2 Releases published by 2 people

• livekit-agents@1.2.0

  published Jul 17, 2025

• livekit-plugins-google@0.11.5

  published Jul 24, 2025

40 Pull requests merged by 14 people

• 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

• reveri/fix-11labs-error-fstring

  #2964 merged Jul 22, 2025

• evals: fix realtime model RuntimeError

  #2965 merged Jul 22, 2025

• gemini: emit input_speech_started when new generation created

  #2963 merged Jul 22, 2025

• azure stt: disable language detection if only one language sepcified

  #2959 merged Jul 22, 2025

• Explictly calling ctx.connect before wait_for_participant

  #2957 merged Jul 21, 2025

• [🤖 readme-manager] Update README

  #2956 merged Jul 21, 2025

• fix azure stt update options and add logs for error reason

  #2954 merged Jul 21, 2025

• fix duplicated user messages when preemptive generation canceled

  #2949 merged Jul 20, 2025

• fix: upgrade bithuman library to unblock accessing agents

  #2948 merged Jul 20, 2025

• plugins: openai: llm: add support for service_tier

  #2945 merged Jul 18, 2025

• parameterize inference worker init timeout

  #2805 merged Jul 18, 2025

• chore: remove prometheus database from repository

  #2944 merged Jul 18, 2025

• add RecorderIO and --record flag to the console mode

  #2934 merged Jul 18, 2025

• fix cartesia non-streaming tts

  #2942 merged Jul 18, 2025

• livekit-agents 1.2.1

  #2937 merged Jul 17, 2025

• fix ruff & bump livekit-agents 1.2.0

  #2936 merged Jul 17, 2025

• livekit-agents 1.2.0

  #2482 merged Jul 17, 2025

• fix missing field in UsageCollector

  #2929 merged Jul 17, 2025

4 Pull requests opened by 4 people

• BUG FIX: tts router fallback adapter streaming fix

  #2932 opened Jul 17, 2025

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

  #2972 opened Jul 22, 2025

• Improve chat_cli status printing

  #2991 opened Jul 23, 2025

• Ultravox Realtime API Plugin

  #2992 opened Jul 24, 2025

17 Issues closed by 8 people

• 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

• session_updated event does not contain tools array

  #1400 closed Jul 23, 2025

• how to fix audio interruption noise

  #1395 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

• ModuleNotFoundError for mcp.client.streamable_http: Requires mcp >=1.8.0 and Python >=3.10

  #2946 closed Jul 22, 2025

• [NEW] Gemini Native [TTS] Support [AMAZING]

  #2431 closed Jul 22, 2025

• support plugins for the GLM Realtime model

  #1394 closed Jul 21, 2025

• Option to receive real-time agent transcriptions up front, rather than segmented

  #2950 closed Jul 20, 2025

• user_away_timeout doesn't seem to take effect

  #2947 closed Jul 20, 2025

• cannot load both english & multilingual EOU

  #2496 closed Jul 18, 2025

• Proposal: blingfire and/or pysbd for better multilingual sentence tokenization

  #1811 closed Jul 18, 2025

• text modality not working for gemini multimodal

  #1938 closed Jul 18, 2025

• feat: add opentelemetry instrumentation for tracing

  #2260 closed Jul 18, 2025

• Cartesia TTS errors out within FallbackAdapter after upgrading to 1.2.1

  #2941 closed Jul 18, 2025

• Import "livekit.agents.multimodal" could not be resolved

  #2933 closed Jul 17, 2025

15 Issues opened by 15 people

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

  #2985 opened Jul 23, 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

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

  #2962 opened Jul 22, 2025

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

  #2961 opened Jul 22, 2025

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

  #2955 opened Jul 21, 2025

• Google Cloud TTS isn't working while running

  #2951 opened Jul 20, 2025

• Bug Report: Gemini Live API function calls always return empty arguments

  #2940 opened Jul 18, 2025

• Groq LLM Provider: Unwanted Third HTTP Request After Tool Completion Bypasses Agent Handoffs

  #2939 opened Jul 17, 2025

• AWS Lexicon

  #2935 opened Jul 17, 2025

• TTS Fallback adapter doesn't support streaming, if any one or more of the base TTS service doesn't supports it

  #2930 opened Jul 17, 2025

• LLM gives no answer

  #2928 opened Jul 17, 2025

23 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.

• fix: don't hardcode role=assistant on openai

  #2926 commented on Jul 20, 2025 • 2 new comments

• Integration of async TTS

  #2922 commented on Jul 17, 2025 • 0 new comments

• Feat/mistralai plugins

  #2887 commented on Jul 21, 2025 • 0 new comments

• fix(tracing): serialise datetime when logging events

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

• Integrate Google Camb-Vertex AI with Livekit

  #2835 commented on Jul 21, 2025 • 0 new comments

• add test for restaurant example

  #2821 commented on Jul 17, 2025 • 0 new comments

• Add Soniox STT integration

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

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

  #2871 commented on Jul 23, 2025 • 0 new comments

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

  #2836 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

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

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

• Feature Request: Ultravox example

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

• Feature Request: Support for tool calling in llm adapters

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

• 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

• STT voxtral integration on mistralai plugin

  #2921 commented on Jul 22, 2025 • 0 new comments

• Clarification needed on function calling and tool definition

  #1606 commented on Jul 20, 2025 • 0 new comments

• AssertionError in turn_detector: “end_of_utterance prediction should always return a result”

  #2465 commented on Jul 18, 2025 • 0 new comments

• FEATURE REQUEST: Add timed transcript (start,end,words in chat history)

  #1670 commented on Jul 18, 2025 • 0 new comments

• Fallback Adapter not catching Gemini parsing failures

  #2488 commented on Jul 18, 2025 • 0 new comments

• Backchannel Prediction

  #2907 commented on Jul 17, 2025 • 0 new comments

• Memory leak within docker container and local machines

  #2166 commented on Jul 17, 2025 • 0 new comments

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

  #1335 commented on Jul 17, 2025 • 0 new comments

• AWS STT ( Transcribe ) Timeout

  #2478 commented on Jul 17, 2025 • 0 new comments