Models/Twelve Labs/Marengo 3.0

Marengo 3.0

Twelve Labs 📐 Embedding

Twelve Labs multimodal video embedding model. Converts video, audio, and text into a shared vector space for semantic search across 36 languages.

Specifications

ModalitiesInput: video, audio, text, image  ·  Output: embedding
FeaturesTools: No Streaming: No

Pricing

Included with plan

Capabilities

embeddingsearch
Use Marengo 3.0 on Zubnet →

More from Twelve Labs

P
Pegasus 1.2
Twelve Labs video understanding model. Summarizes, analyzes, and answers questions about video content with visual and audio comprehension.
🧠 Language Model