{"message": "Error in _tts_inference_task", "level": "ERROR", "name": "livekit.agents", "exc_info": "Traceback (most recent call last):\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\livekit\\agents\\tts\\tts.py\", line 633, in __anext__\n    val = await self._event_aiter.__anext__()\n          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\nStopAsyncIteration\n\nDuring handling of the above exception, another exception occurred:\n\nTraceback (most recent call last):\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\livekit\\agents\\utils\\log.py\", line 17, in async_fn_logs\n    return await fn(*args, **kwargs)\n           ^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\livekit\\agents\\voice\\generation.py\", line 294, in _tts_inference_task\n    pushed_duration += await _tts_node_inference(input_segment, pushed_duration)\n                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\opentelemetry\\util\\_decorator.py\", line 71, in async_wrapper\n    return await func(*args, **kwargs)  # type: ignore\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\livekit\\agents\\voice\\generation.py\", line 252, in _tts_node_inference\n    async for audio_frame in tts_node:\n    ...<13 lines>...\n        audio_duration += audio_frame.duration\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\livekit\\agents\\voice\\agent.py\", line 453, in tts_node\n    async for ev in stream:\n        yield ev.frame\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\livekit\\agents\\tts\\tts.py\", line 636, in __anext__\n    raise exc  # noqa: B904\n    ^^^^^^^^^\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\livekit\\agents\\tts\\tts.py\", line 422, in _traceable_main_task\n    await self._main_task()\n  File \"C:\\Users\\adity\\projects\\thundergen\\frostline-lk-agent\\.venv\\Lib\\site-packages\\livekit\\agents\\tts\\tts.py\", line 467, in _main_task\n    raise APIError(f\"no audio frames were pushed for text: {self._pushed_text}\")\nlivekit.agents._exceptions.APIError: no audio frames were pushed for text: To create a new IAM user, we'll go to the IAM Users page, define the user's identity, then attach the right permissions so they can do what they need without over-privileging.\n\nOkay, on screen I'm opening IAM and heading into Users so we can manage individual identities. Now we're starting the add-user setup, where you choose the username and the type of access this person or system needs. Next, we're attaching permissions policies—this is the key part because it controls what the new user is allowed to do in AWS.\n\nThat creates the new IAM user and sets their permissions. Do you also want this user to have CLI access (so we generate access keys), or is this just for console sign-in? (body=None, retryable=True)",

Hey'll, i am building something and using google tts chirp HD voices through vertexai, but i am repeatedly hitting this error where it is unable to generate the speech. I don't know why it used to work some time ago, is anyone encountering this issue ? The configurations is dead simple

session = AgentSession(
    stt=deepgram.STT(
        model="nova-3"
    ),
    llm=openai.LLM(
        model="gpt-5.2",
    ),
    tts=google.TTS(
        gender=room_metadata.voice.gender,
        voice_name=room_metadata.voice.voice_name,
    ),
    vad=silero.VAD.load(),
    turn_detection=EnglishModel(),
    max_tool_steps=25,
    user_away_timeout=10,
)

Any help will be appreciated, meanwhile suggest me good alternatives.

Did you see this thread? https://livekit-users.slack.com/archives/C07FY8WHGPM/p1769178489297599

This solves the issue, thanks