The platform generates texts from your videos 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:

• Summaries: Encapsulates the key points of a video, presenting the most important information clearly and concisely.
• 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.
• Highlights: List the key events in order. Unlike chapters, they spotlight primary topics.
• 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.
• The maximum length of a prompt is 1500 characters.

Follow the steps in this guide to generate text from your videos:

1. Go to the Indexes page, find the index containing the video for which you want to generate text, and choose Select action > Generate:

   

2. Select the video you want to generate text for by choosing it from the Select a video drop-down or selecting the Select video button after hovering over a video in the right pane:

   

3. Decide on the type of text and proceed with the instructions in one of the sections below.

For predefined templates

1. Select the Templates tab:

   

2. From the Select output drop-down, choose one or multiple templates:

   

3. (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:

   

4. (Optional) Provide an output instruction prompt to guide the model. Note that when crafting output instructions, you are limited to changing the tone, length, format, and context of the text output.

   

   Prompt examples:

   • Generate a summary suitable for a high school audience studying environmental science
   • Provide a summary fit for a Twitter post under 280 characters.

5. When you've finished, select the Generate button. The Playground displays the generated text in the pane to the right. For chapters and highlights, you can click on the timecodes to play the exact moments in the video player:

   

6. (Optional) You can select the View code button to open the modal where code snippets for the requests and the responses are displayed. You can copy and paste the relevant code directly into your application.

   

For custom text

1. Select the Build my own tab:

   

2. Provide clear instructions as a prompt 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.

3. (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.

   

4. When you've finished, select the Generate button:

   

   After you select the Generate button, the Playground displays the generated text:

   

5. (Optional) You can select the View code button to view the code snippet that the platform used to perform this request. You can copy and paste it into your application.