encord-team/ebind
A 5-way embedding model for text, audio, image, video, and 3D point clouds.
This project helps you compare and relate data across different types, such as text descriptions, images, video clips, audio recordings, and 3D models. It takes these varied inputs and translates them into a universal format, allowing you to find similarities between, for example, a picture of a dog and an audio recording of a dog barking. This is ideal for researchers and machine learning engineers working with diverse media.
Use this if you need to understand the relationships and similarities between different kinds of media data, like matching a product image to its spoken description or finding videos related to a 3D model.
Not ideal if your project only involves a single type of data or if you need to analyze relationships within one specific modality.
Stars
11
Forks
3
Language
Python
License
—
Category
Last pushed
Nov 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/encord-team/ebind"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
embeddings-benchmark/mteb
MTEB: Massive Text Embedding Benchmark
harmonydata/harmony
The Harmony Python library: a research tool for psychologists to harmonise data and...
yannvgn/laserembeddings
LASER multilingual sentence embeddings as a pip package
embeddings-benchmark/results
Data for the MTEB leaderboard
Hironsan/awesome-embedding-models
A curated list of awesome embedding models tutorials, projects and communities.