Google today announced Gemini 3.1 Flash Live as its “highest-quality audio and voice model yet” to power big upgrades to Gemini Live and Search Live.
Available in preview via the Gemini Live API in Google AI Studio today, the model is “more effective at recognizing acoustic nuances like pitch and pace” and offers lower latency compared to 2.5 Flash Native Audio. It is better at “discerning relevant speech from environmental sounds like traffic or television.” Specifically, Gemini 3.1 Flash Live “more effectively filters out background noise.”
It also supports over 90 languages for real-time multi-modal conversations. Other improvements include:
- “We’ve significantly improved the model’s ability to trigger external tools and deliver information during live conversations.”
- “Better instruction-following: Adherence to complex system instructions has been boosted significantly. Your agent will stay within its operational guardrails, even when conversations take unexpected turns.”
In Gemini Live on Android and iOS, 3.1 Flash Live delivers faster responses “with fewer awkward pauses” and can “follow the thread of your conversation for twice as long.” This translates to “keeping your train of thought intact during longer brainstorms.” Gemini Live now “dynamically adjusts its answer length & tone to match the moment.”
Google is also using Gemini 3.1 Flash Live to roll out Search Live globally in over 200 countries, or all languages/locations where AI Mode is currently available. This includes the audio and video (Google Lens) capabilities to have a back-and-forth conversation with Google Search.
FTC: We use income earning auto affiliate links. More.
Comments