Extract video chapters

Extract the chapters in a video as structured JSON

You can query a model directly and test the results returned when using different parameter values with the Cloud console, or by calling the Vertex AI API directly.

Prompt Freeform

Chapterize the video content by grouping the video content into chapters and providing a summary for each chapter. Please only capture key events and highlights. If you are not sure about any info, please do not make it up. Return the result in the JSON format with keys as follows : "timecode", "chapterSummary"

Response

[
  {
    "timecode": "0:00-0:19",
    "chapterSummary": "A panoramic view of Rio de Janeiro, highlighting the iconic Christ the Redeemer statue, Copacabana Beach, and the vibrant city life."
  },
  {
    "timecode": "0:19-0:28",
    "chapterSummary": "Introduction to the favelas of Rio, a significant part of the city often depicted negatively in the media."
  },
  {
    "timecode": "0:28-0:37",
    "chapterSummary": "Challenging the stereotypical portrayal of favelas, showcasing the everyday lives and resilience of its inhabitants."
  },
  {
    "timecode": "0:37-0:49",
    "chapterSummary": "Google's initiative to map the favelas, emphasizing the importance of recognizing their identity and address."
  },
  {
    "timecode": "0:49-0:57",
    "chapterSummary": "An invitation to explore the favelas through Google's 360° virtual tour."
  }
]
Model: gemini-1.5-flash-001
Temperature: 1
Max output tokens: 8192
TopK: 40
TopP: 0.95