Gemini 3.1 Flash Live: Google's latest AI audio model

Image: Primary

Published Friday, June 26, 2026 · 6:20 PM EDT

Google introduced Gemini 3.1 Flash Live, its newest audio and voice model for real-time dialogue. The model is available in preview for developers through the Gemini Live API in Google AI Studio. Enterprises can access it in Gemini Enterprise for Customer Experience. It is also available to users through Search Live and Gemini Live. Google reported that the model achieved a score of 90.8 percent on ComplexFuncBench Audio, a benchmark for multi-step function calling. It scored 36.1 percent on Scale AI's Audio MultiChallenge with thinking enabled. The model shows improved tonal understanding and better recognition of acoustic nuances such as pitch and pace compared with 2.5 Flash Native Audio. It also adjusts responses more effectively to expressions of frustration or confusion. Verizon, LiveKit and The Home Depot provided positive feedback on its natural conversation capabilities in their workflows. In Gemini Live and Search Live the model produces faster responses and maintains conversation threads for twice as long as the prior version. The model is multilingual and supports the expansion of Search Live to more than 200 countries and territories. All audio output includes a SynthID watermark.

Sources

Google

In this story

Google

Published by Tech & Business, a media brand covering technology and business. This story was sourced from Google and reviewed by the T&B editorial agent team.

Back to Newswire

Keep reading

Full wire

Robotics Capital

Path Robotics raises $300 million at $2.45 billion valuation

Path Robotics has secured $300 million in new financing, Bloomberg reported. The funding nearly quadruples the startup's valuation to $2.45 billion.

Security

Git releases fixes for six vulnerabilities, including recursive-clone code execution

The Git project released patches for six security vulnerabilities, including a flaw that can execute attacker-controlled code when a user recursively clones a malicious repository, GitHub announced. Fixes are available in Git 2.56.1 and six maintenance releases.

AI Capital

Ancep raises $8.5M to automate insurance brokers' administrative work

London-based Ancep has raised $8.5M in a round led by Creandum, with Kleiner Perkins and Vicus Ventures participating. The company will use the funding to expand and hire staff for its business developing AI agents for commercial insurance brokers.

Capital Security

Dreeze emerges from stealth with $33M seed funding

Dreeze has emerged from stealth with $33M in seed funding, CTech reported. Zerto founders Ziv and Oded Kedem joined Avi Raichel to launch the company, which aims to help businesses recover from cyberattacks by restoring entire cloud applications.

Google opens Gemini 4 Carbon to paying API users and Ultra subscribers

Google made Gemini 4 Carbon available to paying developers and enterprises through its API, with a rollout also starting for Google AI Ultra subscribers. Introductory API pricing is $2 per million input tokens and $10 per million output tokens, matching Gemini 4 Argon.

Capital

AstraZeneca acquires Omniose and its vaccine manufacturing platform

AstraZeneca has acquired Omniose, a preclinical biotechnology company developing vaccines against serious bacterial infections, following three years of exclusive research collaboration.