
@_kyleshechtman and @chasef07 started Acuity Health on a low-code platform, hit a wall, and rebuilt on LiveKit. Now 80% of patient calls are fully handled by their agents, and most bookings take under a minute.
Read more: livekit.com/blog/how-acuity-ā¦
