# Multimodal AI Models for Legal

> Note: This article is just one of 60+ sections from our full report titled: The 2024 Legal AI Retrospective - Key Lessons from the Past Year .

**Author:** Alex Denne  
**Category:** Insights  
**Published:** 2024-12-18  
**Reading time:** 3 min

**Note:** This article is just one of 60+ sections from our full report titled: [The 2024 Legal AI Retrospective - Key Lessons from the Past Year](https://www.genieai.co/blog/legal-ai). Please download the full report to check any citations.

**Multimodal Models**

NLP has expanded beyond text:

 • Text-to-Video Generation: Models can now generate short video clips from textual descriptions, marking a significant leap in multimodal AI.[68]

 • Cross-modal Understanding: Improved integration of text, image, and audio modalities for more comprehensive language understanding.[69]

---

This is the Markdown representation of [https://www.genieai.co/blog/legal-ai-multimodal-models](https://www.genieai.co/blog/legal-ai-multimodal-models), provided for AI agents and crawlers. The HTML page is canonical. See [/llms.txt](https://www.genieai.co/llms.txt) for the full content map.