Gemini 3.1 Flash Live model released

Try  Lyria 3 , our new music generation model capable of producing high-fidelity stereo audio from text and image inputs.
March 23, 2026
Rolled out  Prepay and Postpay billing plans  in
AI Studio. Existing accounts may be affected; read the  Billing  documentation for more information.
March 19, 2026
Updated OpenAI compatibility feature to support  gemini-3-pro-image-preview
and the  /v1/videos  endpoint with our  veo-3.1-generate-preview  model.
Last updated 2026-03-25 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2026-03-25 UTC."],[],[]]

Try the new  Gemini 3.1 Flash Live  audio-to-audio model in  AI Studio .
March 26, 2026
Released   gemini-3.1-flash-live-preview  , the latest
audio-to-audio (A2A) model designed for real-time dialogue and voice-first
AI applications. Read the  Live API  docs to get
started.
Last updated 2026-03-26 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2026-03-26 UTC."],[],[]]