google-gemini-api - Google Gemini API Integration for Multimodal AI Generation
Integrates with Google Gemini API for text generation, multimodal processing, function calling, and streaming capabilities
Tags
Updated: 2026-02-09Capabilities
Typical Inputs
Typical Outputs
What this skill does
- generate text content
- process images
- handle video files
- process audio inputs
- parse PDF documents
- execute function calls
- stream responses
- configure thinking mode
- manage chat conversations
Inputs
- Google API key
- text prompts
- image files
- video files
- audio files
- PDF documents
- function schemas
- system instructions
- model parameters
Outputs
- generated text responses
- multimodal responses
- streamed content chunks
- function call results
- usage metadata
Requirements
- Google Gemini API key
- Node.js runtime (for SDK)
- @google/genai SDK v1.27+
- JavaScript/TypeScript environment
- Internet connectivity