使用 Gemini 多模態技術，為含有音訊的影片檔案生成摘要

這個範例說明如何摘要音訊影片檔案，並傳回附有時間戳記的章節。

深入探索

如需包含這個程式碼範例的詳細說明文件，請參閱下列內容：

• 快速入門導覽課程：使用 Vertex AI Gemini API 生成文字

程式碼範例

Go

在試用這個範例之前，請先按照Go使用用戶端程式庫的 Vertex AI 快速入門中的操作說明進行設定。 詳情請參閱 Vertex AI Go API 參考說明文件。

如要向 Vertex AI 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithVideo shows how to generate text using a video input.
func generateWithVideo(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	modelName := "gemini-2.5-flash"
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: `Analyze the provided video file, including its audio.
Summarize the main points of the video concisely.
Create a chapter breakdown with timestamps for key sections or topics discussed.`},
			{FileData: &genai.FileData{
				FileURI:  "gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
				MIMEType: "video/mp4",
			}},
		},
			Role: "user"},
	}

	resp, err := client.Models.GenerateContent(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)

	// Example response:
	// Here's an analysis of the provided video file:
	//
	// **Summary**
	//
	// The video features Saeka Shimada, a photographer in Tokyo, who uses the new Pixel phone ...
	//
	// **Chapter Breakdown**
	//
	// *   **0:00-0:05**: Introduction to Saeka Shimada and her work as a photographer in Tokyo.
	// ...

	return nil
}

Node.js

在試用這個範例之前，請先按照Node.js使用用戶端程式庫的 Vertex AI 快速入門中的操作說明進行設定。 詳情請參閱 Vertex AI Node.js API 參考說明文件。

如要向 Vertex AI 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateContent(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const ai = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const prompt = `
  Analyze the provided video file, including its audio.
  Summarize the main points of the video concisely.
  Create a chapter breakdown with timestamps for key sections or topics discussed.
 `;

  const video = {
    fileData: {
      fileUri: 'gs://cloud-samples-data/generative-ai/video/pixel8.mp4',
      mimeType: 'video/mp4',
    },
  };

  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [video, prompt],
  });

  console.log(response.text);

  return response.text;
}

Python

在試用這個範例之前，請先按照Python使用用戶端程式庫的 Vertex AI 快速入門中的操作說明進行設定。 詳情請參閱 Vertex AI Python API 參考說明文件。

如要向 Vertex AI 進行驗證，請設定應用程式預設憑證。 詳情請參閱「為本機開發環境設定驗證」。

from google import genai
from google.genai.types import HttpOptions, Part

client = genai.Client(http_options=HttpOptions(api_version="v1"))
prompt = """
Analyze the provided video file, including its audio.
Summarize the main points of the video concisely.
Create a chapter breakdown with timestamps for key sections or topics discussed.
"""
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
            mime_type="video/mp4",
        ),
        prompt,
    ],
)

print(response.text)
# Example response:
# Here's a breakdown of the video:
#
# **Summary:**
#
# Saeka Shimada, a photographer in Tokyo, uses the Google Pixel 8 Pro's "Video Boost" feature to ...
#
# **Chapter Breakdown with Timestamps:**
#
# * **[00:00-00:12] Introduction & Tokyo at Night:** Saeka Shimada introduces herself ...
# ...

後續步驟

如要搜尋及篩選其他 Google Cloud 產品的程式碼範例，請參閱Google Cloud 範例瀏覽器。