Summary
When using gemini-3.1-flash-live-preview, the agent fails to generate the first reply right after joining the room — timing out on generation_created. The exact same code works perfectly with gemini-2.0-flash-live-001 with no issues.
Environment
| Component | Details |
|---|---|
| Model (broken) | gemini-3.1-flash-live-preview |
| Model (working) | gemini-2.5-flash |
| SDK | livekit-agents (Version : 1.5.1) |
| Plugin | livekit-plugins-google |
Code
python
@server.rtc_session(agent_name="my-agent")
async def my_agent(ctx: agents.JobContext):
session = AgentSession(
llm=google.realtime.RealtimeModel(
model="gemini-3.1-flash-live-preview", # ❌ breaks here
# model="gemini-2.5-flash", # ✅ works fine
voice="Puck",
),
vad=silero.VAD.load(),
)
await session.start(ctx.room, participant=ctx.room.remote_participants)
await session.generate_reply(
instructions="Greet the user."
)
Error Log
00:38:57.873 ERROR… livekit.…ns.google error in receive task: 1007 None.
Request contains an invalid argument.
websockets.exceptions.ConnectionClosedError:
received 1007 (invalid frame payload data) Request contains an invalid argument.
google.genai.errors.APIError: 1007 None. Request contains an invalid argument.
00:39:01.264 ERROR… livekit.agents failed to generate a reply:
generate_reply timed out waiting for
generation_created event.
00:39:03.967 WARNI… livekit.…ns.google received server content but no active generation.