Gemini Releases
Google Gemini product news and SDK releases. New features, breaking changes, security advisories and deprecations - each summarised in plain English and updated continuously.
Tracking 77 Gemini releases · Updated
- Gemini Blog ai ·
Vibe-coded schedule app built with Gemini simplifies mornings
A creative technologist built a custom app called Glanceboard using Gemini 3.6 Flash and Nano Banana to transform daily morning routines. The app generates personalized illustrations based on family calendars and local weather, displayed on an e-ink screen to inform users about their schedule and attire. This open-source project aims to provide a serene, personalized, and engaging way to stay organized without relying on bright screens or cloud services.
announcement - Gemini Blog ai ·
Gemini App Updates: July Drop
The Gemini app's July release introduces several new features, including voice interaction on macOS and global availability for Gemini Spark. These updates enhance productivity and personalization for users by offering faster AI models, avatar-based image creation, and expanded app integrations.
feature announcement - Gemini Blog aiengineer ·
Gemini Spark integrates Chrome for automated web errands
Gemini Spark now integrates directly with Chrome, allowing users to automate complex web errands using logged-in accounts and saved passwords, with user permission. This feature aims to simplify tasks like scheduling or booking by leveraging enhanced browsing capabilities, while including security measures for sensitive actions. Access is expanding globally for Google AI Pro subscribers, initially rolling out in the U.S. for the Chrome integration.
feature announcement - Gemini Blog aigaengineer ·
Gemini Robotics ER 2 Enhances Embodied Reasoning for Robots
Google has launched Gemini Robotics ER 2, an updated embodied reasoning model for robots designed to improve real-time decision-making and task planning in physical environments. This release enhances robots' ability to interact with humans, understand their surroundings, and execute multi-step tasks with improved temporal intelligence and adaptability. It is now available to developers via the Gemini API and Google AI Studio, with broader access on Gemini Enterprise Agent Platform.
feature announcement - Gemini Python SDK Releases sdkai ·
Python GenAI SDK v2.16.0 adds environment resource, Maps tool support
The Python GenAI SDK has been updated to version 2.16.0, introducing a new environment resource and enhanced support for Google Maps tool grounding types, including places and routing. This release makes it easier for developers to integrate advanced AI capabilities with location-based services. The update also includes documentation for upcoming major version changes and updates for the 2.15.0 release.
feature patch - Gemini Python SDK Releases sdkai ·
Google Python GenAI SDK Adds Audio Transcription and Enterprise Mode
The Python GenAI SDK version 2.15.0 introduces support for audio transcription capabilities, allowing for more versatile multimodal interactions. It also enhances enterprise mode by enabling API key authentication alongside project and location configurations. These updates are relevant for developers integrating Google's generative AI models into Python applications, offering expanded functionality for handling audio input and more flexible enterprise deployments.
feature patch - Gemini Blog ai ·
Gemini Flash agents streamline dairy farm operations and profitability
A Michigan dairy farmer is using Gemini 3.6 Flash agents to automate the analysis of complex farm data, saving hours of manual work each day. This agentic system integrates siloed data from various sources, calculates daily profitability using a custom metric (Static Variable Margin), and generates concise operational summaries. The approach makes advanced AI tools more cost-effective and accessible for small agricultural businesses.
feature announcement - Genkit Releases sdkaimedia ·
Genkit Go v1.11.0 Adds Telemetry, Vertex AI Support, and Claude Models
Genkit Go v1.11.0 introduces telemetry label propagation and enhances support for Vertex AI with multi-region and apiVersion configurations. The release also registers the latest Claude models from Anthropic and fixes issues with media URL handling in prompts and tool role mapping for Gemini. These updates are relevant for developers integrating AI capabilities into their Go applications.
feature patch - Gemini Python SDK Releases sdkaipreviewdeprecationengineer ·
Google Generative AI Python SDK v2.14.0 adds audio transcription config
The latest release of the Google Generative AI Python SDK, version 2.14.0, introduces new configurations for audio transcription within the GenerateContent API. This update includes deprecation warnings for certain Imagen and LiveConnect configurations, signaling their upcoming removal in a future major version. The changes primarily affect developers using the SDK for generative AI tasks, particularly those involving audio or migrating from older configurations. Audio transcription configuration is now available, while older methods will be phased out.
feature patch - Gemini Blog aiengineer ·
Gemini Live adds visual input for real-time assistance
The Gemini app now features Gemini Live, allowing users to provide visual context through their camera for real-time help. This feature aims to eliminate the need for lengthy descriptions by enabling users to point their camera at objects, error codes, or screens. It supports a variety of use cases, from troubleshooting technical issues to seeking creative advice, and is available for immediate use.
feature announcement - Genkit Releases sdkaideprecationmedia ·
Genkit Python SDK v0.8.0: Expanded Google AI support, multi-region routing
Genkit Python SDK v0.8.0 introduces expanded model support and multi-region routing for Google GenAI and Vertex AI integrations, along with a modernized plugin packaging architecture. This release impacts Python developers integrating with Google's AI services, offering new capabilities like multimodal embeddings and generative video models. A staged rollout maintains compatibility for most plugins while core and Google GenAI packages are updated, with a clear migration path for the renamed Google GenAI plugin.
