Amazon Transcribe Service Update: Amazon Transcribe's Automatic Content Redaction feature enables you to automatically redact sensitive personally identifiable information (PII) from transcription results. It replaces each instance of an identified PII utterance with a [PII] tag in the transcript.

AWS · AWS · commit e72d87e1bfa6 · 2020-02-26T19:05:29.000Z
diff --git a/.changes/next-release/feature-AmazonTranscribeService-cc7be29.json b/.changes/next-release/feature-AmazonTranscribeService-cc7be29.json
@@ -0,0 +1,5 @@
+{
+    "type": "feature",
+    "category": "Amazon Transcribe Service",
+    "description": "Amazon Transcribe's Automatic Content Redaction feature enables you to automatically redact sensitive personally identifiable information (PII) from transcription results. It replaces each instance of an identified PII utterance with a [PII] tag in the transcript."
+}
diff --git a/services/transcribe/src/main/resources/codegen-resources/service-2.json b/services/transcribe/src/main/resources/codegen-resources/service-2.json
@@ -103,7 +103,7 @@
         {"shape":"InternalFailureException"},
         {"shape":"NotFoundException"}
       ],
-      "documentation":"<p>Returns information about a transcription job. To see the status of the job, check the <code>TranscriptionJobStatus</code> field. If the status is <code>COMPLETED</code>, the job is finished and you can find the results at the location specified in the <code>TranscriptionFileUri</code> field.</p>"
+      "documentation":"<p>Returns information about a transcription job. To see the status of the job, check the <code>TranscriptionJobStatus</code> field. If the status is <code>COMPLETED</code>, the job is finished and you can find the results at the location specified in the <code>TranscriptFileUri</code> field. If you enable content redaction, the redacted transcript appears in <code>RedactedTranscriptFileUri</code>.</p>"
     },
     "GetVocabulary":{
       "name":"GetVocabulary",
@@ -250,6 +250,24 @@
       "documentation":"<p>When you are using the <code>CreateVocabulary</code> operation, the <code>JobName</code> field is a duplicate of a previously entered job name. Resend your request with a different name.</p> <p>When you are using the <code>UpdateVocabulary</code> operation, there are two jobs running at the same time. Resend the second request later.</p>",
       "exception":true
     },
+    "ContentRedaction":{
+      "type":"structure",
+      "required":[
+        "RedactionType",
+        "RedactionOutput"
+      ],
+      "members":{
+        "RedactionType":{
+          "shape":"RedactionType",
+          "documentation":"<p>Request parameter that defines the entities to be redacted. The only accepted value is <code>PII</code>.</p>"
+        },
+        "RedactionOutput":{
+          "shape":"RedactionOutput",
+          "documentation":"<p>Request parameter where you choose whether to output only the redacted transcript or generate an additional unredacted transcript.</p> <p>When you choose <code>redacted</code> Amazon Transcribe outputs a JSON file with only the redacted transcript and related information.</p> <p>When you choose <code>redacted_and_unredacted</code> Amazon Transcribe outputs a JSON file with the unredacted transcript and related information in addition to the JSON file with the redacted transcript.</p>"
+        }
+      },
+      "documentation":"<p>Settings for content redaction within a transcription job.</p> <p>You can redact transcripts in US English (en-us). For more information see: <a href=\"https://docs.aws.amazon.com/transcribe/latest/dg/content-redaction.html\">Automatic Content Redaction</a> </p>"
+    },
     "CreateVocabularyFilterRequest":{
       "type":"structure",
       "required":[
@@ -666,7 +684,7 @@
       "members":{
         "MediaFileUri":{
           "shape":"Uri",
