The platform analyzes videos to generate text based on their content using a multimodal approach. This method analyzes the visuals, sounds, spoken words, and relationships between them. As a result, it provides a comprehensive understanding of your videos, capturing nuances that might be overlooked when using an unimodal interpretation.

The platform generates the following types of text:

Topics and hashtags: Represent a swift breakdown of the essence of a video.
Summaries: Encapsulate the key points of a video, presenting the most important information clearly and concisely.
Highlights: List the key events in order. Unlike chapters, they spotlight primary topics.
Chapters: A chapter in a video typically focuses on a particular topic or theme. The platform chronologically lists all the chapters in your video for a thorough content breakdown.
Open-ended text (your own prompt): Custom outputs based on your prompts, including, but not limited to, tables of content, action items, memos, reports, marketing copy, and comprehensive analyses.

Notes

This feature is available only for the indexes that have the Pegasus video understanding engine enabled. See the Create an index section for details.
Your prompts can be instructive or descriptive, or you can also phrase them as questions. For guidance on creating effective prompts, see the Prompt engineering page.
The maximum length of a prompt is 2,000 tokens.

Procedure

Follow the steps in this guide to generate text based on the content of your videos:

From the sidebar, select Analyze.

Choose the Select a video button:
Choose an index and the video for which you want to generate text:

For predefined templates

Select one of the prompt options below the video to generate the corresponding type of text you wish to generate. For summaries, chapters, and highlights, you can provide a custom prompt that guides the model on how to generate the output.

The Playground displays the generated text in the output panel. For chapters and highlights, you can select the timecodes to play the exact moments in the video player.
(Optional) You can select the View code button to view the code snippet the platform used to perform this request. You can copy and paste it into your application.

For open-ended text

In the Input prompt section, provide clear instructions for the desired output:

Prompt examples:
- Generate a company-wide memo based on the announcements made in the video.
- Identify key visual elements, scene changes, and events in the video.
- Generate three taglines for an email marketing campaign based on the video.
(Optional) Temperature is a configurable parameter that controls the randomness of the text output generated by the model. A higher value generates more creative text, while a lower value results in more deterministic text output. Use the Temperature slider to tailor the behavior of the model to your requirements.
When you’ve finished, press Command+Enter or select the button with an upward-pointing arrow icon:

The Playground displays the generated text in the output panel:
(Optional) You can select the View code button to view the code snippet the platform used to perform this request. You can copy and paste it into your application.