Hello is there a way to prevent livekit agent from closing session after all participants have exited out of room from more than 30 sec? We would need livekit agent session for atleast 2-3 min

Hey team, I just upgraded to 1.3.5 from 1.2.18 and are seeing this issue consistently "livekit.agents.llm.realtime.RealtimeError: generate_reply timed out waiting for generation_created event" We are calling generate_reply without instructions:

session.generate_reply()

(Doing this instead works

await session.generate_reply(_instructions_=" ")

) I just discovered it works fine if we pass instructions, so maybe some bug/issue have crept in here? (example where you guys do the same) We are using Gemini realtime + Elevenlabs. This is working in 1.2.x but consistently happening in 1.3.1-1.3.5. We are passing in chat_history, so ideally we don't want to pass another instructions.

./venv/bin/python main.py console
    Agents   Starting console mode 🚀
              
    11:43:43 DEBUG  asyncio          Using selector: KqueueSelector  
             INFO   livekit.agents   starting worker {"version": "1.3.1", "rtc-version": "1.0.19"}
             INFO   livekit.agents   initializing job runner {"tid": 51365078}
             DEBUG  asyncio          Using selector: KqueueSelector  
             INFO   livekit.agents   job runner initialized {"tid": 51365078, "elapsed_time": 0.0}
             INFO   livekit-agent    No metadata found, using test defaults  
             INFO   livekit-agent    Running in console mode, call_id: console-20251127-114343  
             DEBUG  livekit.plugins… connecting to Gemini Realtime API...  
             DEBUG  livekit.agents   using audio io: `Console` -> `AgentSession` -> `Console`  
             WARNI… livekit.agents   resume_false_interruption is enabled but audio output   {"audio_output": "Console"}
                                     does not support pause, it will be ignored                                         
             DEBUG  livekit.agents   using transcript io: `AgentSession` -> (none)  
    11:43:50 ERROR  livekit.agents   Error in _realtime_reply_task                                                      
                                     Traceback (most recent call last):                                                 
                                       File                                                                             
                                     "/Users/jensa/Development/projects/giant/livekit/livekit-agent/venv/lib/python3.1  
                                     3/site-packages/livekit/agents/utils/log.py", line 16, in async_fn_logs            
                                         return await fn(*args, **kwargs)                                               
                                                ^^^^^^^^^^^^^^^^^^^^^^^^^                                               
                                       File                                                                             
                                     "/Users/jensa/Development/projects/giant/livekit/livekit-agent/venv/lib/python3.1  
                                     3/site-packages/livekit/agents/voice/agent_activity.py", line 2058, in             
                                     _realtime_reply_task                                                               
                                         generation_ev = await self._rt_session.generate_reply(                         
                                                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^                         
                                             instructions=instructions or NOT_GIVEN                                     
                                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^                                     
                                         )                                                                              
                                         ^                                                                              
                                     livekit.agents.llm.realtime.RealtimeError: generate_reply timed out waiting for    
                                     generation_created event.

Hi everyone, I need help with setting up LiveKit on a VPS. I’ve deployed LiveKit without a load balancer and followed the deployment docs. Everything works except the TURN part — the connectivity test fails on the TURN step. The only unusual part of my setup is that I don’t have a domain for my TURN server. I’m using a TLS certificate that was issued for my raw IP address, so I configured the TURN server using the IP as the

tls_domain

/ certificate CN. Could this be causing the TURN test to fail? Does LiveKit’s TURN server require a proper domain name for TLS, or is using an IP certificate acceptable? Any guidance is appreciated.

Hi Team does the SIP APIs work on the SIP self hosting or only on livekit cloud server only . @refined-appointment-81829

This has a component of server-api https://livekit-users.slack.com/archives/C05L395US9L/p1764355805919499 to publish the 24/7 rooms

is any one facing a bug in livekit-plugins-groq PlayAI TTS implementation. The plugin isn't properly handling audio sample rates iam using "provider": "groq", "voice": "Nasser-PlayAI", "model": "playai-tts-arabic",

Hi! I need Real-Time project enabled for my account. I only have the Agent/Build project type and cannot create rooms using RoomServiceClient. Project: deepelynx Email: deepelynx@gmail.com

Hello! We are facing an issue in the https://cloud.livekit.io/projects/{project id}/settings/webhooks page. Does anyone know how we might overcome this?

hi again! 👋 i'm wondering what best practices are for passing around an

api.LiveKitAPI

object in a large application in Python. would placing it in a container class with static accessors and mutex locks suffice? how can i ensure it gets properly closed when the process exits? i'm troubleshooting some memory leaks and this is a potential suspect

I’m building off of the

agent-starter-node

, and I’m noticing that when I do

pnpm dev

, my agent gets disconnected whenever it attempts to call a tool. Any idea why that might be?

@lively-winter-88668 Is this quota usage email incorrectly referring to Agent minutes instead of WebRTC when it says the Ship plan has 5,000 minutes? I think it's meant to say 150,000 minutes for WebRTC. This was confusing to me because I'm hosting an agent on my own server, you may want to consider adding clarity.

