2 Releases published by 2 people

• livekit-plugins-google@0.11.5

  published Jul 24, 2025

• livekit-agents@1.2.2

  published Jul 24, 2025

35 Pull requests merged by 11 people

• fix gemini realtime generate_reply

  #3017 merged Jul 25, 2025

• chore(assemblyai): update termination message

  #3001 merged Jul 24, 2025

• livekit-agents 1.2.2

  #3006 merged Jul 24, 2025

• fix sensitive TTS tests

  #3005 merged Jul 24, 2025

• ci: enable verbose evals

  #3004 merged Jul 24, 2025

• message should be None when empty

  #3003 merged Jul 24, 2025

• improve GetEmailTask instructions

  #3002 merged Jul 24, 2025

• Revert "Improve chat_cli status printing"

  #2999 merged Jul 24, 2025

• fix: upgrade bithuman library version

  #2998 merged Jul 24, 2025

• Improve chat_cli status printing

  #2991 merged Jul 24, 2025

• Gladia STT - add region parameter to gladia stt

  #2995 merged Jul 24, 2025

• wait on_exit before pause scheduling

  #2996 merged Jul 24, 2025

• fix deadlock & session close race

  #2997 merged Jul 24, 2025

• Version Packages

  #2990 merged Jul 24, 2025

• nit: update AgentFalseInterruptionEvent

  #2989 merged Jul 23, 2025

• rename AgentFalseInterruptedEvent -> AgentFalseInterruptionEvent

  #2988 merged Jul 23, 2025

• fix AgentFalseInterruptedEvent none message

  #2987 merged Jul 23, 2025

• io: add input source hierarchy & cleanup

  #2983 merged Jul 23, 2025

• hume tts: raise error message from the api

  #2982 merged Jul 23, 2025

• expose transcription sync speed to RoomOutputOptions

  #2984 merged Jul 23, 2025

• clean up avatar example and add retry for datastream io rpc call

  #2943 merged Jul 23, 2025

• remove Resemble from CI

  #2979 merged Jul 23, 2025

• add simli plugin to ci

  #2978 merged Jul 23, 2025

• feat: add simli avatar with example

  #2923 merged Jul 23, 2025

• support resume agent from a false interruption

  #2852 merged Jul 23, 2025

• fix 11labs tts when audio is an empty string

  #2973 merged Jul 23, 2025

• fix types for anam avatar plugin

  #2976 merged Jul 23, 2025

• feat: add anam avatar

  #2938 merged Jul 23, 2025

• tune vad min_silence_duration and min_endpointing_delay

  #2953 merged Jul 23, 2025

• Handle RN format for preconnect mimeType

  #2952 merged Jul 22, 2025

• add warning when enabling unprovided input/output sinks

  #2969 merged Jul 22, 2025

• increase RoomInput frame_size_ms to 50ms

  #2970 merged Jul 22, 2025

• slightly optimize import time

  #2968 merged Jul 22, 2025

• feat(realtime_model): correctly emit errors when the response is done

  #2967 merged Jul 22, 2025

• add RunContext.wait_for_playout and guard against deadlocks

  #2966 merged Jul 22, 2025

8 Pull requests opened by 8 people

• Add Rime TTS example for generating real-time audio from text

  #2972 opened Jul 22, 2025

• Ultravox Realtime API Plugin

  #2992 opened Jul 24, 2025

• fix aws stt restarting

  #2994 opened Jul 24, 2025

• Add Murf AI - TTS Plugin Support

  #3000 opened Jul 24, 2025

• Langfuse audio tracing support

  #3010 opened Jul 24, 2025

• enable - gemini-live-2.5-flash-preview

  #3016 opened Jul 25, 2025

• Gladia STT - fix region parameter to gladia stt on query parameters

  #3018 opened Jul 25, 2025

• feature/enable-prometheus-multiprocess-collector

  #3021 opened Jul 25, 2025

12 Issues closed by 5 people

• 1.2.0 -> 1.2.2 "self.session.generate_reply()" Stopped working for Realtime Gemini Models

  #3015 closed Jul 25, 2025

• Record room agent side instead of using Egress (save minutes and money)

  #2993 closed Jul 25, 2025

• Does the TrackEgressRequest work for streaming audio?

