API ReferenceGenerate text from video

Open-ended texts

This endpoint generates open-ended texts based on your videos, including but not limited to tables of content, action items, memos, and detailed analyses.

Notes
  • This endpoint is rate-limited. For details, see the Rate limits page.
  • This endpoint supports streaming responses. For details on integrating this feature into your application, refer to the Streaming response guide.

Headers

x-api-keystringRequired

Request

This endpoint expects an object.
video_idstringRequired

The unique identifier of the video for which you wish to generate a text.

promptstringRequired

A prompt that guides the model on the desired format or content.

Notes
  • Even though the model behind this endpoint is trained to a high degree of accuracy, the preciseness of the generated text may vary based on the nature and quality of the video and the clarity of the prompt.
  • Your prompts can be instructive or descriptive, or you can also phrase them as questions.
  • The maximum length of a prompt is 375 tokens.

Examples:

  • Based on this video, I want to generate five keywords for SEO (Search Engine Optimization).
  • I want to generate a description for my video with the following format: Title of the video, followed by a summary in 2-3 sentences, highlighting the main topic, key events, and concluding remarks.
temperaturedoubleOptional

Controls the randomness of the text output generated by the model. A higher value generates more creative text, while a lower value produces more deterministic text output.

Default: 0.2 Min: 0 Max: 1

streambooleanOptionalDefaults to false

Set this parameter to true to enable streaming responses in the NDJSON format.

Default: false

Response

The specified video has successfully been processed.

Generate Create Response Dataobject

When the value of the stream parameter is set to false, the response is as follows:

OR
Generate Create Response Oneobject

When the value of the stream parameter is set to true, the platform provides a streaming response in the NDJSON format.

The stream contains three types of events:

  1. Stream start
  2. Text generation
  3. Stream end

To integrate the response into your application, follow the guidelines below:

  • Parse each line of the response as a separate JSON object.
  • Check the event_type field to determine how to handle the event.
  • For text_generation events, process the text field as it arrives. Depending on your application’s requirements, this may involve displaying the text incrementally, storing it for later use, or performing any tasks.
  • Use the stream_start and stream_end events to manage the lifecycle of your streaming session.

Errors