Muse Voice Transcribe from @AIatMeta @MetaforDevs is now live! You can now use Meta's new streaming STT model in LiveKit Agents, with real-time diarization for 20+ speakers. Try Muse in LiveKit Agents:

GPT-Live-1 @openaidevs is now supported in LiveKit Agents. It's full-duplex, so it listens and speaks at the same time instead of taking turns, and it hands reasoning and tool calls off to a backend model so a slow lookup doesn't leave your agent sitting in dead air. Same `AgentSession` API. New plugin: `GPTLiveModel`. Get started:

Gradium TTS is now available on LiveKit Inference, free until Oct. 9. Gradium TTS is designed for conversational use cases, with voice cloning, low latency (below 250ms TTFA), and robust pronunciation on difficult cases. Select @GradiumAI as your TTS provider in LiveKit Inference, no additional account or API key required:

Agent deployments are live on LiveKit Cloud. Your voice agent can have a staging deployment running next to production. Same image, same project, same secrets, different name. Test a change on real infrastructure, then promote that exact build. Read more:

LiveKit Connectors are generally available today. They bring calls from @twilio Programmable Voice and @WhatsApp Business Calling into a LiveKit room as a regular participant, so your agent can answer there with no SIP trunk to provision and nothing new to host. Read the full article:

Gemini 3.5 Transcribe Live is now available in LiveKit Agents, bringing LLM-based realtime transcription built for alphanumerics, domain-specific vocabulary, multilingual speech, and code-switching. Give it a try today on LiveKit Inference:

We built a patient intake agent with @SpaceXAI that runs end to end on Grok voice models. Grok STT → Grok 4.3 → Grok TTS, cascaded through LiveKit Inference. Three model strings in one AgentSession. No separate API key, no separate billing, ZDR on every hop. Talk to it:

Come work for me! @livekit is growing fast. We're hiring a Staff Developer Advocate for community and events, based in the SF Bay Area. LiveKit is the platform developers use to build voice AI agents, the infrastructure behind OpenAI, xAI, Salesforce, and Spotify. I'm building out DevRel and want someone running events and community in person, starting in the Bay Area. The work is part events, part content. You'd host and attend meetups, hackathons, and workshops, speak at conferences, and turn each one into recaps, demos, and tutorials that reach the people who weren't in the room. You'd also bring what developers are telling you back into product and strategy. What I'm after: → A few years in DevRel with events experience → A hands-on technical background, comfortable writing a code sample and running a live demo → Based in the SF Bay Area and happy being outward-facing → Genuinely curious about what developers are building Full role and how to apply:

It's now less expensive to build and run agents on LiveKit. Agent sessions, recording, WebRTC, and SIP are billed per-second with a 10-second minimum. A 14-second outbound call costs 14 seconds, not a full minute. No code changes. Just a smaller bill. Read the full post:

Protect sensitive data without giving up voice agent observability. LiveKit PII Redaction automatically removes personal information from transcripts and recordings before it is stored. It is included with LiveKit Agent Observability at no additional cost. Read more:

Every LLM, STT, and TTS model in LiveKit Inference is zero data retention by default. No flag to set, no tier to upgrade, no dashboard toggle. We did the verification work across every provider so you don't have to redo it every time you add a model.

Here's our take on benchmarks for voice: they're hard to get right, but critical if you're building humanlike AI. Our live benchmarks page is up now: pass rate on real agent scenarios, latency including the worst-case (p99) moments, side-by-side conversation comparison between models over time. Feedback welcome!

Today we’ve raised $52M Seed and we are announcing the public launch of S2.1 Pro. >It can clone a voice from 5 seconds of audio >2x faster than Cartesia & 1/6th the cost of Eleven Labs >most expressive model with word level control over emotion, intonation, pacing etc We support frontier AI companies including HeyGen, LiveKit, Retell, Sanas, and OpenArt all run our model in production. If you're a business and we can't cut your voice AI costs by 50%, we'll give you 1 year of Fish Audio for free. Book a demo: To celebrate our first birthday, we'll give you 1 month of S2.1 Pro for free. Like, retweet, and comment “Fish” to get it.

Voice agents are exploding. Don’t let them be a black box in production. Today, we’re launching LangSmith tracing for 4 voice frameworks: 🎙️ @pipecat_ai 🎙️ @livekit 🎙️ @OpenAI Realtime 🎙️ @GeminiApp Live (Google ADK) Learn more: