Transcription of a local file with diarization

Recognize multiple speakers in a local audio file.

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"
	"os"
	"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(w io.Writer, filename string) error {
	// filename := "path-to-an-audio-file"

	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,
	}

	// Get the contents of the local audio file
	content, err := os.ReadFile(filename)
	if err != nil {
		return fmt.Errorf("error reading file %v", err)
	}
	audio := &speechpb.RecognitionAudio{
		AudioSource: &speechpb.RecognitionAudio_Content{Content: content},
	}

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

	operation, err := client.LongRunningRecognize(ctx, longRunningRecognizeRequest)
	if err != nil {
		return fmt.Errorf("error running recognize %v", 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 the given audio file using speaker diarization.
 *
 * @param fileName the path to an audio file.
 */
public static void transcribeDiarization(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();

    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();

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

    // Speaker Tags are only included in the last result object, which has only one alternative.
    SpeechRecognitionAlternative alternative =
        recognizeResponse.getResults(recognizeResponse.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.

const fs = require('fs');

// 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 lines before running the sample.
 */
// const fileName = 'Local path to audio file, e.g. /path/to/audio.raw';

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

const audio = {
  content: fs.readFileSync(fileName).toString('base64'),
};

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_v1p1beta1 as speech

client = speech.SpeechClient()

speech_file = "resources/commercial_mono.wav"

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

audio = speech.RecognitionAudio(content=content)

diarization_config = speech.SpeakerDiarizationConfig(
    enable_speaker_diarization=True,
    min_speaker_count=2,
    max_speaker_count=10,
)

config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=8000,
    language_code="en-US",
    diarization_config=diarization_config,
)

print("Waiting for operation to complete...")
response = client.recognize(config=config, audio=audio)

# 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

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

return result

What's next

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