Transcribe a local file using an enhanced speech recognition model

Transcribe a local audio file, where you specify an enhanced model.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

Go

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries. For more information, see the Speech-to-Text Go API reference documentation.

To authenticate to Speech-to-Text, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.


func enhancedModel(w io.Writer) error {
	ctx := context.Background()

	client, err := speech.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %w", err)
	}
	defer client.Close()

	data, err := ioutil.ReadFile("../testdata/commercial_mono.wav")
	if err != nil {
		return fmt.Errorf("ReadFile: %w", err)
	}

	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 8000,
			LanguageCode:    "en-US",
			UseEnhanced:     true,
			// A model must be specified to use enhanced model.
			Model: "phone_call",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	})
	if err != nil {
		return fmt.Errorf("Recognize: %w", err)
	}

	for i, result := range resp.Results {
		fmt.Fprintf(w, "%s\n", strings.Repeat("-", 20))
		fmt.Fprintf(w, "Result %d\n", i+1)
		for j, alternative := range result.Alternatives {
			fmt.Fprintf(w, "Alternative %d: %s\n", j+1, alternative.Transcript)
		}
	}
	return nil
}

Java

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries. For more information, see the Speech-to-Text Java API reference documentation.

To authenticate to Speech-to-Text, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

/**
 * Transcribe the given audio file using an enhanced model.
 *
 * @param fileName the path to an audio file.
 */
public static void transcribeFileWithEnhancedModel(String fileName) throws Exception {
  Path path = Paths.get(fileName);
  byte[] content = Files.readAllBytes(path);

  try (SpeechClient speechClient = SpeechClient.create()) {
    // Get the contents of the local audio file
    RecognitionAudio recognitionAudio =
        RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();

    // Configure request to enable enhanced models
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            .setSampleRateHertz(8000)
            .setUseEnhanced(true)
            // A model must be specified to use enhanced model.
            .setModel("phone_call")
            .build();

    // Perform the transcription request
    RecognizeResponse recognizeResponse = speechClient.recognize(config, recognitionAudio);

    // Print out the results
    for (SpeechRecognitionResult result : recognizeResponse.getResultsList()) {
      // There can be several alternative transcripts for a given chunk of speech. Just use the
      // first (most likely) one here.
      SpeechRecognitionAlternative alternative = result.getAlternatives(0);
      System.out.format("Transcript: %s\n\n", alternative.getTranscript());
    }
  }
}

Node.js

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries. For more information, see the Speech-to-Text Node.js API reference documentation.

To authenticate to Speech-to-Text, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

// Imports the Google Cloud client library for Beta API
/**
 * TODO(developer): Update client library import to use new
 * version of API when desired features become available
 */
const speech = require('@google-cloud/speech').v1p1beta1;
const fs = require('fs');

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

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const filename = 'Local path to audio file, e.g. /path/to/audio.raw';
// const encoding = 'Encoding of the audio file, e.g. LINEAR16';
// const sampleRateHertz = 16000;
// const languageCode = 'BCP-47 language code, e.g. en-US';

const config = {
  encoding: encoding,
  languageCode: languageCode,
  useEnhanced: true,
  model: 'phone_call',
};
const audio = {
  content: fs.readFileSync(filename).toString('base64'),
};

const request = {
  config: config,
  audio: audio,
};

// Detects speech in the audio file
const [response] = await client.recognize(request);
response.results.forEach(result => {
  const alternative = result.alternatives[0];
  console.log(alternative.transcript);
});

PHP

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries.

To authenticate to Speech-to-Text, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

use Google\Cloud\Speech\V1\SpeechClient;
use Google\Cloud\Speech\V1\RecognitionAudio;
use Google\Cloud\Speech\V1\RecognitionConfig;
use Google\Cloud\Speech\V1\RecognitionConfig\AudioEncoding;

/**
 * @param string $audioFile path to an audio file
 */
function transcribe_enhanced_model(string $audioFile)
{
    // change these variables if necessary
    $encoding = AudioEncoding::LINEAR16;
    $sampleRateHertz = 8000;
    $languageCode = 'en-US';

    // get contents of a file into a string
    $content = file_get_contents($audioFile);

    // set string as audio content
    $audio = (new RecognitionAudio())
        ->setContent($content);

    // set config
    $config = (new RecognitionConfig())
        ->setEncoding($encoding)
        ->setSampleRateHertz($sampleRateHertz)
        ->setLanguageCode($languageCode)
        ->setUseEnhanced(true)
        ->setModel('phone_call');

    // create the speech client
    $client = new SpeechClient();

    // make the API call
    $response = $client->recognize($config, $audio);
    $results = $response->getResults();

    // print results
    foreach ($results as $result) {
        $alternatives = $result->getAlternatives();
        $mostLikely = $alternatives[0];
        $transcript = $mostLikely->getTranscript();
        $confidence = $mostLikely->getConfidence();
        printf('Transcript: %s' . PHP_EOL, $transcript);
        printf('Confidence: %s' . PHP_EOL, $confidence);
    }

    $client->close();
}

Python

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries. For more information, see the Speech-to-Text Python API reference documentation.

To authenticate to Speech-to-Text, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.


from google.cloud import speech


def transcribe_file_with_enhanced_model(audio_file: str) -> speech.RecognizeResponse:
    """Transcribe the given audio file using an enhanced model.
    Args:
        audio_file (str): Path to the local audio file to be transcribed.
            Example: "resources/commercial_mono.wav"
    Returns:
        speech.RecognizeResponse: The response containing the transcription results.
    """

    client = speech.SpeechClient()

    # audio_file = 'resources/commercial_mono.wav'
    with open(audio_file, "rb") as f:
        audio_content = f.read()

    audio = speech.RecognitionAudio(content=audio_content)
    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=8000,
        language_code="en-US",
        use_enhanced=True,
        # A model must be specified to use enhanced model.
        model="phone_call",
    )

    response = client.recognize(config=config, audio=audio)

    for i, result in enumerate(response.results):
        alternative = result.alternatives[0]
        print("-" * 20)
        print(f"First alternative of result {i}")
        print(f"Transcript: {alternative.transcript}")

    return response

Ruby

To learn how to install and use the client library for Speech-to-Text, see Speech-to-Text client libraries.

To authenticate to Speech-to-Text, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

# audio_file_path = "path/to/audio.wav"

require "google/cloud/speech"

speech = Google::Cloud::Speech.speech

config = {
  encoding:          :LINEAR16,
  sample_rate_hertz: 8000,
  language_code:     "en-US",
  use_enhanced:      true,
  model:             "phone_call"
}

audio_file = File.binread audio_file_path
audio      = { content: audio_file }

operation = speech.long_running_recognize config: config, audio: audio

puts "Operation started"

operation.wait_until_done!

raise operation.results.message if operation.error?

results = operation.response.results

results.each_with_index do |result, i|
  alternative = result.alternatives.first
  puts "-" * 20
  puts "First alternative of result #{i}"
  puts "Transcript: #{alternative.transcript}"
end

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.