Use StartTranscriptionJob with an Amazon SDK or CLI

    /// <summary>
    /// Start a transcription job for a media file. This method returns
    /// as soon as the job is started.
    /// </summary>
    /// <param name="jobName">A unique name for the transcription job.</param>
    /// <param name="mediaFileUri">The URI of the media file, typically an Amazon S3 location.</param>
    /// <param name="mediaFormat">The format of the media file.</param>
    /// <param name="languageCode">The language code of the media file, such as en-US.</param>
    /// <param name="vocabularyName">Optional name of a custom vocabulary.</param>
    /// <returns>A TranscriptionJob instance with information on the new job.</returns>
    public async Task<TranscriptionJob> StartTranscriptionJob(string jobName, string mediaFileUri,
        MediaFormat mediaFormat, LanguageCode languageCode, string? vocabularyName)
    {
        var response = await _amazonTranscribeService.StartTranscriptionJobAsync(
            new StartTranscriptionJobRequest()
            {
                TranscriptionJobName = jobName,
                Media = new Media()
                {
                    MediaFileUri = mediaFileUri
                },
                MediaFormat = mediaFormat,
                LanguageCode = languageCode,
                Settings = vocabularyName != null ? new Settings()
                {
                    VocabularyName = vocabularyName
                } : null
            });
        return response.TranscriptionJob;
    }

Example 1: To transcribe an audio file

The following start-transcription-job example transcribes your audio file.

aws transcribe start-transcription-job \
    --cli-input-json file://myfile.json

Contents of myfile.json:

{
    "TranscriptionJobName": "cli-simple-transcription-job",
    "LanguageCode": "the-language-of-your-transcription-job",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
    }
}

For more information, see Getting Started (Amazon Command Line Interface) in the Amazon Transcribe Developer Guide.

Example 2: To transcribe a multi-channel audio file

The following start-transcription-job example transcribes your multi-channel audio file.

aws transcribe start-transcription-job \
    --cli-input-json file://mysecondfile.json

Contents of mysecondfile.json:

{
    "TranscriptionJobName": "cli-channelid-job",
    "LanguageCode": "the-language-of-your-transcription-job",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
    },
    "Settings":{
        "ChannelIdentification":true
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-channelid-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "the-language-of-your-transcription-job",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
        },
        "StartTime": "2020-09-17T16:07:56.817000+00:00",
        "CreationTime": "2020-09-17T16:07:56.784000+00:00",
        "Settings": {
            "ChannelIdentification": true
        }
    }
}

For more information, see Transcribing Multi-Channel Audio in the Amazon Transcribe Developer Guide.

Example 3: To transcribe an audio file and identify the different speakers

The following start-transcription-job example transcribes your audio file and identifies the speakers in the transcription output.

aws transcribe start-transcription-job \
    --cli-input-json file://mythirdfile.json

Contents of mythirdfile.json:

{
    "TranscriptionJobName": "cli-speakerid-job",
    "LanguageCode": "the-language-of-your-transcription-job",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
    },
    "Settings":{
    "ShowSpeakerLabels": true,
    "MaxSpeakerLabels": 2
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-speakerid-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "the-language-of-your-transcription-job",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
        },
        "StartTime": "2020-09-17T16:22:59.696000+00:00",
        "CreationTime": "2020-09-17T16:22:59.676000+00:00",
        "Settings": {
            "ShowSpeakerLabels": true,
            "MaxSpeakerLabels": 2
        }
    }
}

For more information, see Identifying Speakers in the Amazon Transcribe Developer Guide.

Example 4: To transcribe an audio file and mask any unwanted words in the transcription output

The following start-transcription-job example transcribes your audio file and uses a vocabulary filter you've previously created to mask any unwanted words.

aws transcribe start-transcription-job \
    --cli-input-json file://myfourthfile.json

Contents of myfourthfile.json:

{
    "TranscriptionJobName": "cli-filter-mask-job",
    "LanguageCode": "the-language-of-your-transcription-job",
    "Media": {
          "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
    },
    "Settings":{
        "VocabularyFilterName": "your-vocabulary-filter",
        "VocabularyFilterMethod": "mask"
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-filter-mask-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "the-language-of-your-transcription-job",
        "Media": {
            "MediaFileUri": "s3://Amazon-S3-Prefix/your-media-file.file-extension"
        },
        "StartTime": "2020-09-18T16:36:18.568000+00:00",
        "CreationTime": "2020-09-18T16:36:18.547000+00:00",
        "Settings": {
            "VocabularyFilterName": "your-vocabulary-filter",
            "VocabularyFilterMethod": "mask"
        }
    }
}

For more information, see Filtering Transcriptions in the Amazon Transcribe Developer Guide.

