Generate text from a video

This sample demonstrates how to use the Gemini API to generate text from a video

Explore further

For detailed documentation that includes this code sample, see the following:

• Video understanding

Code sample

Go

Before trying this sample, follow the Go setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Go API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithMuteVideo shows how to generate text using a video with no sound as the input.
func generateWithMuteVideo(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: "What is in the video?"},
			{FileData: &genai.FileData{
				FileURI:  "gs://cloud-samples-data/generative-ai/video/ad_copy_from_video.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:
	// The video shows several surfers riding waves in an ocean setting. The waves are ...

	return nil
}

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Java API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.genai.Client;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Part;

public class TextGenerationWithMuteVideo {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text with mute video input
  public static String generateContent(String modelId) {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests.
    try (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromUri(
                      "gs://cloud-samples-data/generative-ai/video/ad_copy_from_video.mp4",
                      "video/mp4"),
                  Part.fromText("What is in this video?")),
              null);

      System.out.print(response.text());
      // Example response:
      // This video features **surfers in the ocean**.
      //
      // The main focus is on **one individual who catches and rides a wave**, executing various
      // turns and maneuvers as the wave breaks and dissipates into whitewater...
      return response.text();
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Node.js API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

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 generateText(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [
      {
        role: 'user',
        parts: [
          {
            fileData: {
              mimeType: 'video/mp4',
              fileUri:
                'gs://cloud-samples-data/generative-ai/video/ad_copy_from_video.mp4',
            },
          },
          {
            text: 'What is in the video?',
          },
        ],
      },
    ],
  });

  console.log(response.text);

  // Example response:
  // The video shows several people surfing in an ocean with a coastline in the background. The camera ...

  return response.text;
}

Python

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

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

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/video/ad_copy_from_video.mp4",
            mime_type="video/mp4",
        ),
        "What is in the video?",
    ],
)
print(response.text)
# Example response:
# The video shows several people surfing in an ocean with a coastline in the background. The camera ...

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.