Transcribing long audio files

This page demonstrates how to transcribe long audio files (longer than 1 minute) to text using asynchronous speech recognition.

Asynchronous speech recognition starts a long running audio processing operation. Use asynchronous speech recognition to recognize audio that is longer than a minute. For shorter audio, Synchronous Speech Recognition is faster and simpler.

You can retrieve the results of the operation via the google.longrunning.Operations interface. Results remain available for retrieval for 5 days (120 hours). Audio content can be sent directly to Speech-to-Text or it can process audio content that already resides in Google Cloud Storage. See also the audio limits for asynchronous speech recognition requests.

The Cloud Speech-to-Text v1 is officially released and is generally available from the endpoint. The Client Libraries are released as Alpha and will likely be changed in backward-incompatible ways. The client libraries are currently not recommended for production use.

These samples require that you have set up gcloud and have created and activated a service account. For information about setting up gcloud, and also creating and activating a service account, see Quickstart.

The samples also use a Cloud Storage bucket to store the raw audio input for the long-running transcription process.


Refer to the speech:longrunningrecognize API endpoint for complete details.

To perform synchronous speech recognition, make a POST request and provide the appropriate request body. The following shows an example of a POST request using curl. The example uses the access token for a service account set up for the project using the Google Cloud Cloud SDK. For instructions on installing the Cloud SDK, setting up a project with a service account, and obtaining an access token, see the quickstart.

curl -X POST \
     -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \
     --data "{
  'config': {
    'language_code': 'en-US'
}" ""

See the RecognitionConfig and RecognitionAudio reference documentation for more information on configuring the request body.

If the request is successful, the server returns a 200 OK HTTP status code and the response in JSON format:

  "name": "7612202767953098924"

where name is the name of the long running operation created for the request.

Wait for processing to complete. Processing time differs depending on your source audio. In most cases, you will get results in half the length of the source audio. You can get the status of your long-running operation by making a GET request to the endpoint. Replace your-operation-name with the name returned from your longrunningrecognize request. You can get the estimated progress of the request from the progressPercent field.

curl -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \

If the request is successful, the server returns a 200 OK HTTP status code and the response in JSON format:

  "name": "7612202767953098924",
  "metadata": {
    "@type": "",
    "progressPercent": 100,
    "startTime": "2017-07-20T16:36:55.033650Z",
    "lastUpdateTime": "2017-07-20T16:37:17.158630Z"
  "done": true,
  "response": {
    "@type": "",
    "results": [
        "alternatives": [
            "transcript": "okay so what am I doing here...(etc)...",
            "confidence": 0.96096134,
        "alternatives": [

If the operation has not completed, you can poll the endpoint by repeatedly making the GET request until the done property of the response is true.

gcloud command

Refer to the recognize-long-running command for complete details.

To perform asynchronous speech recognition, use the gcloud command line tool, providing the path of a local file or a Google Cloud Storage URL.

gcloud ml speech recognize-long-running \
    'gs://cloud-samples-tests/speech/brooklyn.flac' \
     --language-code='en-US' --async

If the request is successful, the server returns the ID of the long-running operation in JSON format.

  "name": OPERATION_ID

You can then get information about the operation by running the following command.

gcloud ml speech operations describe OPERATION_ID

You can also poll the operation until it completes by running the following command.

gcloud ml speech operations wait OPERATION_ID

Once the operation completes, the operation returns the audio in JSON-format.

  "@type": "",
  "results": [
      "alternatives": [
          "confidence": 0.9840146,
          "transcript": "how old is the Brooklyn Bridge"


static object AsyncRecognizeGcs(string storageUri)
    var speech = SpeechClient.Create();
    var longOperation = speech.LongRunningRecognize(new RecognitionConfig()
        Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
        SampleRateHertz = 16000,
        LanguageCode = "en",
    }, RecognitionAudio.FromStorageUri(storageUri));
    longOperation = longOperation.PollUntilCompleted();
    var response = longOperation.Result;
    foreach (var result in response.Results)
        foreach (var alternative in result.Alternatives)
            Console.WriteLine($"Transcript: { alternative.Transcript}");
    return 0;


func sendGCS(w io.Writer, client *speech.Client, gcsURI string) error {
	ctx := context.Background()

