Transcription of a file in Cloud Storage with diarization (beta)

Recognize multiple speakers in an audio file stored in Cloud Storage.

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.


import (
	"context"
	"fmt"
	"io"
	"strings"

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

// transcribe_diarization_gcs_beta Transcribes a remote audio file using speaker diarization.
func transcribe_diarization_gcs_beta(w io.Writer) error {
	// Google Cloud Storage URI pointing to the audio content.

	ctx := context.Background()

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

	diarizationConfig := &speechpb.SpeakerDiarizationConfig{
		EnableSpeakerDiarization: true,
		MinSpeakerCount:          2,
		MaxSpeakerCount:          2,
	}

	recognitionConfig := &speechpb.RecognitionConfig{
		Encoding:          speechpb.RecognitionConfig_LINEAR16,
		SampleRateHertz:   8000,
		LanguageCode:      "en-US",
		DiarizationConfig: diarizationConfig,
	}

	// Set the remote path for the audio file
	audio := &speechpb.RecognitionAudio{
		AudioSource: &speechpb.RecognitionAudio_Uri{Uri: "gs://cloud-samples-tests/speech/commercial_mono.wav"},
	}

	longRunningRecognizeRequest := &speechpb.LongRunningRecognizeRequest{
		Config: recognitionConfig,
		Audio:  audio,
	}

	operation, err := client.LongRunningRecognize(ctx, longRunningRecognizeRequest)
	if err != nil {
		return fmt.Errorf("error running recognize %w", err)
	}

	response, err := operation.Wait(ctx)
	if err != nil {
		return err
	}

	// Speaker Tags are only included in the last result object, which has only one
	// alternative.
	alternative := response.Results[len(response.Results)-1].Alternatives[0]

	wordInfo := alternative.GetWords()[0]
	currentSpeakerTag := wordInfo.GetSpeakerTag()

	var speakerWords strings.Builder

	speakerWords.WriteString(fmt.Sprintf("Speaker %d: %s", wordInfo.GetSpeakerTag(), wordInfo.GetWord()))

	// For each word, get all the words associated with one speaker, once the speaker changes,
	// add a new line with the new speaker and their spoken words.
	for i := 1; i < len(alternative.Words); i++ {
		wordInfo := alternative.Words[i]
		if currentSpeakerTag == wordInfo.GetSpeakerTag() {
			speakerWords.WriteString(" ")
			speakerWords.WriteString(wordInfo.GetWord())
		} else {
			speakerWords.WriteString(fmt.Sprintf("\nSpeaker %d: %s",
				wordInfo.GetSpeakerTag(), wordInfo.GetWord()))
			currentSpeakerTag = wordInfo.GetSpeakerTag()
		}
	}
	fmt.Fprintf(w, speakerWords.String())
	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 a remote audio file using speaker diarization.
 *
 * @param gcsUri the path to an audio file.
 */
public static void transcribeDiarizationGcs(String gcsUri) throws Exception {
  try (SpeechClient speechClient = SpeechClient.create()) {
    SpeakerDiarizationConfig speakerDiarizationConfig =
        SpeakerDiarizationConfig.newBuilder()
            .setEnableSpeakerDiarization(true)
            .setMinSpeakerCount(2)
            .setMaxSpeakerCount(2)
            .build();

    // Configure request to enable Speaker diarization
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            .setSampleRateHertz(8000)
            .setDiarizationConfig(speakerDiarizationConfig)
            .build();

    // Set the remote path for the audio file
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use non-blocking call for getting file transcription
    OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
        speechClient.longRunningRecognizeAsync(config, audio);

    while (!response.isDone()) {
      System.out.println("Waiting for response...");
      Thread.sleep(10000);
    }

    // Speaker Tags are only included in the last result object, which has only one alternative.
    LongRunningRecognizeResponse longRunningRecognizeResponse = response.get();
    SpeechRecognitionAlternative alternative =
        longRunningRecognizeResponse
            .getResults(longRunningRecognizeResponse.getResultsCount() - 1)
            .getAlternatives(0);

