Welcome to the Gemini API Cookbook

This cookbook provides a structured learning path for using the Gemini API, focusing on hands-on tutorials and practical examples.

For comprehensive API documentation, visit ai.google.dev.

For Gemma quickstarts and examples, check out the Gemma cookbook.

---

Gemini 3.8 Flash: Our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows. Get started with the Get Started and the thinking guides.

🎙️ Gemini 3.8 TTS & Custom Voices: Generate expressive single- and multi-speaker speech with Gemini 3.8 TTS , and design custom voices from text or replicate voices from audio with the new Voices guide !

Omni Flash: The Nano Banana of video editing is here! Learn how to call the model using the interactions API, edit videos with natural language and more here !

🍌 Nano-Banana 2: Go bananas with our latest image generation model: Nano-Banana 2. Get started here with 512px, thinking, search and image grounding, and a ton of examples!

🎶 Lyria 3.5: Channel your inner composer with Lyria 3.5. Get started here with full song generation, image-to-music, and a ton of examples!

Agents API: Create and run your custom agents using the new Antigravity agent !

---

Navigating the Cookbook

This cookbook is organized into two main categories:

1. Quick Starts: Step-by-step guides covering both introductory topics ("Get Started ") and specific API features.
2. Examples: Practical use cases demonstrating how to combine multiple features.

We also showcase Demos in separate repositories, illustrating end-to-end applications of the Gemini API.

What's New?

Here are the recent additions and updates to the Gemini API and the Cookbook:

• 🎙️ Gemini 3.8 TTS, Voice Design & Voice Replication: Generate expressive single- and multi-speaker speech with the TTS quickstart , and design custom voices from text or replicate voices from audio with Voices (Voice Design & Replication) .
• Gemini 3.8 Flash: Our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows. Learn how to build with the model in the Getting started cookbook .
• Gemini 3.5 Flash-Lite: The fastest, lowest-cost model in the 3.5 family. Outperforms prior Flash-Lite generations for high-throughput execution. Learn more in the Getting started cookbook .
• Omni Flash: Get started with conversational video generation and editing using Gemini Omni Flash and the Interactions API in the Omni Flash guide!

1. Quick Starts

The quickstarts section contains step-by-step tutorials to get you started with Gemini and learn about its specific features.

To begin, you'll need:

1. A Google account.
2. An API key (create one in Google AI Studio).
   
   

We recommend starting with the following:

• Authentication : Set up your API key for access.
• Get Started : Get started with Gemini models and the Gemini API, covering basic prompting and multimodal input.
  
  

Then, explore the other quickstarts tutorials to learn about individual features:

• Get started with Text-to-Speech (TTS) and Voices (Voice Design & Replication) : Generate expressive single- and multi-speaker speech, design custom voices from text prompts, or replicate voices from audio samples
• Get started with Live API : Get started with the live API with this comprehensive overview of its capabilities
• Get started with Live Extended Thinking : Use extended thinking in real-time Live API sessions with conversational filler cues and non-blocking background tools
• Get started with Live Translation : Translate audio streams in real-time using the Live Translation API
• Get started with Gemini Transcribe : Transcribe audio files and real-time streams with word-level timestamps, speaker diarization, and smart transcription

2. Examples (Practical Use Cases)

These examples demonstrate how to combine multiple Gemini API features or 3rd-party tools to build more complex applications.

• Browser as a tool : Use a web browser for live and internal (intranet) web interactions
• Illustrate a book : Use Gemini to create illustration for an open-source book
• Animated Story Generation : Create animated videos by combining Gemini's story generation, Imagen, and audio synthesis
• Plotting and mapping Live : Mix Live API and Code execution to solve complex tasks live
• 3D Spatial understanding : Use Gemini 3D spatial abilities to understand 3D scenes
• Cost Estimation and Health Monitoring : Build an observability layer for Gemini API applications to estimate USD costs and monitor health

3. Demos (End-to-End Applications)

These fully functional, end-to-end applications showcase the power of Gemini in real-world scenarios.

• Gemini CLI: Open-source AI agent that brings the power of Gemini directly into your terminal
• Gemini API quickstart: Python Flask App running with the Google AI Gemini API, designed to get you started building with Gemini's multi-modal capabilities
• Multimodal Live API Web Console: React-based starter app for using the Multimodal Live API over a websocket
• Fullstack Langgraph Quickstart: A fullstack application using a React frontend and a LangGraph-powered backend agent
• Google AI Studio Starter Applets: A collection of small apps that demonstrate how Gemini can be used to create interactive experiences
  
  

Official SDKs

The Gemini API is a REST API. You can call it directly using tools like curl (see REST examples or the great Postman workspace), or use one of our official SDKs:

• Python
• Go
• Node.js
• Java
• C#
  
  

Get Help

Ask a question on the Google AI Developer Forum.

The Gemini API on Google Cloud Vertex AI

For enterprise developers, the Gemini API is also available on Google Cloud Vertex AI. See this repo for examples.

Contributing

Contributions are welcome! See CONTRIBUTING.md for details.

Thank you for developing with the Gemini API! We're excited to see what you create.