Generate text from a video

using Google.GenAI;
using Google.GenAI.Types;
using System;
using System.Collections.Generic;
using System.Threading.Tasks;

public class TextGenWithMuteVideo
{
    public async Task<string> GenerateContent(
        string projectId = "your-project-id",
        string location = "global",
        string model = "gemini-2.5-flash")
    {
        await using var client = new Client(
            project: projectId,
            location: location,
            vertexAI: true,
            httpOptions: new HttpOptions { ApiVersion = "v1" });

        var contents = new List<Content>
        {
            new Content
            {
                Role = "user",
                Parts = new List<Part>
                {
                    new Part
                    {
                        FileData = new FileData
                        {
                            FileUri = "gs://cloud-samples-data/generative-ai/video/ad_copy_from_video.mp4",
                            MimeType = "video/mp4"
                        }
                    },
                    new Part { Text = "What is in this video?"}
                }
            }
        };

        GenerateContentResponse response = await client.Models.GenerateContentAsync(
            model: model,
            contents: contents);

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);
        // Example response:
        // This video shows an aerial view of people surfing in the ocean on a misty
        // or hazy day, with a distant coastline and mountains in the background...
        return responseText;
    }
}

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: genai.RoleUser},
	}

	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
}

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();
    }
  }
}

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-lite',
    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?',
          },
        ],
      },
    ],
    config: {
      mediaResolution: 'MEDIA_RESOLUTION_LOW',
    },
  });

  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;
}

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 ...