Releases Index
LiveKit

LiveKit

livekit.ioDeveloper Tools
$npx @buildinternet/releases get livekit
Recently Shipped184 releases · updated Oct 17, 2026

Recently shipped GPT-Live over LiveKit Inference, Gemini Live and Grok Voice model support, and a JS SDK fix for leaked audio contexts.

GPT-Live runs on LiveKit Inference. AgentSession(llm="openai/gpt-live-1") uses LiveKit credentials instead of a separate OpenAI key, with inference.DuplexModel handling the protocol. Gemini Live model strings and xAI Grok Voice 3.0 joined the Inference list, alongside a TypeSafe Jev decision-model plugin. Breaking: inference.RealtimeModel no longer subclasses the OpenAI plugin's realtime model, so isinstance checks need updating.

Python agents can measure realtime reply latency. livekit-agents 1.8.7 reports end-to-end latency — last detected user speech to first assistant playback — from assistant message metrics when local VAD is configured. Breaking: telemetry fallback attributes moved to adapter request spans, Anthropic custom HTTP clients must use httpx2, and the OpenTelemetry Events API is replaced by LogRecord(event_name=...).

Rust SDKs can mint agent credentials. livekit-api 0.9.0, livekit-token, and livekit-uniffi add the agent grant and kind claim that Go, Python, and JS already carry; breaking, the four server-inferred grants are now Option<bool>, read through server-matching getters. Data streams error with AbnormalEnd when a room closes, a room dropped without close() no longer leaks its RTC engine, and livekit-capture 0.1.2 parses H.264/H.265 access units and adds GPU wall-clock and test-pattern sources.

Egress moved to Chrome 154, closing CVE-2026-85046 and CVE-2026-87491, two V8 remote-code-execution bugs exploited in the wild; egress runs Chrome unsandboxed unless enable_chrome_sandbox is set. Egress also gained a native OCI Object Storage upload backend and SDK-source compositing for room composite recordings.

Smaller surfaces. Client SDK JS v2.23.0 releases audio contexts and web audio graphs after room.disconnect(), which previously accumulated across mute/unmute cycles. Server v1.13.10 filters VP8, VP9, and AV1 simulcast temporal layers with dependency descriptors; v1.13.9 restored egress-start behavior broken in v1.13.8. lk simulations merged into lk agent simulate as Agent Simulations.

NativeAudioSource use-after-free crash fixed; key leakage prevented

preThis release2 featuresNew capabilities3 enhancementsImprovements to existing features5 fixesBug fixesAI-tallied from the release notes
Rust SDKs · webrtc-51c367e

Ships the external_audio_source.patch fix: after an unpublish and renegotiation, a NativeAudioSource send stream could be registered with AudioState and never removed, so the capture thread called into a freed stream once the PeerConnection closed. Also prevents raw_key/derived_key from leaking via LS_INFO, verifies server-injected frame payloads before skipping decryption, fails AddTransceiver with INVALID_STATE on a closed PeerConnection, and ships missing ObjC headers in the mac framework.

Read more ↗

Audio contexts released on disconnect; E2EE H.264 decrypt fixed

Breaking (minor)This release6 enhancementsImprovements to existing features10 fixesBug fixesAI-tallied from the release notes
Client SDK JS · v2.23.0

Web audio graphs and audio contexts the SDK created are now released after room.disconnect() instead of accumulating over mute/unmute cycles, fixing a false AudioSilenceDetected on autoplay-blocked pages. Fixed E2EE H.264/H.265 decryption for encoders emitting 3-byte Annex B start codes, and encrypting h264 frames from the correct offset when an SEI or AUD NALU precedes the slice.

Read more ↗