Example 5: To transcribe an audio file and remove any unwanted words in the transcription output

The following start-transcription-job example transcribes your audio file and uses a vocabulary filter you've previously created to mask any unwanted words.

aws transcribe start-transcription-job \
    --cli-input-json file://myfifthfile.json

Contents of myfifthfile.json:

{
    "TranscriptionJobName": "cli-filter-remove-job",
    "LanguageCode": "the-language-of-your-transcription-job",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
    },
    "Settings":{
        "VocabularyFilterName": "your-vocabulary-filter",
        "VocabularyFilterMethod": "remove"
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-filter-remove-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "the-language-of-your-transcription-job",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
        },
        "StartTime": "2020-09-18T16:36:18.568000+00:00",
        "CreationTime": "2020-09-18T16:36:18.547000+00:00",
        "Settings": {
            "VocabularyFilterName": "your-vocabulary-filter",
            "VocabularyFilterMethod": "remove"
        }
    }
}

For more information, see Filtering Transcriptions in the Amazon Transcribe Developer Guide.

Example 6: To transcribe an audio file with increased accuracy using a custom vocabulary

The following start-transcription-job example transcribes your audio file and uses a vocabulary filter you've previously created to mask any unwanted words.

aws transcribe start-transcription-job \
    --cli-input-json file://mysixthfile.json

Contents of mysixthfile.json:

{
    "TranscriptionJobName": "cli-vocab-job",
    "LanguageCode": "the-language-of-your-transcription-job",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
    },
    "Settings":{
        "VocabularyName": "your-vocabulary"
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-vocab-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "the-language-of-your-transcription-job",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
        },
        "StartTime": "2020-09-18T16:36:18.568000+00:00",
        "CreationTime": "2020-09-18T16:36:18.547000+00:00",
        "Settings": {
            "VocabularyName": "your-vocabulary"
        }
    }
}

For more information, see Filtering Transcriptions in the Amazon Transcribe Developer Guide.

Example 7: To identify the language of an audio file and transcribe it

The following start-transcription-job example transcribes your audio file and uses a vocabulary filter you've previously created to mask any unwanted words.

aws transcribe start-transcription-job \
    --cli-input-json file://myseventhfile.json

Contents of myseventhfile.json:

{
    "TranscriptionJobName": "cli-identify-language-transcription-job",
    "IdentifyLanguage": true,
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-identify-language-transcription-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/Amazon-S3-prefix/your-media-file-name.file-extension"
        },
        "StartTime": "2020-09-18T22:27:23.970000+00:00",
        "CreationTime": "2020-09-18T22:27:23.948000+00:00",
        "IdentifyLanguage": true
    }
}

For more information, see Identifying the Language in the Amazon Transcribe Developer Guide.

Example 8: To transcribe an audio file with personally identifiable information redacted

The following start-transcription-job example transcribes your audio file and redacts any personally identifiable information in the transcription output.

aws transcribe start-transcription-job \
    --cli-input-json file://myeighthfile.json

Contents of myeigthfile.json:

{
    "TranscriptionJobName": "cli-redaction-job",
    "LanguageCode": "language-code",
    "Media": {
        "MediaFileUri": "s3://Amazon-S3-Prefix/your-media-file.file-extension"
    },
    "ContentRedaction": {
        "RedactionOutput":"redacted",
        "RedactionType":"PII"
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-redaction-job",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://Amazon-S3-Prefix/your-media-file.file-extension"
        },
        "StartTime": "2020-09-25T23:49:13.195000+00:00",
        "CreationTime": "2020-09-25T23:49:13.176000+00:00",
        "ContentRedaction": {
            "RedactionType": "PII",
            "RedactionOutput": "redacted"
        }
    }
}

For more information, see Automatic Content Redaction in the Amazon Transcribe Developer Guide.

Example 9: To generate a transcript with personally identifiable information (PII) redacted and an unredacted transcript

The following start-transcription-job example generates two transcrptions of your audio file, one with the personally identifiable information redacted, and the other without any redactions.

aws transcribe start-transcription-job \
    --cli-input-json file://myninthfile.json

Contents of myninthfile.json:

{
    "TranscriptionJobName": "cli-redaction-job-with-unredacted-transcript",
    "LanguageCode": "language-code",
    "Media": {
          "MediaFileUri": "s3://Amazon-S3-Prefix/your-media-file.file-extension"
        },
    "ContentRedaction": {
        "RedactionOutput":"redacted_and_unredacted",
        "RedactionType":"PII"
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-redaction-job-with-unredacted-transcript",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://Amazon-S3-Prefix/your-media-file.file-extension"
        },
        "StartTime": "2020-09-25T23:59:47.677000+00:00",
        "CreationTime": "2020-09-25T23:59:47.653000+00:00",
        "ContentRedaction": {
            "RedactionType": "PII",
            "RedactionOutput": "redacted_and_unredacted"
        }
    }
}

For more information, see Automatic Content Redaction in the Amazon Transcribe Developer Guide.

