Gerar texto de um vídeo

using Google.Api.Gax.Grpc;
using Google.Cloud.AIPlatform.V1;
using System.Text;
using System.Threading.Tasks;

public class MultimodalVideoInput
{
    public async Task<string> GenerateContent(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-2.0-flash-001"
    )
    {
        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = "What's in the video?" },
                        new Part { FileData = new() { MimeType = "video/mp4", FileUri = "gs://cloud-samples-data/video/animals.mp4" }}
                    }
                }
            }
        };

        using PredictionServiceClient.StreamGenerateContentStream response = predictionServiceClient.StreamGenerateContent(generateContentRequest);

        StringBuilder fullText = new();

        AsyncResponseStream<GenerateContentResponse> responseStream = response.GetResponseStream();
        await foreach (GenerateContentResponse responseItem in responseStream)
        {
            fullText.Append(responseItem.Candidates[0].Content.Parts[0].Text);
        }
        return fullText.ToString();
    }
}

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function sendMultiModalPromptWithVideo(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-2.0-flash-001'
) {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: projectId, location: location});

  const generativeVisionModel = vertexAI.getGenerativeModel({
    model: model,
  });

  // Pass multimodal prompt
  const request = {
    contents: [
      {
        role: 'user',
        parts: [
          {
            fileData: {
              fileUri: 'gs://cloud-samples-data/video/animals.mp4',
              mimeType: 'video/mp4',
            },
          },
          {
            text: 'What is in the video?',
          },
        ],
      },
    ],
  };

  // Create the response
  const response = await generativeVisionModel.generateContent(request);
  // Wait for the response to complete
  const aggregatedResponse = await response.response;
  // Select the text from the response
  const fullTextResponse =
    aggregatedResponse.candidates[0].content.parts[0].text;

  console.log(fullTextResponse);
}