	// Send the contents of the audio file with the encoding and
	// and sample rate information to be transcripted.
	req := &speechpb.LongRunningRecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:        speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz: 16000,
			LanguageCode:    "en-US",
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Uri{Uri: gcsURI},

	op, err := client.LongRunningRecognize(ctx, req)
	if err != nil {
		return err
	resp, err := op.Wait(ctx)
	if err != nil {
		return err

	// Print the results.
	for _, result := range resp.Results {
		for _, alt := range result.Alternatives {
			fmt.Fprintf(w, "\"%v\" (confidence=%3f)\n", alt.Transcript, alt.Confidence)
	return nil


 * Performs non-blocking speech recognition on remote FLAC file and prints the transcription.
 * @param gcsUri the path to the remote LINEAR16 audio file to transcribe.
public static void asyncRecognizeGcs(String gcsUri) throws Exception {
  // Instantiates a client with GOOGLE_APPLICATION_CREDENTIALS
  try (SpeechClient speech = SpeechClient.create()) {

    // Configure remote file request for FLAC
    RecognitionConfig config =
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use non-blocking call for getting file transcription
    OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
        speech.longRunningRecognizeAsync(config, audio);
    while (!response.isDone()) {
      System.out.println("Waiting for response...");

    List<SpeechRecognitionResult> results = response.get().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());


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

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

 * TODO(developer): Uncomment the following lines before running the sample.
// const gcsUri = 'gs://my-bucket/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,
  sampleRateHertz: sampleRateHertz,
  languageCode: languageCode,

const audio = {
  uri: gcsUri,

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

// Detects speech in the audio file. This creates a recognition job that you
// can wait for now, or get its result later.
const [operation] = await client.longRunningRecognize(request);
// Get a Promise representation of the final result of the job
const [response] = await operation.promise();
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
console.log(`Transcription: ${transcription}`);


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 */
// $uri = 'The Cloud Storage object to transcribe (gs://your-bucket-name/your-object-name)';

// change these variables if necessary
$encoding = AudioEncoding::LINEAR16;
$sampleRateHertz = 32000;
$languageCode = 'en-US';

// set string as audio content
$audio = (new RecognitionAudio())

// set config
$config = (new RecognitionConfig())

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

// create the asyncronous recognize operation
$operation = $client->longRunningRecognize($config, $audio);

if ($operation->operationSucceeded()) {
    $response = $operation->getResult();

    // each result is for a consecutive portion of the audio. iterate
    // through them to get the transcripts for the entire audio file.
    foreach ($response->getResults() 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);
} else {



from import speech_v1
from import enums

def sample_long_running_recognize(storage_uri):
    Transcribe long audio file from Cloud Storage using asynchronous speech

      storage_uri URI for audio file in Cloud Storage, e.g. gs://[BUCKET]/[FILE]

    client = speech_v1.SpeechClient()

    # storage_uri = 'gs://cloud-samples-data/speech/brooklyn_bridge.raw'

    # Sample rate in Hertz of the audio data sent
    sample_rate_hertz = 16000

    # The language of the supplied audio
    language_code = "en-US"

    # Encoding of audio data sent. This sample sets this explicitly.
    # This field is optional for FLAC and WAV audio formats.
    encoding = enums.RecognitionConfig.AudioEncoding.LINEAR16
    config = {
        "sample_rate_hertz": sample_rate_hertz,
        "language_code": language_code,
        "encoding": encoding,
    audio = {"uri": storage_uri}

    operation = client.long_running_recognize(config, audio)

    print(u"Waiting for operation to complete...")
    response = operation.result()

    for result in response.results:
        # First alternative is the most probable result
        alternative = result.alternatives[0]
        print(u"Transcript: {}".format(alternative.transcript))


# storage_path = "Path to file in Cloud Storage, eg. gs://bucket/audio.raw"

require "google/cloud/speech"

speech =

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

operation = speech.long_running_recognize config, audio

puts "Operation started"


raise operation.results.message if operation.error?

results = operation.response.results

alternatives = results.first.alternatives
alternatives.each do |alternative|
  puts "Transcription: #{alternative.transcript}"