Esta página se ha traducido con Cloud Translation API.

Hacer una solicitud de transcripción de audio

Transcribir de forma síncrona un archivo de audio local.

Investigar más

Para obtener documentación detallada que incluya este código de muestra, consulta lo siguiente:

Código de ejemplo

Go

Para saber cómo instalar y usar la biblioteca de cliente de Cloud STT, consulta Bibliotecas de cliente de Cloud STT. Para obtener más información, consulta la documentación de referencia de la API Cloud STT Go.

Para autenticarte en Cloud STT, configura las credenciales predeterminadas de la aplicación. Para obtener más información, consulta el artículo Configurar la autenticación en un entorno de desarrollo local.


// Sample speech-quickstart uses the Google Cloud Speech API to transcribe
// audio.
package main

import (
	"context"
	"fmt"
	"log"

	speech "cloud.google.com/go/speech/apiv1"
	"cloud.google.com/go/speech/apiv1/speechpb"
)

func main() {
	ctx := context.Background()

	// Creates a client.
	client, err := speech.NewClient(ctx)
	if err != nil {
		log.Fatalf("Failed to create client: %v", err)
	}
	defer client.Close()

	// The path to the remote audio file to transcribe.
	fileURI := "gs://cloud-samples-data/speech/brooklyn_bridge.raw"

	// Detects speech in the audio file.
	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Uri{Uri: fileURI},
		},
	})
	if err != nil {
		log.Fatalf("failed to recognize: %v", err)
	}

	// Prints the results.
	for _, result := range resp.Results {
		for _, alt := range result.Alternatives {
			fmt.Printf("\"%v\" (confidence=%3f)\n", alt.Transcript, alt.Confidence)
		}
	}
}

Java

// Imports the Google Cloud client library
import com.google.cloud.speech.v1.RecognitionAudio;
import com.google.cloud.speech.v1.RecognitionConfig;
import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding;
import com.google.cloud.speech.v1.RecognizeResponse;
import com.google.cloud.speech.v1.SpeechClient;
import com.google.cloud.speech.v1.SpeechRecognitionAlternative;
import com.google.cloud.speech.v1.SpeechRecognitionResult;
import java.util.List;

public class QuickstartSample {

  /** Demonstrates using the Speech API to transcribe an audio file. */
  public static void main(String... args) throws Exception {
    // Instantiates a client
    try (SpeechClient speechClient = SpeechClient.create()) {

      // The path to the audio file to transcribe
      String gcsUri = "gs://cloud-samples-data/speech/brooklyn_bridge.raw";

      // Builds the sync recognize request
      RecognitionConfig config =
          RecognitionConfig.newBuilder()
              .setEncoding(AudioEncoding.LINEAR16)
              .setSampleRateHertz(16000)
              .setLanguageCode("en-US")
              .build();
      RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

      // Performs speech recognition on the audio file
      RecognizeResponse response = speechClient.recognize(config, audio);
      List<SpeechRecognitionResult> results = response.getResultsList();

      for (SpeechRecognitionResult result : results) {
        // There can be several alternative transcripts for a given chunk of speech. Just use the
        // first (most likely) one here.
        SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
        System.out.printf("Transcription: %s%n", alternative.getTranscript());
      }
    }
  }
}

Node.js

// Imports the Google Cloud client library
const speech = require('@google-cloud/speech');

// Creates a client
const client = new speech.SpeechClient();

async function quickstart() {
  // The path to the remote LINEAR16 file
  const gcsUri = 'gs://cloud-samples-data/speech/brooklyn_bridge.raw';

  // The audio file's encoding, sample rate in hertz, and BCP-47 language code
  const audio = {
    uri: gcsUri,
  };
  const config = {
    encoding: 'LINEAR16',
    sampleRateHertz: 16000,
    languageCode: 'en-US',
  };
  const request = {
    audio: audio,
    config: config,
  };

  // Detects speech in the audio file
  const [response] = await client.recognize(request);
  const transcription = response.results
    .map(result => result.alternatives[0].transcript)
    .join('\n');
  console.log(`Transcription: ${transcription}`);
}
quickstart();

PHP

Para saber cómo instalar y usar la biblioteca de cliente de Cloud STT, consulta Bibliotecas de cliente de Cloud STT.