Example 10: To use a custom language model you've previously created to transcribe an audio file.

The following start-transcription-job example transcribes your audio file with a custom language model you've previously created.

aws transcribe start-transcription-job \
    --cli-input-json file://mytenthfile.json

Contents of mytenthfile.json:

{
    "TranscriptionJobName": "cli-clm-2-job-1",
    "LanguageCode": "language-code",
    "Media": {
        "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.file-extension"
    },
    "ModelSettings": {
        "LanguageModelName":"cli-clm-2"
    }
}

Output:

{
    "TranscriptionJob": {
        "TranscriptionJobName": "cli-clm-2-job-1",
        "TranscriptionJobStatus": "IN_PROGRESS",
        "LanguageCode": "language-code",
        "Media": {
            "MediaFileUri": "s3://DOC-EXAMPLE-BUCKET/your-audio-file.file-extension"
        },
        "StartTime": "2020-09-28T17:56:01.835000+00:00",
        "CreationTime": "2020-09-28T17:56:01.801000+00:00",
        "ModelSettings": {
            "LanguageModelName": "cli-clm-2"
        }
    }
}

For more information, see Improving Domain-Specific Transcription Accuracy with Custom Language Models in the Amazon Transcribe Developer Guide.

public class TranscribeStreamingDemoApp {
    private static final Region REGION = Region.US_EAST_1;
    private static TranscribeStreamingAsyncClient client;

    public static void main(String args[])
            throws URISyntaxException, ExecutionException, InterruptedException, LineUnavailableException {

        client = TranscribeStreamingAsyncClient.builder()
                .credentialsProvider(getCredentials())
                .region(REGION)
                .build();

        CompletableFuture<Void> result = client.startStreamTranscription(getRequest(16_000),
                new AudioStreamPublisher(getStreamFromMic()),
                getResponseHandler());

        result.get();
        client.close();
    }

    private static InputStream getStreamFromMic() throws LineUnavailableException {

        // Signed PCM AudioFormat with 16kHz, 16 bit sample size, mono
        int sampleRate = 16000;
        AudioFormat format = new AudioFormat(sampleRate, 16, 1, true, false);
        DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);

        if (!AudioSystem.isLineSupported(info)) {
            System.out.println("Line not supported");
            System.exit(0);
        }

        TargetDataLine line = (TargetDataLine) AudioSystem.getLine(info);
        line.open(format);
        line.start();

        InputStream audioStream = new AudioInputStream(line);
        return audioStream;
    }

    private static AwsCredentialsProvider getCredentials() {
        return DefaultCredentialsProvider.create();
    }

    private static StartStreamTranscriptionRequest getRequest(Integer mediaSampleRateHertz) {
        return StartStreamTranscriptionRequest.builder()
                .languageCode(LanguageCode.EN_US.toString())
                .mediaEncoding(MediaEncoding.PCM)
                .mediaSampleRateHertz(mediaSampleRateHertz)
                .build();
    }

    private static StartStreamTranscriptionResponseHandler getResponseHandler() {
        return StartStreamTranscriptionResponseHandler.builder()
                .onResponse(r -> {
                    System.out.println("Received Initial response");
                })
                .onError(e -> {
                    System.out.println(e.getMessage());
                    StringWriter sw = new StringWriter();
                    e.printStackTrace(new PrintWriter(sw));
                    System.out.println("Error Occurred: " + sw.toString());
                })
                .onComplete(() -> {
                    System.out.println("=== All records stream successfully ===");
                })
                .subscriber(event -> {
                    List<Result> results = ((TranscriptEvent) event).transcript().results();
                    if (results.size() > 0) {
                        if (!results.get(0).alternatives().get(0).transcript().isEmpty()) {
                            System.out.println(results.get(0).alternatives().get(0).transcript());
                        }
                    }
                })
                .build();
    }

    private InputStream getStreamFromFile(String audioFileName) {
        try {
            File inputFile = new File(getClass().getClassLoader().getResource(audioFileName).getFile());
            InputStream audioStream = new FileInputStream(inputFile);
            return audioStream;
        } catch (FileNotFoundException e) {
            throw new RuntimeException(e);
        }
    }

    private static class AudioStreamPublisher implements Publisher<AudioStream> {
        private final InputStream inputStream;
        private static Subscription currentSubscription;

        private AudioStreamPublisher(InputStream inputStream) {
            this.inputStream = inputStream;
        }

