Raised an PR solving issue 1179: gemini-3.1-live model support fix

Server SDKs
,
1

Hi team, I tried picking the issue (#1179). Both issues are addressed, pushAudio() now sends the audio field directly instead of mediaChunks, and generateReply() switches from sendClientContent to sendRealtimeInput({ text }) which works across all Live API models including 3.1. Also cleaned up empty tools and sessionResumption fields in session setup that were causing rejections on stricter versions.
PR: #1186

1 Like
2

Thanks, as you saw (so this is for anyone else who finds this thread), the latest plan was detailed by our Agents JS maintainer in that PR: fix(google): add Gemini 3.1 Flash Live compatibility by swayamg20 · Pull Request #1186 · livekit/agents-js · GitHub

Thanks for the work here. I’m taking over this effort in a follow-up PR: #1189.

Given the discussion and outcome in Python, we should hold off on the generateReply workaround for Gemini 3.1 until we have a proper upstream direction from the Gemini team. Reference: livekit/agents#5251.

So the current plan is to defer full Gemini 3.1 generateReply behavior changes until there is an official fix/guidance.

1 Like