音訊理解 (僅限語音)

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

client = genai.Client(http_options=HttpOptions(api_version="v1"))
prompt = """
Provide a concise summary of the main points in the audio file.
"""
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents=[
        prompt,
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
            mime_type="audio/mpeg",
        ),
    ],
)
print(response.text)
# Example response:
# Here's a summary of the main points from the audio file:

# The Made by Google podcast discusses the Pixel feature drops with product managers Aisha Sheriff and De Carlos Love.  The key idea is that devices should improve over time, with a connected experience across phones, watches, earbuds, and tablets.

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithAudio shows how to generate text using an audio input.
func generateWithAudio(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: `Provide the summary of the audio file.
Summarize the main points of the audio concisely.
Create a chapter breakdown with timestamps for key sections or topics discussed.`},
			{FileData: &genai.FileData{
				FileURI:  "gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
				MIMEType: "audio/mpeg",
			}},
		},
			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:
	// Here is a summary and chapter breakdown of the audio file:
	//
	// **Summary:**
	//
	// The audio file is a "Made by Google" podcast episode discussing the Pixel Feature Drops, ...
	//
	// **Chapter Breakdown:**
	//
	// *   **0:00 - 0:54:** Introduction to the podcast and guests, Aisha Sharif and DeCarlos Love.
	// ...

	return nil
}

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 prompt =
    'Provide a concise summary of the main points in the audio file.';

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [
      {
        fileData: {
          fileUri: 'gs://cloud-samples-data/generative-ai/audio/pixel.mp3',
          mimeType: 'audio/mpeg',
        },
      },
      {text: prompt},
    ],
  });

  console.log(response.text);

  // Example response:
  //  Here's a summary of the main points from the audio file:
  //  The Made by Google podcast discusses the Pixel feature drops with product managers Aisha Sheriff and De Carlos Love.  The key idea is that devices should improve over time, with a connected experience across phones, watches, earbuds, and tablets.

  return response.text;
}

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 TextGenerationWithGcsAudio {

  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 audio input
  public static String generateContent(String modelId) {
    // Client Initialization. Once created, it 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/audio/pixel.mp3", "audio/mpeg"),
                  Part.fromText("Provide a concise summary of the main points in the audio file.")),
              null);

      System.out.print(response.text());
      // Example response:
      // The audio features Google product managers Aisha Sharif and D. Carlos Love discussing Pixel
      // Feature Drops, emphasizing their role in continually enhancing devices across the entire
      // Pixel ecosystem...
      return response.text();
    }
  }
}

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

client = genai.Client(http_options=HttpOptions(api_version="v1"))
prompt = """
Transcribe the interview, in the format of timecode, speaker, caption.
Use speaker A, speaker B, etc. to identify speakers.
"""
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents=[
        prompt,
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
            mime_type="audio/mpeg",
        ),
    ],
    # Required to enable timestamp understanding for audio-only files
    config=GenerateContentConfig(audio_timestamp=True),
)
print(response.text)
# Example response:
# [00:00:00] **Speaker A:** your devices are getting better over time. And so ...
# [00:00:14] **Speaker B:** Welcome to the Made by Google podcast where we meet ...
# [00:00:20] **Speaker B:** Here's your host, Rasheed Finch.
# [00:00:23] **Speaker C:** Today we're talking to Aisha Sharif and DeCarlos Love. ...
# ...

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateAudioTranscript shows how to generate an audio transcript.
func generateAudioTranscript(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: `Transcribe the interview, in the format of timecode, speaker, caption.
Use speaker A, speaker B, etc. to identify speakers.`},
			{FileData: &genai.FileData{
				FileURI:  "gs://cloud-samples-data/generative-ai/audio/pixel.mp3",
				MIMEType: "audio/mpeg",
			}},
		},
			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:
	// 00:00:00, A: your devices are getting better over time.
	// 00:01:13, A: And so we think about it across the entire portfolio from phones to watch, ...
	// ...

	return nil
}

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 prompt = `Transcribe the interview, in the format of timecode, speaker, caption.
    Use speaker A, speaker B, etc. to identify speakers.`;

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [
      {text: prompt},
      {
        fileData: {
          fileUri: 'gs://cloud-samples-data/generative-ai/audio/pixel.mp3',
          mimeType: 'audio/mpeg',
        },
      },
    ],
    // Required to enable timestamp understanding for audio-only files
    config: {
      audioTimestamp: true,
    },
  });

  console.log(response.text);

  // Example response:
  // [00:00:00] **Speaker A:** your devices are getting better over time. And so ...
  // [00:00:14] **Speaker B:** Welcome to the Made by Google podcast where we meet ...
  // [00:00:20] **Speaker B:** Here's your host, Rasheed Finch.
  // [00:00:23] **Speaker C:** Today we're talking to Aisha Sharif and DeCarlos Love. ...
  // ...

  return response.text;
}

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

public class TextGenerationTranscriptWithGcsAudio {

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

  // Generates transcript with audio input
  public static String generateContent(String modelId) {
    // Client Initialization. Once created, it can be reused for multiple requests.
    try (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      String prompt =
          "Transcribe the interview, in the format of timecode, speaker, caption.\n"
              + "Use speaker A, speaker B, etc. to identify speakers.";

      // Enable audioTimestamp to generate timestamps for audio-only files.
      GenerateContentConfig contentConfig =
          GenerateContentConfig.builder().audioTimestamp(true).build();

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromUri(
                      "gs://cloud-samples-data/generative-ai/audio/pixel.mp3", "audio/mpeg"),
                  Part.fromText(prompt)),
              contentConfig);

      System.out.print(response.text());
      // Example response:
      // 00:00 - Speaker A: your devices are getting better over time. And so we think about it...
      // 00:14 - Speaker B: Welcome to the Made by Google Podcast, where we meet the people who...
      // 00:41 - Speaker A: So many features. I am a singer, so I actually think recorder...
      return response.text();
    }
  }
}