Overview
Google Gemini is Google’s AI assistant for conversation, learning, research, writing, coding, and creative work. The Gemini product is available on the web and through mobile apps, while Google’s developer documentation describes text, image, video, audio, tool use, live voice and video, and managed-agent capabilities. People can use Gemini for everyday questions and more involved multimodal tasks. Developers use the separate Gemini API and Google AI tools to build applications and agents. The consumer Gemini product and its model-serving systems are proprietary rather than open-source software.