Process audio, video, images, and documents via Google Gemini's multimodal API.
npx skills add https://github.com/Tietve/Lawweb --skill ai-multimodal-tietve
Please help me install this Agent Skill. Skill: ai-multimodal Source: https://github.com/Tietve/Lawweb/tree/main/.claude/skills/ai-multimodal Command: npx skills add https://github.com/Tietve/Lawweb --skill ai-multimodal-tietve
This Skill unifies processing of audio, images, video, and documents via Gemini's multimodal API, enabling automated analysis and content generation across media types.
Example: Transcribe an audio file and generate an image from a text prompt, or ask for a caption for an image using Gemini multimodal.
High-intent search queries and answers about installing and using this skill.
Gemini's multimodal API transcribes audio files up to 9.5 hours long with timestamps and summaries. Upload your audio file via the File API or provide inline data, send a transcription prompt, and receive structured JSON or text output with word-level timing and content analysis.
Yes, Gemini multimodal processes PDFs and office documents (Word, Excel) to extract tables, forms, and text via OCR. Upload files or images, specify extraction requirements in your prompt, and receive structured JSON results with organized field mappings and multi-page context.
Upload video files up to 6 hours to Gemini multimodal for scene detection, visual Q&A, and transcription with visual context. Gemini processes video frames and audio together, returning structured analysis of objects, actions, and spoken content in JSON or markdown format.
Gemini 2.5-flash-image model generates images from text descriptions with style control. Provide your prompt specifying visual elements and style preferences; the API returns generated images you can save locally or integrate into downstream workflows.
Yes, the Skill supports batch processing across audio, video, and document files. Process multiple items in one workflow, apply the same prompt or varied prompts per file, and receive consolidated JSON or markdown results with per-file identifiers.
Gemini processes audio up to 9.5 hours, video up to 6 hours, PDFs, DOCX, images, and office documents. The API supports inline data and File API uploads, with context windows up to 2M tokens, enabling processing of large documents and long media without format conversion.
danielctcProcess audio, images, video, and documents with Google Gemini APIs.
jackspaceConvert PDFs, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, and images into Markdown.
RooseveltAdvisorsCreate, edit, and analyze Microsoft Word .docx files with tracked changes.
tntdev21Orchestrate multimodal analysis and content generation via Google's Gemini API.
