LiveKit

366 posts

LiveKit banner
LiveKit

LiveKit

@livekit

Open source framework and cloud platform for building voice, video, and physical AI agents. https://t.co/OWLvFH82oN

🌐 Beigetreten Haziran 2021
22 Folgt8.9K Follower
Angehefteter Tweet
LiveKit
LiveKit@livekit·
We learn to speak before we learn to read. Voice is the most natural interface we have. We just raised a $100M to make building voice AI as easy as a web app.
English
85
60
688
208.9K
LiveKit
LiveKit@livekit·
How can a voice agent tell when you’re actually interrupting it? VAD is too sensitive—laughs, “mm-hmm,” or a sneeze shouldn’t stop the agent. We trained an audio model for adaptive interruption handling so agents can distinguish real interruptions from noise.
English
23
42
460
30.5K
LiveKit retweetet
Shayne
Shayne@shayneparlo·
Our @DeepgramAI plugin now supports mid-stream control messages for Flux, so you can update keyterms in real time as conversational context evolves, without disconnecting and reconnecting. Watch me add a keyterm in real time for my name, which every STT always gets wrong!
English
3
3
15
982
LiveKit
LiveKit@livekit·
Grok's Text to Speech API is now available in LiveKit Inference. Natural, expressive voices with low-latency streaming. Multilingual in 20+ languages. Telephony and production-ready out of the box. One API key. No extra setup. → docs.livekit.io/agents/models/…
xAI@xai

Grok's Text to Speech API is now available. Start building with natural voices and expressive controls to bring your apps to life. #text-to-speech" target="_blank" rel="nofollow noopener">x.ai/api/voice#text

English
49
68
470
91.1K
LiveKit
LiveKit@livekit·
LiveKit turns 5 today. What began as an open source project now powers 300k+ developers, 5k+ customers, and billions of calls across voice, video, and physical AI agents. Next: building the infrastructure for voice-driven computing. Thank you to our community for 5 incredible years.
English
5
14
87
5.8K
LiveKit retweetet
Jesse Hall
Jesse Hall@codeSTACKr·
Built a starter kit for the YC × @GoogleDeepMind hackathon. It's a real-time multimodal agent powered by Gemini 3.1 + LiveKit Agents that generates images with NanoBanana 2 and background music with Lyria RealTime.
English
5
3
15
1.3K
LiveKit
LiveKit@livekit·
Universal-3 Pro from @AssemblyAI is their first promptable speech model. You can prompt it like an LLM. We ran four live tests with LiveKit to measure the accuracy gains. Watch the results.
English
4
3
72
3.5K
LiveKit
LiveKit@livekit·
We shipped the tutorial for Agents UI. In 5 minutes you'll have a fully wired voice agent frontend with audio visualizers, media controls, and session management built directly into your codebase. Watch it, build it, own it. shadcn inside™.
LiveKit@livekit

Introducing Agents UI, an open-source @shadcn component library for building polished React frontends for your voice agents. Audio visualizers. Media controls. Session management tools. Chat transcripts. All wired to LiveKit Agents. Install via the shadcn CLI and own the code.

English
7
15
187
19.9K
AssemblyAI
AssemblyAI@AssemblyAI·
Real-time transcription just got a significant upgrade. Universal-3-Pro is now available for streaming — bringing AssemblyAI's most accurate speech model to live audio for the first time. Developers building voice agents, live captioning tools, and real-time analytics pipelines now get three things they've been asking for: 🔹 Best-in-class word error and entity detection across streaming ASR benchmarks 🔹 Real-time speaker labels — know who said what, as it happens 🔹 Superior entity detection for names, places, orgs, and specialized terminology in real-time 🔹 Code-switching and global language coverage built-in
English
8
7
59
14.3K
LiveKit
LiveKit@livekit·
Introducing Agents UI, an open-source @shadcn component library for building polished React frontends for your voice agents. Audio visualizers. Media controls. Session management tools. Chat transcripts. All wired to LiveKit Agents. Install via the shadcn CLI and own the code.
English
38
102
1.3K
178.6K
LiveKit
LiveKit@livekit·
We evaluated coding assistants across multiple voice-agent scenarios. Without guidance, they hallucinate imports and APIs. With a starter template + Agent Skills + the Docs MCP server, the generated agents consistently work! Try the skill stack -> details in the thread.
English
3
5
44
3.9K
LiveKit
LiveKit@livekit·
Voice agents do not sound robotic because they are slow. They sound robotic because the model writes like an essay and then reads it out loud. We just shared a post on making STT to LLM to TTS sound human. Make the model more human by including ums, sos, real pauses, and even laughter tags. Tiny rhythm changes can make a huge difference.
English
10
17
340
45.3K
LiveKit
LiveKit@livekit·
We made The Agentic List 2026 as a leading Agent Development Platform for building, testing, and deploying autonomous AI agents. Huge credit to the teams shipping voice agents to production on LiveKit, you've pushed us and the voice AI industry forward. #TheAgenticList2026
LiveKit tweet media
English
2
4
25
1.5K