Transcribe a local file using a transcription model

Transcribe a local audio file using a trained transcription model.

Documentation pages that include this code sample

To view the code sample used in context, see the following documentation:

Code sample

Go


func modelSelection(w io.Writer, path string) error {
	ctx := context.Background()

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

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

	req := &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
			Model:           "video",
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	}

	resp, err := client.Recognize(ctx, req)
	if err != nil {
		return fmt.Errorf("Recognize: %v", 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

/**
 * Performs transcription of the given audio file synchronously with the selected model.
 *
 * @param fileName the path to a audio file to transcribe
 */
public static void transcribeModelSelection(String fileName) throws Exception {
  Path path = Paths.get(fileName);
  byte[] content = Files.readAllBytes(path);

  try (SpeechClient speech = SpeechClient.create()) {
    // Configure request with video media type
    RecognitionConfig recConfig =
        RecognitionConfig.newBuilder()
            // encoding may either be omitted or must match the value in the file header
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            // sample rate hertz may be either be omitted or must match the value in the file
            // header
            .setSampleRateHertz(16000)
            .setModel("video")
            .build();

    RecognitionAudio recognitionAudio =
        RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();

    RecognizeResponse recognizeResponse = speech.recognize(recConfig, recognitionAudio);
    // Just print the first result here.
    SpeechRecognitionResult result = recognizeResponse.getResultsList().get(0);
    // 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("Transcript : %s\n", alternative.getTranscript());
  }
}

Node.js

// 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 model = 'Model to use, e.g. phone_call, video, default';
// 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,
  sampleRateHertz: sampleRateHertz,
  languageCode: languageCode,
  model: model,
};
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);
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
console.log('Transcription: ', transcription);

PHP

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;

/** Uncomment and populate these variables in your code */
// $audioFile = 'path to an audio file';
// $model = 'video';

// change these variables if necessary
$encoding = AudioEncoding::LINEAR16;
$sampleRateHertz = 32000;
$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)
    ->setModel($model);

// 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

def transcribe_model_selection(speech_file, model):
    """Transcribe the given audio file synchronously with
    the selected model."""
    from google.cloud import speech

    client = speech.SpeechClient()

    with open(speech_file, "rb") as audio_file:
        content = audio_file.read()

    audio = speech.RecognitionAudio(content=content)

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

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

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

Ruby

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

require "google/cloud/speech"

speech = Google::Cloud::Speech.speech

config = {
  encoding:          :LINEAR16,
  sample_rate_hertz: 16_000,
  language_code:     "en-US",
  model:             model
}

file  = File.binread file_path
audio = { content: 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