Anyone else using "gemini-live-2.5-flash-preview" model? Last night looks like it stopped working out of the blue...

{
  "level": "ERROR",
  "name": "livekit.agents",
  "message": "AgentSession is closing due to unrecoverable error\nTraceback (most recent call last):\n  File \"/home/appuser/.local/lib/python3.11/site-packages/livekit/plugins/google/realtime/realtime_api.py\", line 667, in _main_task\n    async with self._client.aio.live.connect(\n  File \"/usr/local/lib/python3.11/contextlib.py\", line 204, in __aenter__\n    return await anext(self.gen)\n           ^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/appuser/.local/lib/python3.11/site-packages/google/genai/live.py\", line 1092, in connect\n    raw_response = await ws.recv(decode=False)\n                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/home/appuser/.local/lib/python3.11/site-packages/websockets/asyncio/connection.py\", line 322, in recv\n    raise self.protocol.close_exc from self.recv_exc\nwebsockets.exceptions.ConnectionClosedError: received 1008 (policy violation) models/gemini-live-2.5-flash-preview is not found for API version v1beta, or is not supported for bidiGenerateContent. Call; then sent 1008 (policy violation) models/gemini-live-2.5-flash-preview is not found for API version v1beta, or is not supported for bidiGenerateContent. Call",
  "exc_info": "websockets.exceptions.ConnectionClosedError: received 1008 (policy violation) models/gemini-live-2.5-flash-preview is not found for API version v1beta, or is not supported for bidiGenerateContent. Call; then sent 1008 (policy violation) models/gemini-live-2.5-flash-preview is not found for API version v1beta, or is not supported for bidiGenerateContent. Call",
  "pid": 93528,
  "job_id": "AJ_ygYw6Jv3SMCe",
  "room_id": "RM_wLZw6DNxPRf3",
  "timestamp": "2025-12-11T07:17:59.895800+00:00"
}

3/10 merges this happens I am getting intermittent error

Failed to merge calls: Error: moveParticipant requires LiveKit Cloud. Please ensure you are using LiveKit Cloud or update your SDK version.

Thread in Slack Conversation

Hi, Is there any way to get the livekit session or room audio recording in local recordings folder after session ends?

Hi team, I have a project that streams a browser from backend to client, capturing screenshots via playwright. Unfortunately playwright only supports screenshots so I would have to send a stream of screenshots (30fps in my case). I was wondering if the data channel would be via the API call stream_bytes? Or would there be another approach I can do this to achieve lower latency, closer to video streaming?

HI Team, I there any way to get the status of sip participant status

Hey, noticed that

await api.LiveKitAPI().start_room_composite_egress(req)

would fail silently when called in livekit agent when credentials are misconfigured. Is this expected? Shouldnt it throw an unauthorised error? Can anyone help me catch error here? I was following this guide from https://docs.livekit.io/deploy/observability/data/#record-audio-or-video Code:

file_outputs = [

api.EncodedFileOutput(

file_type=api.EncodedFileType.OGG,

filepath=filepath,

azure=api.AzureBlobUpload(

account_name=account_name,

account_key=account_key,

container_name=container_name,

),

)

]

req = api.RoomCompositeEgressRequest(room_name=ctx.room.name, audio_only=True, file_outputs=file_outputs, audio_mixing="DUAL_CHANNEL_AGENT")

lkapi = api.LiveKitAPI()

try:

await lkapi.egress.start_room_composite_egress(req)

except Exception as e:

print(e)

Hello! Anyone know what is the correct API endpoint for: lk dispatch create \ --agent-name test_agent \ --room aloha2 \ --metadata '{"user_id":"123"}' when I use CLI with this command works fine but when I try to do API call to https://my.livekit.cloud/twirp/agentdispatch.AgentDispatchService/CreateDispatch with same JSON body I have status OK but the room is not created.

Is anyone knows what IP Range needs to be whitelisted for LiveKit Agent to access from other country

Hi LiveKit team, I am from deepdub's R&D team We would like to add our real time text to speech model to your TTS plugins - would love instructions on how to do it Thanks! Peter

alert This channel is being sunset on 27th February 2026: alert

Hi everyone, please be aware that we have a new community forum at community.livekit.io and the plan is to move support for this channel into that new forum. Please see full details here. The Slack community will remain, but we will do housekeeping of the technical channels after that date.

Hi , i am getting 404 for AcceptWhatsAppCall API . how can i solve this issue ?

This message was deleted.

This message was deleted.

@alert-easter-19258 since this year my outbound when i call

sip.list_sip_outbound_trunk

my password would appear redacted with "****" how can i fix the issue?

Are there any current degradation on LiveKit? We are seeing 30-90 second connection times to our agents. Never seen this before.

Facing issue while integrating Grok new voice model and Livekit Building a react native app and integrating the new grok voice model using livekit but facing issues in estabilishing session while I tap connect on my frontend. In the backend it is getting timed out, even after pre-downloading VAD in dockerfiles. Btw backend is on gcloud run

This message was deleted.

@icy-policeman-64898 explain the difference between livekit inferencing model and a normal inferencing model with numbers

archived the channel