TwelveLabs Pegasus 1.5 Launches on Amazon Bedrock for Video Metadata Extraction

1 reports archived1 independent sourcesupdated 10/20/2026, 00:49:19

Synthesis & Latest Updates

1 Sources Cross-Validated

TwelveLabs' video language model Pegasus 1.5 is now available on Amazon Bedrock. It enables automated extraction of structured, timestamped metadata from long-form videos without pre-indexing, supporting multimodal prompting and real-time processing to streamline video content understanding.

LATEST/TwelveLabs' video language model Pegasus 1.5 is now available on Amazon Bedrock. It enables automated extraction of structured, timestamped metadata from long-form videos without pre-indexing, supporting multimodal prompting and real-time processing to streamline video content understanding.

HEAT TRENDHourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

TIMELINECoverage timeline

Total 1 reports · Latest first

AWS Machine Learning BlogT1·Oct 20, 00:4968 pts
TwelveLabs Pegasus 1.5 Launches on Amazon Bedrock for Video Metadata Extraction
- Pegasus 1.5 converts long-form videos into timestamped JSON metadata, addressing the challenge of unsearchable video content
- Supports direct video input via S3 URIs or Base64 strings without requiring pre-indexing
- Introduces video segmentation and multimodal prompting with reference images
View Related Reports & Analysis Original Source