ADK graph workflows / structured control for streaming voice agents

Hello,
I’m using ADK 2.x graph workflows for deterministic control in text-based agents.

Now I am also trying to build some voice/S2S agents using the Gemini Live API and want to introduce structured control for predictable conversations, but graphs don’t currently support live streaming.

Is there any planned support for:

  • streaming / event-driven graph execution

  • Pipecat-style flows pipelines for voice agents

Or is there a recommended alternative architecture for this use case in ADK?