Pegasus is a generative model for video-to-text generation. The current version is Pegasus 1.2.

Pegasus processes multiple modalities in video content to generate contextually relevant text based on the content of your videos.

Key features

• Video-to-text generation: Creates detailed textual descriptions based on video content
• Extended processing capacity: Processes videos up to 1 hour in length
• Granular visual comprehension: Analyzes objects, on-screen text, and numerical content
• Temporal grounding: Accurately identifies timestamps of specific events
• Multimodal understanding: Combines visual, audio, and textual information for comprehensive analysis

Use cases

• Content summarization: Generate concise summaries of video content
• Detailed descriptions: Create comprehensive textual descriptions of visual scenes
• Timestamp identification: Answer questions about when specific events occur in videos
• Content analysis: Extract key information from video content for further processing

Examples

This section contains examples of using the Pegasus video understanding model.

Summarizing educational videos

In the example screenshot below, the platform has summarized an educational video using predefined templates without any customization:

To see this example in the Playground, ensure you’re logged in, and then open this URL in your browser.

Generating captions for social media

In the example screenshot below, the prompt instructs the platform to generate a caption for a social media post:

To see this example in the Playground, ensure you’re logged in, and then open this URL in your browser.

Writing police reports

In the example screenshot below, the prompt instructs the platform to write a police report using a specific template for a video showing a robbery:

To see this example in the Playground, ensure you’re logged in, and then open this URL in your browser.

Using different languages

This sections provides example of using different languages to generate text from videos.

Spanish

The following example summarizes a video, indicating that the response should be in Spanish. Note that the prompt is in English, and the output is in Spanish.

To see this example in the Playground, ensure you’re logged in, and then open this URL in your browser.

French

The following example summarizes the main three takeaways from this video. Note that the prompt and the output are in French.

To see this example in the Playground, ensure you’re logged in, and then open this URL in your browser.

Support

For support or feedback regarding Pegasus, contact support@twelvelabs.io.