Transcribing audio with multiple channels

This page describes how to transcribe audio files that include more than one channel using Speech-to-Text.

Often times, audio data include a channel for each speaker present on the recording. For audio of two people talking over the phone, as an example, the audio may contain two channels where each line is recorded separately.

To transcribe audio data that includes multiple channels, you must provide the number of channels in your request to the Speech-to-Text API. In your request, set the audioChannelCount field in your request to the number of channels present in your audio.

When you send a request with multiple channels, Speech-to-Text returns a result to you that identifies the different channels present in the audio, labeling the alternatives for each result with the channelTag field.

The following code sample demonstrates how to transcribe audio that contains multiple channels.

Protocol

Refer to the speech:recognize 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.

The following example show how to send a POST request using curl, where the body of the request specifies the number of channels present on the audio sample.

curl -X POST -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     --data '{
    "config": {
        "encoding": "LINEAR16",
        "languageCode": "en-US",
        "audioChannelCount": 2,
        "enableSeparateRecognitionPerChannel": true
    },
    "audio": {
        "uri": "gs://cloud-samples-tests/speech/commercial_stereo.wav"
    }
}' "https://speech.googleapis.com/v1/speech:recognize" > multi-channel.txt

If the request is successful, the server returns a 200 OK HTTP status code and the response in JSON format, saved to a file named multi-channel.txt.

{
  "results": [
    {
      "alternatives": [
        {
          "transcript": "hi I'd like to buy a Chromecast I'm always wondering whether you could help me with that",
          "confidence": 0.8991147
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": "certainly which color would you like we have blue black and red",
          "confidence": 0.9408236
        }
      ],
      "channelTag": 2,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " let's go with the black one",
          "confidence": 0.98783094
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " would you like the new Chromecast Ultra model or the regular Chromecast",
          "confidence": 0.9573053
        }
      ],
      "channelTag": 2,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " regular Chromecast is fine thank you",
          "confidence": 0.9671048
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " okay sure would you like to ship it regular or Express",
          "confidence": 0.9544821
        }
      ],
      "channelTag": 2,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " express please",
          "confidence": 0.9487205
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " terrific it's on the way thank you",
          "confidence": 0.97655964
        }
      ],
      "channelTag": 2,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " thank you very much bye",
          "confidence": 0.9735077
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    }
  ]
}

Go


// transcribeMultichannel generates a transcript from a multichannel speech file and tags the speech from each channel.
func transcribeMultichannel(w io.Writer, path string) error {
	ctx := context.Background()

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

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

	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:                            speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz:                     44100,
			LanguageCode:                        "en-US",
			AudioChannelCount:                   2,
			EnableSeparateRecognitionPerChannel: true,
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	})
	if err != nil {
		return fmt.Errorf("Recognize: %v", err)
	}

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

Java

/**
 * Transcribe a remote audio file with multi-channel recognition
 *
 * @param gcsUri the path to the audio file
 */
public static void transcribeMultiChannelGcs(String gcsUri) throws Exception {

  try (SpeechClient speechClient = SpeechClient.create()) {

    // Configure request to enable multiple channels
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            .setSampleRateHertz(44100)
            .setAudioChannelCount(2)
            .setEnableSeparateRecognitionPerChannel(true)
            .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);
    }
    // Just print the first result here.
    for (SpeechRecognitionResult result : response.get().getResultsList()) {

      // 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);

      // Print out the result
      System.out.printf("Transcript : %s\n", alternative.getTranscript());
      System.out.printf("Channel Tag : %s\n", result.getChannelTag());
    }
  }
}

Node.js

const speech = require('@google-cloud/speech').v1;

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

const config = {
  encoding: 'LINEAR16',
  languageCode: 'en-US',
  audioChannelCount: 2,
  enableSeparateRecognitionPerChannel: true,
};

const audio = {
  uri: gcsUri,
};

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

const [response] = await client.recognize(request);
const transcription = response.results
  .map(
    result =>
      ` Channel Tag: ${result.channelTag} ${result.alternatives[0].transcript}`
  )
  .join('\n');
console.log(`Transcription: \n${transcription}`);

Ruby

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

require "google/cloud/speech"

speech = Google::Cloud::Speech.speech

config = {
  encoding:                                :LINEAR16,
  sample_rate_hertz:                       44_100,
  language_code:                           "en-US",
  audio_channel_count:                     2,
  enable_separate_recognition_per_channel: true
}

audio = { uri: storage_path }

response = speech.recognize config: config, audio: audio

results = 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}"
  puts "Channel Tag: #{result.channel_tag}"
end

Python

from google.cloud import speech_v1


def sample_recognize(storage_uri):
    """
    Transcribe a short audio file from Cloud Storage with multiple channels

    Args:
      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/multi.wav'

    # The number of channels in the input audio file (optional)
    audio_channel_count = 2

    # When set to true, each audio channel will be recognized separately.
    # The recognition result will contain a channel_tag field to state which
    # channel that result belongs to
    enable_separate_recognition_per_channel = True

    # The language of the supplied audio
    language_code = "en-US"
    config = {
        "audio_channel_count": audio_channel_count,
        "enable_separate_recognition_per_channel": enable_separate_recognition_per_channel,
        "language_code": language_code,
    }
    audio = {"uri": storage_uri}

    response = client.recognize(config, audio)
    for result in response.results:
        # channel_tag to recognize which audio channel this result is for
        print(u"Channel tag: {}".format(result.channel_tag))
        # First alternative is the most probable result
        alternative = result.alternatives[0]
        print(u"Transcript: {}".format(alternative.transcript))

C#

static object SyncRecognizeMultipleChannels(string filePath, int channelCount)
{
    var speech = SpeechClient.Create();

    // Create transcription request
    var response = speech.Recognize(new RecognitionConfig()
    {
        Encoding = RecognitionConfig.Types.AudioEncoding.Linear16,
        LanguageCode = "en",
        // Configure request to enable multiple channels
        EnableSeparateRecognitionPerChannel = true,
        AudioChannelCount = channelCount
        // Note: Sample uses local file.
    }, RecognitionAudio.FromFile(filePath));

    // Print out the results.
    foreach (var result in response.Results)
    {
        // There can be several transcripts for a chunk of audio.
        // Print out the first (most likely) one here.
        var alternative = result.Alternatives[0];
        Console.WriteLine($"Transcript: {alternative.Transcript}");
        Console.WriteLine($"Channel Tag: {result.ChannelTag}");
    }
    return 0;
}