product update

Google Gemini Live gains access to Memory and Connected Apps from past conversations

TL;DR

Google has updated Gemini Live to access past conversation history through Memory and Connected Apps. The feature, currently available in English in the US, allows the voice assistant to reference previous chats and information from YouTube, Workspace, Utilities, and image generation tools during conversations.

2 min read
0

Google Gemini Live gains access to Memory and Connected Apps from past conversations

Google has updated Gemini Live to access past conversation history, Memory, and Connected Apps, achieving feature parity with the main chat experience.

What's New

Gemini Live can now "use memories of your past chats and info from some Connected Apps," according to Google's support page. The expanded Connected Apps access allows Live to call upon YouTube, Utilities, Workspace, and image generation tools during voice conversations.

The feature follows the same permissions users set for regular Gemini chat. Testing confirms that Gemini Live successfully references previous chat conversations to provide what Google describes as "helpful, tailored responses."

Memory Functionality

According to Google's about page, Gemini Live can "securely remember key details you mention across different sessions, like dietary preferences, important family dates, or your favorite hobbies, so you don't have to keep repeating yourself during future chats."

The Personal Intelligence settings page on Android still indicates Memory is "coming soon to Live," suggesting a phased rollout.

Availability and Context

The Memory access feature is currently available in English in the United States. The update was added to Google's support page sometime after I/O 2026, which introduced deeper integration between Gemini Live and the chat experience for quick switching between voice and text conversations.

Google Messages access for Connected Apps remains unavailable. The update follows last month's Neural Expressive redesign and new voice additions for Gemini Live.

What This Means

This update brings Gemini Live's capabilities in line with the standard text-based Gemini experience, making the voice interface more practical for ongoing conversations. The ability to reference past interactions and pull information from connected services addresses a key limitation that previously made voice assistants feel disconnected from users' broader context. The staggered rollout across different settings pages suggests Google is testing the feature with a subset of users before broader deployment.

Related Articles

product update

Anthropic Merges Claude Cowork Into Chat, Cuts Product Down to Two Modes

Anthropic is merging Claude Cowork with its standard chat interface, dropping Claude from three modes down to two: Chat and Code. The change rolls out to Pro and Max subscribers over the coming weeks, with Claude Docs, Claude Slides, and Claude Design now available directly inside conversations.

product update

Anthropic Merges Claude Chat and Cowork Into Single Unified Product

Anthropic is merging Claude Chat and Cowork into one interface, letting Claude automatically determine task complexity instead of forcing users to switch environments. The update also adds Claude Docs and Claude Slides for creating and exporting documents and presentations directly in chat.

product update

Anthropic Launches Claude Docs and Slides, Merges Chat and Cowork Into 'One Claude'

Anthropic is rolling out Claude Docs and Slides in beta, letting users create and edit documents and presentations directly from Claude chats. The company is also merging regular chats and Cowork into a single unified interface called 'one Claude.'

product update

iOS 27 Adds Opt-In Setting Letting Users Share Data to Train Apple's Foundation Models

iOS 27, released alongside the public launch of Siri AI, adds a new setup prompt asking users to opt in to sharing audio and text data to improve Apple's Foundation Models. The data collected is unchanged from before, but Apple will now also use it to train its foundation models rather than only Siri and Dictation.

Comments

Loading...