NEWS · MODELS · #2212
TwelveLabs' Pegasus 1.5 is now available on Amazon Bedrock
TwelveLabs has made Pegasus 1.5 — a video language model that converts long-form video into structured, timestamped JSON metadata — available on Amazon Bedrock. New features include full-video segmentation, multimodal prompting with reference images, on-the-fly processing with no pre-indexing, and extended single-request analysis up to two hours; calls are made via the bedrock-runtime InvokeModel or InvokeModelWithResponseStream APIs and can process video from an S3 URI or a base64 string while keeping data within the AWS boundary.
KEY POINTS
- TwelveLabs has made Pegasus 1.5 — a video language model that converts long-form video into structured, timestamped JSON metadata — available on Amazon Bedrock.
- New features include full-video segmentation, multimodal prompting with reference images, on-the-fly processing with no pre-indexing, and extended single-request analysis up to two hours; calls are made via the bedrock-runtime InvokeModel or InvokeModelWithResponseStream APIs and can process video from an S3 URI or a base64 string while keeping data within the AWS boundary.
- This release makes scalable, timestamped video understanding directly usable inside AWS workflows without pre-indexing, lowering the effort to extract structured insights from long-form video.
WHY IT MATTERS
This release makes scalable, timestamped video understanding directly usable inside AWS workflows without pre-indexing, lowering the effort to extract structured insights from long-form video.