    // The alternative is made up of WordInfo objects that contain the speaker_tag.
    WordInfo wordInfo = alternative.getWords(0);
    int currentSpeakerTag = wordInfo.getSpeakerTag();

    // For each word, get all the words associated with one speaker, once the speaker changes,
    // add a new line with the new speaker and their spoken words.
    StringBuilder speakerWords =
        new StringBuilder(
            String.format("Speaker %d: %s", wordInfo.getSpeakerTag(), wordInfo.getWord()));

    for (int i = 1; i < alternative.getWordsCount(); i++) {
      wordInfo = alternative.getWords(i);
      if (currentSpeakerTag == wordInfo.getSpeakerTag()) {
        speakerWords.append(" ");
        speakerWords.append(wordInfo.getWord());
      } else {
        speakerWords.append(
            String.format("\nSpeaker %d: %s", wordInfo.getSpeakerTag(), wordInfo.getWord()));
        currentSpeakerTag = wordInfo.getSpeakerTag();
      }
    }

    System.out.println(speakerWords.toString());
  }
}

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
const speech = require('@google-cloud/speech').v1p1beta1;

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

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const uri = path to GCS audio file e.g. `gs:/bucket/audio.wav`;

const config = {
  encoding: 'LINEAR16',
  sampleRateHertz: 8000,
  languageCode: 'en-US',
  enableSpeakerDiarization: true,
  minSpeakerCount: 2,
  maxSpeakerCount: 2,
  model: 'phone_call',
};

const audio = {
  uri: gcsUri,
};

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

const [response] = await client.recognize(request);
const transcription = response.results
  .map(result => result.alternatives[0].transcript)
  .join('\n');
console.log(`Transcription: ${transcription}`);
console.log('Speaker Diarization:');
const result = response.results[response.results.length - 1];
const wordsInfo = result.alternatives[0].words;
// Note: The transcript within each result is separate and sequential per result.
// However, the words list within an alternative includes all the words
// from all the results thus far. Thus, to get all the words with speaker
// tags, you only have to take the words list from the last result:
wordsInfo.forEach(a =>
  console.log(` word: ${a.word}, speakerTag: ${a.speakerTag}`)
);

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_diarization_gcs_beta(audio_uri: str) -> bool:
    """Transcribe a remote audio file (stored in Google Cloud Storage) using speaker diarization.
    Args:
        audio_uri (str): The Google Cloud Storage path to an audio file.
            E.g., gs://[BUCKET]/[FILE]
    Returns:
        True if the operation successfully completed, False otherwise.
    """

    client = speech.SpeechClient()
    # Enhance diarization config with more speaker counts and details
    speaker_diarization_config = speech.SpeakerDiarizationConfig(
        enable_speaker_diarization=True,
        min_speaker_count=2,  # Set minimum number of speakers
        max_speaker_count=2,  # Adjust max speakers based on expected number of speakers
    )

    # Configure recognition with enhanced audio settings
    recognition_config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        language_code="en-US",
        sample_rate_hertz=8000,
        diarization_config=speaker_diarization_config,
    )

    # Set the remote path for the audio file
    audio = speech.RecognitionAudio(
        uri=audio_uri,
    )

    # Use non-blocking call for getting file transcription
    response = client.long_running_recognize(
        config=recognition_config, audio=audio
    ).result(timeout=300)

    # The transcript within each result is separate and sequential per result.
    # However, the words list within an alternative includes all the words
    # from all the results thus far. Thus, to get all the words with speaker
    # tags, you only have to take the words list from the last result
    result = response.results[-1]
    words_info = result.alternatives[0].words

    # Print the output
    for word_info in words_info:
        print(f"word: '{word_info.word}', speaker_tag: {word_info.speaker_tag}")
    return True

What's next

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