音频理解（仅限语音）

import vertexai
from vertexai.generative_models import GenerativeModel, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

prompt = """
Please provide a summary for the audio.
Provide chapter titles, be concise and short, no need to provide chapter summaries.
Do not make up any information that is not part of the audio and do not be verbose.
"""

audio_file_uri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3"
audio_file = Part.from_uri(audio_file_uri, mime_type="audio/mpeg")

contents = [audio_file, prompt]

response = model.generate_content(contents)
print(response.text)
# Example response:
# **Made By Google Podcast Summary**
# **Chapter Titles:**
# * Introduction
# * Transformative Pixel Features
# ...

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;

public class AudioInputSummarization {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    summarizeAudio(projectId, location, modelName);
  }

  // Analyzes the given audio input.
  public static String summarizeAudio(String projectId, String location, String modelName)
      throws IOException {
    // 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 (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String audioUri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              "Please provide a summary for the audio.\n"
                  + "Provide chapter titles with timestamps, be concise and short, "
                  + "no need to provide chapter summaries.\n"
                  + "Do not make up any information that is not part of the audio "
                  + "and do not be verbose.",
              PartMaker.fromMimeTypeAndData("audio/mp3", audioUri)
          ));

      String output = ResponseHandler.getText(response);
      System.out.println(output);

      return output;
    }
  }
}

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

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function summarize_audio(projectId = 'PROJECT_ID') {
  const vertexAI = new VertexAI({project: projectId, location: 'us-central1'});

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-flash-001',
  });

  const filePart = {
    file_data: {
      file_uri: 'gs://cloud-samples-data/generative-ai/audio/pixel.mp3',
      mime_type: 'audio/mpeg',
    },
  };
  const textPart = {
    text: `
    Please provide a summary for the audio.
    Provide chapter titles with timestamps, be concise and short, no need to provide chapter summaries.
    Do not make up any information that is not part of the audio and do not be verbose.`,
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  const resp = await generativeModel.generateContent(request);
  const contentResponse = await resp.response;
  console.log(JSON.stringify(contentResponse));
}

import (
	"context"
	"errors"
	"fmt"
	"io"
	"mime"
	"path/filepath"

	"cloud.google.com/go/vertexai/genai"
)

// summarizeAudio shows how to send an audio asset and a text question to a model, writing the response to the
// provided io.Writer.
func summarizeAudio(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"
	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)
	model.SetTemperature(0.4)

	// Given an audio file URL, prepare audio file as genai.Part
	part := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext("pixel.mp3")),
		FileURI:  "gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
	}

	res, err := model.GenerateContent(ctx, part, genai.Text(`
		Please provide a summary for the audio.
		Provide chapter titles with timestamps, be concise and short, no need to provide chapter summaries.
		Do not make up any information that is not part of the audio and do not be verbose.
	`,
	))
	if err != nil {
		return fmt.Errorf("unable to generate contents: %w", err)
	}

	if len(res.Candidates) == 0 ||
		len(res.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	fmt.Fprintf(w, "generated summary:\n%s\n", res.Candidates[0].Content.Parts[0])
	return nil
}

using Google.Cloud.AIPlatform.V1;
using System;
using System.Threading.Tasks;

public class AudioInputSummarization
{
    public async Task<string> SummarizeAudio(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001")
    {
        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        string prompt = @"Please provide a summary for the audio.
Provide chapter titles with timestamps, be concise and short, no need to provide chapter summaries.
Do not make up any information that is not part of the audio and do not be verbose.";

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = prompt },
                        new Part { FileData = new() { MimeType = "audio/mp3", FileUri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3" } }
                    }
                }
            }
        };

        GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);

        return responseText;
    }
}

import vertexai
from vertexai.generative_models import GenerativeModel, GenerationConfig, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

prompt = """
Can you transcribe this interview, in the format of timecode, speaker, caption.
Use speaker A, speaker B, etc. to identify speakers.
"""

audio_file_uri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3"
audio_file = Part.from_uri(audio_file_uri, mime_type="audio/mpeg")

contents = [audio_file, prompt]

response = model.generate_content(contents, generation_config=GenerationConfig(audio_timestamp=True))

print(response.text)
# Example response:
# [00:00:00] Speaker A: Your devices are getting better over time...
# [00:00:16] Speaker B: Welcome to the Made by Google podcast, ...
# [00:01:00] Speaker A: So many features. I am a singer. ...
# [00:01:33] Speaker B: Amazing. DeCarlos, same question to you, ...

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;

public class AudioInputTranscription {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    transcribeAudio(projectId, location, modelName);
  }

  // Analyzes the given audio input.
  public static String transcribeAudio(String projectId, String location, String modelName)
      throws IOException {
    // 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 (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String audioUri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              "Can you transcribe this interview, in the format of timecode, speaker, caption.\n"
                  + "Use speaker A, speaker B, etc. to identify speakers.",
              PartMaker.fromMimeTypeAndData("audio/mp3", audioUri)
          ));

      String output = ResponseHandler.getText(response);
      System.out.println(output);

      return output;
    }
  }
}

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

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function transcript_audio(projectId = 'PROJECT_ID') {
  const vertexAI = new VertexAI({project: projectId, location: 'us-central1'});

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-flash-001',
  });

  const filePart = {
    file_data: {
      file_uri: 'gs://cloud-samples-data/generative-ai/audio/pixel.mp3',
      mime_type: 'audio/mpeg',
    },
  };
  const textPart = {
    text: `
    Can you transcribe this interview, in the format of timecode, speaker, caption?
    Use speaker A, speaker B, etc. to identify speakers.`,
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  const resp = await generativeModel.generateContent(request);
  const contentResponse = await resp.response;
  console.log(JSON.stringify(contentResponse));
}

import (
	"context"
	"errors"
	"fmt"
	"io"
	"mime"
	"path/filepath"

	"cloud.google.com/go/vertexai/genai"
)

// transcribeAudio generates a response into w
func transcribeAudio(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"

	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	// Optional: set an explicit temperature
	model.SetTemperature(0.4)

	// Given an audio file URL, prepare audio file as genai.Part
	img := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext("pixel.mp3")),
		FileURI:  "gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
	}

	res, err := model.GenerateContent(ctx, img, genai.Text(`
			Can you transcribe this interview, in the format of timecode, speaker, caption.
			Use speaker A, speaker B, etc. to identify speakers.
	`))
	if err != nil {
		return fmt.Errorf("unable to generate contents: %w", err)
	}

	if len(res.Candidates) == 0 ||
		len(res.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	fmt.Fprintf(w, "generated transcript:\n%s\n", res.Candidates[0].Content.Parts[0])
	return nil
}

using Google.Cloud.AIPlatform.V1;
using System;
using System.Threading.Tasks;

public class AudioInputTranscription
{
    public async Task<string> TranscribeAudio(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001")
    {

        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        string prompt = @"Can you transcribe this interview, in the format of timecode, speaker, caption.
Use speaker A, speaker B, etc. to identify speakers.";

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = prompt },
                        new Part { FileData = new() { MimeType = "audio/mp3", FileUri = "gs://cloud-samples-data/generative-ai/audio/pixel.mp3" } }
                    }
                }
            }
        };

        GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);

        return responseText;
    }
}