Orchestrate multimodal analysis and content generation via Google's Gemini API.
npx skills add https://github.com/tntdev21/3d --skill ai-multimodal-tntdev21
Please help me install this Agent Skill. Skill: ai-multimodal Source: https://github.com/tntdev21/3d/tree/main/.claude/skills/ai-multimodal Command: npx skills add https://github.com/tntdev21/3d --skill ai-multimodal-tntdev21
This Skill enables end-to-end multimodal workflows: analyzing and transcribing audio, understanding and describing images, processing PDFs, extracting structured data, and generating images/videos from prompts using Google Gemini's multimodal models.
Set GEMINI_API_KEY, install dependencies, then run:
High-intent search queries and answers about installing and using this skill.
Multimodal audio transcription extracts speech with temporal markers and analyzes sound content using Gemini's API. Run `python scripts/gemini_batch_process.py --files <audio> --task analyze` to transcribe with timestamps, extract speaker intent, and perform music or sound analysis in one workflow.
Yes. This Skill processes PDFs and DOCX files through OCR, form extraction, and structured data retrieval using Gemini's document understanding. Dependencies include pypdf and python-docx for format handling; run batch processing to extract and convert documents to searchable text.
Use Imagen 4 for image generation and Veo 3 for video creation via Gemini's multimodal API. Set `IMAGE_GEN_MODEL` and `VIDEO_GEN_MODEL` environment variables, then run `python scripts/gemini_batch_process.py --task generate --prompt "<text>" --model imagen-4.0-generate-001` to create media at scale.
Yes. The `gemini_batch_process.py` script handles batch analysis and generation across audio, images, video, and documents. It manages token/context limits up to 2M tokens, applies media optimization, and provides error handling for large-scale workflows.
Yes. Gemini's multimodal models enable image captioning, object detection, segmentation, and visual question answering. Use batch processing to analyze multiple images, extract visual content, and generate descriptive captions or structured metadata.
Supported models include Imagen 4 for images, Veo 3 for video, and Gemini 3/2.5 for analysis. Set defaults via environment variables (`GEMINI_MODEL`, `IMAGE_GEN_MODEL`, `VIDEO_GEN_MODEL`) for backward compatibility, or specify per-task in batch processing commands.
resultanyildiziGenerate and edit images via Google's Gemini 3 Pro Image API.
hmzainjamilConvert office and document files between common formats in batch.
shahmirerrorConvert data, documents, and images across common formats using Python libraries.
lengo0951Process images, audio, and video with the Gemini API.
