Marengo
Marengo enables multimodal video search using text and reference image queries.
What it does
- Vector search
- Video analytics
Features 4
- Single multimodal embeddingCombines visual, audio and language inputs into one embedding, so one query can span all three.
- Text and image queriesQueries video with text, a reference image, or both fused into one embedding.
- Natural-language moment searchFinds moments in video from a natural-language description, a reference image, or both.
- Multilingual searchLets users search video in their own language, with over 100 languages supported.
Sources
- Pricing
-
Pricing page: "Pay-as-you-go rates for usage beyond your plan's included allowances. Overage is available only on the Pro plan."
- Description
-
Official documentation · 5 Nov 2026
Product page: "Multimodal retrieval across visual, audio, dialogue, and on-screen text."
- What it does
-
Official documentation · 5 Nov 2026
Product page: "Multimodal retrieval across visual, audio, dialogue, and on-screen text."
- Sold within
-
Sold on its own with published plans.
- Name
-
Official documentation · 5 Nov 2026
Name as published on the product page.
- URL
-
Official documentation · 5 Nov 2026
Product page, read 2026-11-05.
- Deployment
-
Official documentation · 5 Nov 2026
Product page: "Try search, analysis, and segmentation on your own videos in the browser."
- Interfaces
-
Official documentation · 5 Nov 2026
Product page: "Try search, analysis, and segmentation on your own videos in the browser."
Also from TwelveLabs
-
Jockey AI agent
Searches a library of videos and photos by meaning, explains each clip scene by scene and assembles finished media from the source footage, from Claude, ChatGPT or an API.
-
Compliance by TwelveLabs Application
Reviews a video library against compliance rule packs that a team forks, edits and versions, and returns a ranked queue of flagged moments with timestamped evidence and signed reports.
-
Pegasus Model API
Video-analysis model API (the Analyze endpoint) that reads the visuals, audio and speech of a video of up to two hours, or an image, and returns summaries, chapters, reports, time-coded metadata or any JSON schema the caller defines.
Open TwelveLabs in the directory
Something wrong here? Send a correction — quote this product id: twelve-labs-marengo.