# Includes the autoloader for libraries installed with composer
require __DIR__ . '/vendor/autoload.php';

# Imports the Google Cloud client library

use Google\Cloud\Speech\V2\Client\SpeechClient;
use Google\Cloud\Speech\V2\CreateRecognizerRequest;
use Google\Cloud\Speech\V2\ExplicitDecodingConfig;
use Google\Cloud\Speech\V2\ExplicitDecodingConfig\AudioEncoding;
use Google\Cloud\Speech\V2\RecognitionConfig;
use Google\Cloud\Speech\V2\Recognizer;
use Google\Cloud\Speech\V2\RecognizeRequest;

# The name of the audio file to transcribe
$gcsURI = 'gs://cloud-samples-data/speech/brooklyn_bridge.raw';

# Your Google Cloud Project ID and location
$projectId = 'YOUR_PROJECT_ID';
$location = 'global';

# Instantiates a client
$speech = new SpeechClient();

// Create a Recognizer
$createRecognizerRequest = new CreateRecognizerRequest([
    'parent' => SpeechClient::locationName($projectId, $location),
    'recognizer_id' => $recognizerId = 'quickstart-recognizer-' . uniqid(),
    'recognizer' => new Recognizer([
        'language_codes' => ['en-US'],
        'model' => 'latest_short'
    ])
]);

$operation = $speech->createRecognizer($createRecognizerRequest);

// Wait for the operation to complete
$operation->pollUntilComplete();
if ($operation->operationSucceeded()) {
    $result = $operation->getResult();
    printf('Created Recognizer: %s' . PHP_EOL, $result->getName());
} else {
    print_r($operation->getError());
}

$config = (new RecognitionConfig())
    // Can also use {@see Google\Cloud\Speech\V2\AutoDetectDecodingConfig}
    // ->setAutoDecodingConfig(new AutoDetectDecodingConfig());

    ->setExplicitDecodingConfig(new ExplicitDecodingConfig([
        'encoding' => AudioEncoding::LINEAR16,
        'sample_rate_hertz' => 16000,
        'audio_channel_count' => 1,
    ]));

$recognizerName = SpeechClient::recognizerName($projectId, $location, $recognizerId);
$request = (new RecognizeRequest())
    ->setRecognizer($recognizerName)
    ->setConfig($config)
    ->setUri($gcsURI);

# Detects speech in the audio file
$response = $speech->recognize($request);

# Print most likely transcription
foreach ($response->getResults() as $result) {
    $alternatives = $result->getAlternatives();
    $mostLikely = $alternatives[0];
    $transcript = $mostLikely->getTranscript();
    printf('Transcript: %s' . PHP_EOL, $transcript);
}

$speech->close();

Python


# Imports the Google Cloud client library


from google.cloud import speech



def run_quickstart() -> speech.RecognizeResponse:
    # Instantiates a client
    client = speech.SpeechClient()

    # The name of the audio file to transcribe
    gcs_uri = "gs://cloud-samples-data/speech/brooklyn_bridge.raw"

    audio = speech.RecognitionAudio(uri=gcs_uri)

    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=16000,
        language_code="en-US",
    )

    # Detects speech in the audio file
    response = client.recognize(config=config, audio=audio)

    for result in response.results:
        print(f"Transcript: {result.alternatives[0].transcript}")

Siguientes pasos

Para buscar y filtrar ejemplos de código de otros Google Cloud productos, consulta el Google Cloud navegador de ejemplos.

Hacer una solicitud de transcripción de audio Organízate con las colecciones Guarda y clasifica el contenido según tus preferencias.