← Back to Discover

Google AI Studio

Google's site for trying its Gemini, image, video, speech and music models, getting a Gemini API key and remixing example apps built on the Gemini API.

Model APIsApp builders
Visit website ↗

What it does

Google AI Studio is Google's site for experimenting with its latest generative models and starting to build with the Gemini API. The front page lists Gemini 3 for reasoning, Nano Banana for image generation, Veo for video, Gemini TTS for controllable speech, Gemini Live for real-time voice and video interactions, Omni for video editing and creation, and Lyria for music generation. For developers, the page points to API key management with usage monitoring, official SDKs for Python, JavaScript, Go, Java and C++, an Interactions API for stateful multi-turn agents with managed tool execution, and a tools section covering function calling with Search and Maps grounding. A gallery of projects can be remixed, including a multiplayer snake game, an app that generates window views and a city-management game. Starter ideas include a language-learning partner, a background remover and a garden designer. Case studies from Shopify, Holywater and CompScience show how developers use the Gemini API. The page does not state prices.

Capabilities

  • Try Gemini, Nano Banana, Veo, Gemini TTS, Gemini Live, Omni and Lyria models
  • Create and manage Gemini API keys and monitor usage
  • Official SDKs for Python, JavaScript, Go, Java and C++
  • Interactions API for stateful multi-turn agents
  • Function calling with Search and Maps grounding
  • Gallery of example apps you can remix

When to use it

  • You want to prototype with Google's models before writing application code
  • You need a Gemini API key and a place to monitor its usage
  • You want a starting point you can remix into your own app