Get the top 6 updates from Firebase for August 2026 in the latest Firebase Release Notes, ranging from the latest Gemini models in AI Logic to new Firebase CLI features designed for your AI agents π₯π
Chapters:
0:00 - Firestore updates
0:57 - Cloud Functions and Extensions
1:47 - Firebase AI Logic updates
3:00 - Major SDK and CLI releases
3:41 - App Check News
4:13 - Firebase ML deprecation
Gemini text-to-speech (TTS) models enable direct audio generation from text prompts in apps via Firebase AI Logic π
This means you can now add natural, customizable voice generation features into your mobile and web apps to create richer, more engaging experiences.
Spend caps are designed to act as a circuit breaker for services like the Gemini API and Cloud Functions, helping to reduce the risk of a financial surprise from a simple coding error or an unexpected spike in traffic.
Learn more β
Introducing spend caps for Firebase services, a much-requested feature designed to give you more financial control οΏ½οΏ½οΏ½
Leverage these powerful new capabilities to build and scale your projects without worrying about unexpected costs β
Introducing spend caps for Firebase services, a much-requested feature designed to give you more financial control π
Leverage these powerful new capabilities to build and scale your projects without worrying about unexpected costs β
Spend cap budgets are currently available in Public Preview, and we're working hard to improve the experience, as well as add new configurability options and more eligible services.
Get help or information about Firebase and your project, and access agentive AI tools that can make changes to your code and Firebase project: https://t.co/iQ0fc9c3ie
πΈ Firebase agent skills πΈ
Install portable packages of instructions, best practices, and scripts into AI coding agents like Antigravity, Claude Code, and Cursor.
Testing and measuring the success of AI agents and skills is one of the hardest parts of building reliable AI apps.
π₯ Today on #FirebaseAfterHours, we'll explore the concept of "Eval-Driven Development" and discuss how you can write, run, and interpret the results of your evals using open-source frameworks like Inspect AI.