Using speech config when Runner.run_live gives error 1007 invalid frame payload data

[ParohyGr]

Project setup

• Running a websocket in google cloud run
• Agent session is created on demand from client

Session creaetion

• When client creates audio connection, i start a Runner with RunConfig using modality AUDIO

if not params.is_audio:
    modality = [types.Modality.TEXT]
    streaming_mode = StreamingMode.NONE
    speech_config = None
else:
    modality = [types.Modality.AUDIO]
    streaming_mode = StreamingMode.BIDI
    voice_config = types.PrebuiltVoiceConfig(
        voice_name="Kore"
    )
    speech_config = types.SpeechConfig(
        voice_config=voice_config,
        language_code="en-US"
    )

run_config = RunConfig(
    streaming_mode=streaming_mode,
    response_modalities=modality,
    session_resumption=types.SessionResumptionConfig(),
    speech_config=speech_config
)

live_request_queue = LiveRequestQueue()

live_events = runner.run_live(
    session=session,
    live_request_queue=live_request_queue,
    run_config=run_config
)

Observing events and place of crash

async def agent_to_client(websocket: ServerConnection, live_events: AsyncGenerator[Event, None]):
    """Listens to events from the agent and forward them to the client."""
    try:
        async for event in live_events:
            logging.info(f"AGENT EVENT: {event}")
            try:
                if event.turn_complete or event.interrupted:
                    await websocket.send(
                        system_message({"turn_complete": event.turn_complete, "interrupted": event.interrupted}))
                    continue

                part: Optional[types.Part] = event.content and event.content.parts and event.content.parts[0]
                if not part:
                    continue

                if part.inline_data and part.inline_data.mime_type.startswith("audio/pcm"):
                    audio_data = part.inline_data.data
                    if audio_data:
                        await websocket.send(AUDIO_HEADER + audio_data)
                        logging.info(f"[AGENT->CLIENT]: audio/pcm: {len(audio_data)} bytes.")
                elif part.text and event.partial:
                    await websocket.send(agent_message("text/plain", part.text))
            except Exception as e:
                await websocket.send(exception_json(e))
                logging.error(f"Error processing single agent event: {e}")
    except Exception as e:
        await websocket.send(exception_json(e))
        logging.error(f"Agent-to-client loop failed: {e}")
    finally:
        logging.info("Exiting agent-to-client loop.")

Error in "Agent-to-client" log
When I run this code:

• It successfully creates a session
• after 1-2s connection is closed with the following error:

google_adk.google.adk.flows.llm_flows.base_llm_flow:Connection closed: received 1007 (invalid frame payload data) Request contains an invalid argument.; then sent 1007 (invalid frame payload data) Request contains an invalid argument.

When I run AUDIO without speech config it works as expected.

[ParohyGr]

Also having both multiple modality like [TEXT, AUDIO] and no speech_config, it fails as well with the same error.

[hangfei]

This is likely a Gemini Live API issue. Please reach out to Gemini Live API team.

Do you see it works without cloudrun and with speech config?

[ParohyGr]

It is giving me the same error If I run it locally on my machine.

[adk-bot]

Response from ADK Answering Agent (experimental, answer may be inaccurate)

TLDR: This error likely stems from one of two issues: 1) The audio format being sent from your client (e.g., sample rate) does not match what the server expects for bidirectional streaming, or 2) The underlying LLM is not compatible with the Gemini Live API, which is required for audio modality.

---

Hello! Thanks for the detailed report. The error Connection closed: received 1007 (invalid frame payload data) strongly suggests a mismatch between the audio stream being sent from your client and the format the backend service expects. This is consistent with the fact that the error appears when you request AUDIO in response_modalities, which activates the real-time audio processing pipeline.

Here are a couple of things to check:

1. Client-Side Audio Format: For bidirectional streaming (Speech-to-Text), the backend is very specific about the incoming audio format. Please ensure your client is sending single-channel (mono) audio encoded as Linear PCM with a 16kHz sample rate. Any other sample rate (e.g., 44.1kHz, 48kHz, or even the 24kHz used for output audio) will cause the connection to be rejected with an "invalid frame payload" error.

2. Model Compatibility: Bidirectional audio streaming requires using a model that specifically supports the Gemini Live API. [1] If the model configured in your agent does not support this, the API will reject the request when audio modality is enabled. Please verify that your agent is configured to use a compatible model. [2]

Your observation that it also fails with [TEXT, AUDIO] and no speech_config is a key clue that the issue is with enabling the audio output modality itself, which triggers these stricter requirements.

[1] https://google.github.io/adk-docs/deploy/gke/
[2] https://google.github.io/adk-docs/streaming/custom-streaming/