Gemini-2.0-flash-live-001 model call starts silent, no greeting or system instruction honored on first connection

Gemini API Documentation
,
1

Hello everyone,

I’m using the Gemini-2.0-flash-live-001 model for voice calls. When a call connects, the system instruction (like a greeting message) is not played initially—the call goes silent. Only after the user starts speaking does Gemini respond.

This issue does not occur with OpenAI’s models. In Ultravox, there is a parameter called "firstSpeaker": "FIRST_SPEAKER_AGENT" which controls this behavior and ensures the agent speaks first.

Is there a similar parameter or configuration for Gemini to ensure it honors the system instruction and plays the greeting message at the start of the call? Any guidance on how to fix this would be much appreciated.

4

Hello!

You can try to resolve this by configuring your settings as follows:

client = genai.Client(api_key="GOOGLE_API_KEY", http_options={"api_version": "v1alpha"})

config = types.LiveConnectConfig(
    response_modalities=["AUDIO"],
    proactivity={'proactive_audio': True}
)

Please note that “api_version” should be “v1alpha”.

For more details you can refer to live API documentation.

6

Proactive audio is only supported by native audio models