        @Override
        public void subscribe(Subscriber<? super AudioStream> s) {

            if (this.currentSubscription == null) {
                this.currentSubscription = new SubscriptionImpl(s, inputStream);
            } else {
                this.currentSubscription.cancel();
                this.currentSubscription = new SubscriptionImpl(s, inputStream);
            }
            s.onSubscribe(currentSubscription);
        }
    }

    public static class SubscriptionImpl implements Subscription {
        private static final int CHUNK_SIZE_IN_BYTES = 1024 * 1;
        private final Subscriber<? super AudioStream> subscriber;
        private final InputStream inputStream;
        private ExecutorService executor = Executors.newFixedThreadPool(1);
        private AtomicLong demand = new AtomicLong(0);

        SubscriptionImpl(Subscriber<? super AudioStream> s, InputStream inputStream) {
            this.subscriber = s;
            this.inputStream = inputStream;
        }

        @Override
        public void request(long n) {
            if (n <= 0) {
                subscriber.onError(new IllegalArgumentException("Demand must be positive"));
            }

            demand.getAndAdd(n);

            executor.submit(() -> {
                try {
                    do {
                        ByteBuffer audioBuffer = getNextEvent();
                        if (audioBuffer.remaining() > 0) {
                            AudioEvent audioEvent = audioEventFromBuffer(audioBuffer);
                            subscriber.onNext(audioEvent);
                        } else {
                            subscriber.onComplete();
                            break;
                        }
                    } while (demand.decrementAndGet() > 0);
                } catch (Exception e) {
                    subscriber.onError(e);
                }
            });
        }

        @Override
        public void cancel() {
            executor.shutdown();
        }

        private ByteBuffer getNextEvent() {
            ByteBuffer audioBuffer = null;
            byte[] audioBytes = new byte[CHUNK_SIZE_IN_BYTES];

            int len = 0;
            try {
                len = inputStream.read(audioBytes);

                if (len <= 0) {
                    audioBuffer = ByteBuffer.allocate(0);
                } else {
                    audioBuffer = ByteBuffer.wrap(audioBytes, 0, len);
                }
            } catch (IOException e) {
                throw new UncheckedIOException(e);
            }

            return audioBuffer;
        }

        private AudioEvent audioEventFromBuffer(ByteBuffer bb) {
            return AudioEvent.builder()
                    .audioChunk(SdkBytes.fromByteBuffer(bb))
                    .build();
        }
    }
}

Start a transcription job.

// Import the required AWS SDK clients and commands for Node.js
import { StartTranscriptionJobCommand } from "@aws-sdk/client-transcribe";
import { transcribeClient } from "./libs/transcribeClient.js";

// Set the parameters
export const params = {
  TranscriptionJobName: "JOB_NAME",
  LanguageCode: "LANGUAGE_CODE", // For example, 'en-US'
  MediaFormat: "SOURCE_FILE_FORMAT", // For example, 'wav'
  Media: {
    MediaFileUri: "SOURCE_LOCATION",
    // For example, "https://transcribe-demo.s3-REGION.amazonaws.com/hello_world.wav"
  },
  OutputBucketName: "OUTPUT_BUCKET_NAME"
};

export const run = async () => {
  try {
    const data = await transcribeClient.send(
      new StartTranscriptionJobCommand(params)
    );
    console.log("Success - put", data);
    return data; // For unit tests.
  } catch (err) {
    console.log("Error", err);
  }
};
run();

Create the client.

import { TranscribeClient } from "@aws-sdk/client-transcribe";
// Set the AWS Region.
const REGION = "REGION"; //e.g. "us-east-1"
// Create an Amazon Transcribe service client object.
const transcribeClient = new TranscribeClient({ region: REGION });
export { transcribeClient };

def start_job(
    job_name,
    media_uri,
    media_format,
    language_code,
    transcribe_client,
    vocabulary_name=None,
):
    """
    Starts a transcription job. This function returns as soon as the job is started.
    To get the current status of the job, call get_transcription_job. The job is
    successfully completed when the job status is 'COMPLETED'.

    :param job_name: The name of the transcription job. This must be unique for
                     your AWS account.
    :param media_uri: The URI where the audio file is stored. This is typically
                      in an Amazon S3 bucket.
    :param media_format: The format of the audio file. For example, mp3 or wav.
    :param language_code: The language code of the audio file.
                          For example, en-US or ja-JP
    :param transcribe_client: The Boto3 Transcribe client.
    :param vocabulary_name: The name of a custom vocabulary to use when transcribing
                            the audio file.
    :return: Data about the job.
    """
    try:
        job_args = {
            "TranscriptionJobName": job_name,
            "Media": {"MediaFileUri": media_uri},
            "MediaFormat": media_format,
            "LanguageCode": language_code,
        }
        if vocabulary_name is not None:
            job_args["Settings"] = {"VocabularyName": vocabulary_name}
        response = transcribe_client.start_transcription_job(**job_args)
        job = response["TranscriptionJob"]
        logger.info("Started transcription job %s.", job_name)
    except ClientError:
        logger.exception("Couldn't start transcription job %s.", job_name)
        raise
    else:
        return job