Gemini 3.1 Flash Live

Real-time voice dialogue model: text, images, audio and video in, speech and text out. Acoustic nuance detection and low latency are stated. Runs over the Live API.

Превью. Проактивное аудио и affective dialogue в этой версии пока не поддерживаются.

Understands

text, images, audio, video

Produces

speech, text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.