Lightlines
By mrgoonie

ai-multimodal

mrgoonie527 installs

Analyze your media or create images with Gemini.

What it does

Analyzes audio, images, videos, and documents and generates images through the Gemini API.

When to use it

Use for media analysis, transcription, document extraction, image creation, or implementing multimodal AI features.

How to use it

Give it media files to process or an image-generation request; it saves extracted results or generated images in the project.

What you provide

  • Your files

Uses

Good to know

  • cannot be undone: Google Gemini

Latest review

What you need · 7

The bundled scripts require Python 3.10 or newer.

The processing scripts require the Google Gen AI SDK; setup includes installing it.


Access · 4

This skill

Google Gemini

Write

Uploads media to Gemini (irreversible)

google-genai

Execute

Installs the Gemini SDK