Open source framework and cloud platform for building voice, video, and physical AI agents. https://nitter.cf/t.co/OWLvFH82oN
🌐
Joined June 2021
- Tweets509
- Following35
- Followers11.4K
- Likes499
Greg from Accounting has been “wrapping up” since 2009. He’s 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 👻 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? 👻
Séance 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
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/model…
Introducing Phonic-1, the most advanced speech-to-speech model for agentic tasks — from @phonic_co, the speech-to-speech model company.
We’ve had a breakout year and raised a $27.5M Series A led by @firstround with participation from @Lux_Capital, @felicis, and Definition.
There’s a new TTS model on LiveKit Inference: assemblyai-tts-1, the first text-to-speech model from @AssemblyAI
At a glance:
• ~90ms to first audio
• 4,000+ voices
• English, Spanish, French, German, Italian, and Portuguese, with more on the way
• Word-level timestamps
• $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/model…
Try some of these 👻 🎃 spoooooooky 👻 🎃 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 👻
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 👻
seance.demo.fish/
What if you could talk to the dead? 👻
Our enginner @RaghhavAhuja built a spooky Halloween experiment with @livekit × Fish Audio Drama 3.
Summon a spirit, uncover its story, and maybe help it find peace.
Enter the séance, if you dare. 🕯️
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/engineering…
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 Inworld’s speech models and LiveKit’s realtime infrastructure help developers build voice applications that can scale with their users.
Through Inworld’s 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-2’s voice steering helped the team bring Expressive Mode to LiveKit Agents.
“Inworld'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.” - David Zhao, CTO, LiveKit
Watch the video or read the full partner story for more on our work together: inworld.ai/customers/livekit
“In today’s world, ‘low code’ really just means ‘low customization.’”
@_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-…
Two small models we trained for voice agents: turn detection knows when the user is actually done talking, adaptive interruption knows “uh huh” isn’t an interruption.
Free for agents on LiveKit Cloud. Starting today, self-hosted agents can run them in production too: a free development allowance, then metered per request. The old monthly cap is gone.
docs.livekit.io/agents/logic…
Meet SpookyKit, five haunted voices for your voice agent 🎃
Voices from LiveKit coworkers (guess who?), via @FishAudio as a custom voice:
🕯️ the hollow whisperer (v_rcMdmMksGhqr)
📞 the grave caller (v_ou7cbav4LMuq)
🌊 the thing below (v_U9DZ7HDMqqtM)
Voices summoned from the shadows by our spooky friends at @GradiumAI 🧡
💀 the bone barker (hwchrc8s07s20000)
📻 the dead air host (hwchrc8s07s00000)
paste a voice ID into LiveKit Inference or Agent Builder and go give someone a fright 👻
Try them now >
cloud.livekit.io
Voice agents get built three ways: cascaded (STT, LLM, TTS), turn-based speech-to-speech, and full-duplex, where the model listens and talks at the same time.
All three now run on LiveKit Inference: GPT-Live and GPT Realtime from @OpenAI, @grok Voice Think Fast from @xai, and Gemini Live from @GoogleDeepMind. One LiveKit Cloud key, one bill.
Interested in trying @GoogleDeepMind's Gemini-4 Argon? It's available in LiveKit Inference! Drop it into your voice agent with a single line of code, run a test call, and hear the difference for yourself.
Try it out now:
docs.livekit.io/agents/model…
LiveKit retweeted
80% of Moss customers use @livekit. 👀
LiveKit handles real-time voice. Moss handles the retrieval.
Together, your agent gets the context it needs on every turn, automatically.
No tool call. No extra roundtrip. No dead air.
Sub-10ms retrieval for voice AI.
→ moss.dev/integrations/liveki…
Next week: AI Agents Speakeasy w/ @modal, #LATechWeek. Cocktails, delicious food, and conversation with the people shipping agents.
Wed Oct 14 · 6-9pm · LA
RSVP: partiful.com/e/4K1RcwGixzueN…
Know exactly what your agent can do, catch gaps before customers do, and test any model against your own scenarios before you switch. Your agent has a QA team now.
Try LiveKit Simulations free through October: livekit.com/products/agent-s…
Listen to this support call using @MicrosoftAI's speech models and LiveKit Agents.
• MAI-Transcribe-2-Streaming hears you
• Gemma 4 on LiveKit Inference reasons and calls tools
• MAI-Voice-2.1-Flash answers
What do you think?
STT: livek.it/E4qoZvU
TTS: livek.it/RsCc37l