feature breaking patch - Gemini Blog ai ·
Google Enhances Gemini Intelligence on Samsung Foldables and Wearables
Google is expanding Gemini Intelligence capabilities across Samsung's new Galaxy Z Fold8 and Flip8 devices, enhancing task automation and introducing Gemini Notebook. These updates aim to help users offload daily chores and manage complex projects more effectively, with some features accessible directly from the device's Flex Window or via a watch and glasses integration. The enhancements leverage advanced reasoning and multimodal capabilities, offering a more proactive and integrated AI experience for users.
feature announcement - Gemini Blog aiengineer ·
Google AI Tools for College Student Summer Productivity
Google highlights 13 AI-powered tools and features to help college students with internships, studies, and new skills this summer. These tools, including Gemini and Career Dreamer, offer personalized career advice, study assistance, and creative project support. The article provides practical tips for using these resources to reduce stress and maximize productivity during the summer break, with many features available now.
feature announcement - Genkit Releases sdkaiengineer ·
Genkit v1.40.1: Gemini Tool Role Compatibility Fix
Version 1.40.1 of Genkit resolves an issue where tool roles were not correctly mapped for Gemini compatibility. This update ensures that the 'user' role is properly recognized, which is crucial for developers integrating Genkit with Gemini models. The change is available now as a patch release.
patch - Gemini Python SDK Releases sdkaiengineer ·
Python GenAI client v2.13.0 adds custom vocabulary and model selection
The Python GenAI client library has been updated to version 2.13.0, introducing a `custom_vocabulary` field for `BidiGenerateContentSetup` and a model selector feature. These enhancements improve customization and control for developers working with generative AI models. The update is available now and impacts users integrating AI capabilities into their Python applications.
feature patch - Gemini Blog ai ·
Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber Models Launched
Google has released three new Gemini models: 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber, designed for increased token efficiency, lower latency, and improved performance in production AI agent workflows. These models offer better cost-effectiveness and capabilities for tasks like coding, knowledge work, multimodal analysis, and cybersecurity. Gemini 3.6 Flash and 3.5 Flash-Lite are available starting today through various Google AI platforms and apps.
feature announcement - Gemini Blog aiengineer ·
5 ways to build a side hustle using Gemini
Google's Gemini AI can assist in launching a business by automating complex tasks and accelerating growth. The platform offers features for idea structuring, market research via Deep Research, brand asset generation, logistics automation with Gemini Spark, and pricing analysis. These capabilities are designed to help entrepreneurs turn ideas into profitable ventures with greater efficiency.
feature announcement - Genkit Releases sdkaiengineer ·
Genkit v1.40.0: New Model Support and Multi-Region
Genkit v1.40.0 introduces new capabilities for developers working with AI models. This release includes support for Claude Sonnet 5 across both Anthropic and Vertex AI plugins, along with multi-region support for Google GenAI. These enhancements improve flexibility and integration options for AI-powered applications built with Genkit.
feature patch - Gemini Python SDK Releases sdkaiengineer ·
Google Python GenAI Client Updates for Interaction Normalization
This patch release addresses a bug in the Google Python GenAI client library related to the normalization of Interactions within triggers. The fix ensures that interactions are processed correctly, which is important for the reliable functioning of trigger-based workflows. This update is relevant for developers using the library, especially those implementing custom triggers or advanced interaction handling.
patch - Gemini Blog aiengineer ·
Gemini Adoption and Features in Southeast Asia
Gemini is experiencing record-breaking adoption in Southeast Asia, driven by its local language fluency and a young, tech-savvy population. The app is becoming an indispensable tool for work, study, and daily life, with users leveraging its multi-modal capabilities and creative generation features. Future developments include AI agents like Gemini Spark, integrated with Workspace tools, aimed at proactively managing tasks for users.
feature announcement
About Gemini release tracking on ReleaseBytes
Google's Gemini models and APIs move fast: new model versions, pricing changes, SDK releases and capability launches arrive weekly. ReleaseBytes tracks the official Gemini and Google DeepMind announcement channels and SDK changelogs, so you can see every model update, deprecation notice and API change in one feed.
Frequently asked questions
How often are Gemini release notes updated on ReleaseBytes? ›
Continuously. ReleaseBytes monitors the official Gemini release channels around the clock and publishes a plain-English summary of each announcement shortly after it lands.
What kinds of Gemini changes does ReleaseBytes track? ›
New features, enhancements, bug fixes, security advisories, breaking changes, deprecations and end-of-life announcements. Every item is tagged by type so you can filter to just the changes that need action.
How can I get alerts for new Gemini releases? ›
Set up a free email or Slack alert filtered to Gemini, subscribe to the weekly digest, or follow the RSS feed. Teams can also install the ReleaseBytes GitHub App or connect via MCP.
Where does the Gemini release data come from? ›
From the official sources: Google Gemini product news and SDK releases. Every item links back to the original vendor announcement.