AI & VideoProduct Launch
TwelveLabs launches Marengo 3.0 for video retrieval
TwelveLabs has announced Marengo 3.0, a new multimodal embedding model designed for video retrieval. This iteration supports advanced features including composed queries, multilingual search capabilities, and the processing of long-form video content.
Key Takeaways
- Marengo 3.0 is TwelveLabs’ multimodal embedding model for video retrieval.
- The model supports composed queries for more specific video search.
- Marengo 3.0 adds multilingual search capabilities.
- The model is designed to process long-form video content.
Why It Matters
Marengo 3.0 expands the core retrieval layer for video applications by combining multimodal embeddings with composed queries, multilingual search, and long-form video processing. That matters for teams building search and discovery across large video libraries, where finding the right clip often depends on more than a single keyword. The key signal to watch is how TwelveLabs positions Marengo 3.0 in real deployments and what video lengths or language coverage it publicly supports.
Read full article at twelvelabs.io