TwelveLabs' Pegasus 1.5 is now available on Amazon Bedrock. This video language model processes long-form video content to produce structured, timestamped metadata. Users can define specific moments or criteria, and the model returns matching video segments in JSON format.
Video content often remains unsearchable and underutilized due to its unstructured nature. Pegasus 1.5 aims to address this by automating the extraction of actionable insights, a process that previously required manual review or fragmented toolchains. This allows for more efficient analysis and retrieval of information from video.
Pegasus 1.5 introduces several new capabilities. It analyzes entire videos to find segments matching user-defined criteria, returning structured, timestamped metadata. New features include video segmentation, multimodal prompting with reference images, and on-the-fly processing. The model can now analyze videos up to two hours long, an increase from the one-hour limit in Pegasus 1.2.
With Pegasus 1.5 on Amazon Bedrock, users can analyze videos directly from an Amazon S3 URI or a base64 string without pre-indexing. Data processing occurs within the AWS data boundary, ensuring data residency. This integration simplifies the workflow for AWS users.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
TwelveLabs' Pegasus 1.5, a video language model, is now available on Amazon Bedrock. This update allows for the analysis of long-form video to generate structured, timestamped metadata, enabling better searchability and utilization of video content.