Amazon Transcribe

Automatically convert speech to text

Extract key business insights from customer calls, video files, clinical conversations, and more.
Improve business outcomes with state of the art speech recognition models that are fully managed and continuously trained.
Ensure customer privacy and safety by masking sensitive information.

Usage

Amazon ML Processors are implemented to utilize ML services based on the official AWS API Reference. You can find example json payload in the documentation at the Request Syntax sections. For more details please check the official Transcribe API reference With this processor you will trigger a startTranscriptionJob async call to AWS Transcribe Service. You can define json payload as property or provide as a flow file content. Property has higher precedence. After the job is triggered the serialized json response will be written to the output flow file. The awsTaskId attribute will be populated, so it makes it easier to query job status by the corresponding get job status processor.

JSON payload template - note that these can be simplified with the optional fields, check AWS documentation for more details - examples:


    {
   "ContentRedaction": {
      "PiiEntityTypes": [ "string" ],
      "RedactionOutput": "string",
      "RedactionType": "string"
   },
   "IdentifyLanguage": boolean,
   "IdentifyMultipleLanguages": boolean,
   "JobExecutionSettings": {
      "AllowDeferredExecution": boolean,
      "DataAccessRoleArn": "string"
   },
   "KMSEncryptionContext": {
      "string" : "string"
   },
   "LanguageCode": "string",
   "LanguageIdSettings": {
      "string" : {
         "LanguageModelName": "string",
         "VocabularyFilterName": "string",
         "VocabularyName": "string"
      }
   },
   "LanguageOptions": [ "string" ],
   "Media": {
      "MediaFileUri": "string",
      "RedactedMediaFileUri": "string"
   },
   "MediaFormat": "string",
   "MediaSampleRateHertz": number,
   "ModelSettings": {
      "LanguageModelName": "string"
   },
   "OutputBucketName": "string",
   "OutputEncryptionKMSKeyId": "string",
   "OutputKey": "string",
   "Settings": {
      "ChannelIdentification": boolean,
      "MaxAlternatives": number,
      "MaxSpeakerLabels": number,
      "ShowAlternatives": boolean,
      "ShowSpeakerLabels": boolean,
      "VocabularyFilterMethod": "string",
      "VocabularyFilterName": "string",
      "VocabularyName": "string"
   },
   "Subtitles": {
      "Formats": [ "string" ],
      "OutputStartIndex": number
   },
   "Tags": [
      {
         "Key": "string",
         "Value": "string"
      }
   ],
   "TranscriptionJobName": "string"
}