  #3012 closed Jul 25, 2025

• Offer manual controls to signal end of turn

  #1026 closed Jul 24, 2025

• Feature Request: Allow Selective Track Subscription for VoiceAssistant

  #1399 closed Jul 24, 2025

• generated_msg.model_copy() raises an error if generated_msg is undefined in agent_activity.py

  #2985 closed Jul 24, 2025

• Session output mode switching does not seem to work like examples

  #2958 closed Jul 23, 2025

• When using LiveKit with Gemini Live API, is it possible to get a transcript of what the user has said?

  #2974 closed Jul 23, 2025

• how to fix audio interruption noise

  #1395 closed Jul 23, 2025

• session_updated event does not contain tools array

  #1400 closed Jul 23, 2025

• Integration of Nova sonic(AWS multimodal)

  #2083 closed Jul 22, 2025

• Nova Sonic Tool Response Parsing Bug

  #2874 closed Jul 22, 2025

12 Issues opened by 12 people

• Handling Phone Calls During Pod Upgrades in Kubernetes

  #3020 opened Jul 25, 2025

• Allow dynamic control of interruptions during conversation phases

  #3019 opened Jul 25, 2025

• Gladia STT v1.2.2 causing API Connection Error

  #3014 opened Jul 25, 2025

• LangGraph RemoteGraph raises AttributeError with HumanMessage input state

  #3011 opened Jul 24, 2025

• Support for Google TTS Chirp 3 Custom Voice

  #3013 opened Jul 24, 2025

• [Feature] Langfuse Audio Trace Support via Multimodal Tracing

  #3008 opened Jul 24, 2025

• Agent State Not Updated In Real-Time When Using Tavus Avatar

  #3007 opened Jul 24, 2025

• TTS Optimization to generate speech lazily

  #2981 opened Jul 23, 2025

• Memory Leak During Prolonged Silence

  #2980 opened Jul 23, 2025

• Is update_chat_ctx supported for AWS Realtime?

  #2977 opened Jul 23, 2025

• ERROR livekit.agents - worker failed

  #2975 opened Jul 23, 2025

• Agent iterating alone

  #2971 opened Jul 22, 2025

18 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• got errors while building up avatar with bithuman like "process memory usage is high" and "worker is at full capacity

  #2325 commented on Jul 22, 2025 • 0 new comments

• Support for combined STT + LLM with models like gpt4o-audio-preview

  #2955 commented on Jul 22, 2025 • 0 new comments

• Feature Request: Support for tool calling in llm adapters

  #1966 commented on Jul 22, 2025 • 0 new comments

• Feature Request: Ultravox example

  #1378 commented on Jul 23, 2025 • 0 new comments

• Critical Issues in Voice Agent Communication and Room Connectivity with LiveKit

  #2962 commented on Jul 23, 2025 • 0 new comments

• Feature Request: Support for asynchronous function calling (Gemini + Google Live API)

  #2367 commented on Jul 23, 2025 • 0 new comments

• Bug Report: Egress Recording Stops Capturing Agent Voice Mid-Conversation

  #2716 commented on Jul 23, 2025 • 0 new comments

• AWS STT not working when allow_interruptions=False in LiveKit AgentSession

  #2961 commented on Jul 24, 2025 • 0 new comments

• Does livekit have integrations with langchain/langgraph or Agno?

  #2871 commented on Jul 24, 2025 • 0 new comments

• LangGraph LLMAdapter streams intermediate LLM outputs instead of only final responses

  #2836 commented on Jul 24, 2025 • 0 new comments

• Multilingual Agent (STT and TTS); is that possible with LiveKit?

  #1335 commented on Jul 24, 2025 • 0 new comments

• Feature Request: Recording Audio Inside The Agent

  #2310 commented on Jul 25, 2025 • 0 new comments

• Add Soniox STT integration

  #2443 commented on Jul 23, 2025 • 0 new comments

• Rebase on latest main upstream

  #2812 commented on Jul 24, 2025 • 0 new comments

• Mivi latest

  #2837 commented on Jul 24, 2025 • 0 new comments

• Fix LangGraph LLMAdapter streaming node filtering

  #2838 commented on Jul 25, 2025 • 0 new comments

• fix(tracing): serialise datetime when logging events

  #2840 commented on Jul 23, 2025 • 0 new comments

• update/mistralai-plugins

  #2887 commented on Jul 25, 2025 • 0 new comments