-          "documentation":"<p>The S3 location of the input media file. The URI must be in the same region as the API endpoint that you are calling. The general form is:</p> <p> <code> https://s3.&lt;aws-region&gt;.amazonaws.com/&lt;bucket-name&gt;/&lt;keyprefix&gt;/&lt;objectkey&gt; </code> </p> <p>For example:</p> <p> <code>https://s3.us-east-1.amazonaws.com/examplebucket/example.mp4</code> </p> <p> <code>https://s3.us-east-1.amazonaws.com/examplebucket/mediadocs/example.mp4</code> </p> <p>For more information about S3 object names, see <a href=\"http://docs.aws.amazon.com/AmazonS3/latest/dev/UsingMetadata.html#object-keys\">Object Keys</a> in the <i>Amazon S3 Developer Guide</i>.</p>"
+          "documentation":"<p>The S3 object location of the input media file. The URI must be in the same region as the API endpoint that you are calling. The general form is:</p> <p> <code> s3://&lt;bucket-name&gt;/&lt;keyprefix&gt;/&lt;objectkey&gt; </code> </p> <p>For example:</p> <p> <code>s3://examplebucket/example.mp4</code> </p> <p> <code>s3://examplebucket/mediadocs/example.mp4</code> </p> <p>For more information about S3 object names, see <a href=\"http://docs.aws.amazon.com/AmazonS3/latest/dev/UsingMetadata.html#object-keys\">Object Keys</a> in the <i>Amazon S3 Developer Guide</i>.</p>"
         }
       },
       "documentation":"<p>Describes the input media file in a transcription request.</p>"
@@ -720,6 +738,17 @@
       "type":"list",
       "member":{"shape":"Phrase"}
     },
+    "RedactionOutput":{
+      "type":"string",
+      "enum":[
+        "redacted",
+        "redacted_and_unredacted"
+      ]
+    },
+    "RedactionType":{
+      "type":"string",
+      "enum":["PII"]
+    },
     "Settings":{
       "type":"structure",
       "members":{
@@ -788,7 +817,7 @@
         },
         "OutputBucketName":{
           "shape":"OutputBucketName",
-          "documentation":"<p>The location where the transcription is stored.</p> <p>If you set the <code>OutputBucketName</code>, Amazon Transcribe puts the transcription in the specified S3 bucket. When you call the <a>GetTranscriptionJob</a> operation, the operation returns this location in the <code>TranscriptFileUri</code> field. The S3 bucket must have permissions that allow Amazon Transcribe to put files in the bucket. For more information, see <a href=\"https://docs.aws.amazon.com/transcribe/latest/dg/security_iam_id-based-policy-examples.html#auth-role-iam-user\">Permissions Required for IAM User Roles</a>.</p> <p>You can specify an AWS Key Management Service (KMS) key to encrypt the output of your transcription using the <code>OutputEncryptionKMSKeyId</code> parameter. If you don't specify a KMS key, Amazon Transcribe uses the default Amazon S3 key for server-side encryption of transcripts that are placed in your S3 bucket.</p> <p>If you don't set the <code>OutputBucketName</code>, Amazon Transcribe generates a pre-signed URL, a shareable URL that provides secure access to your transcription, and returns it in the <code>TranscriptFileUri</code> field. Use this URL to download the transcription.</p>"
+          "documentation":"<p>The location where the transcription is stored.</p> <p>If you set the <code>OutputBucketName</code>, Amazon Transcribe puts the transcript in the specified S3 bucket. When you call the <a>GetTranscriptionJob</a> operation, the operation returns this location in the <code>TranscriptFileUri</code> field. If you enable content redaction, the redacted transcript appears in <code>RedactedTranscriptFileUri</code>. If you enable content redaction and choose to output an unredacted transcript, that transcript's location still appears in the <code>TranscriptFileUri</code>. The S3 bucket must have permissions that allow Amazon Transcribe to put files in the bucket. For more information, see <a href=\"https://docs.aws.amazon.com/transcribe/latest/dg/security_iam_id-based-policy-examples.html#auth-role-iam-user\">Permissions Required for IAM User Roles</a>.</p> <p>You can specify an AWS Key Management Service (KMS) key to encrypt the output of your transcription using the <code>OutputEncryptionKMSKeyId</code> parameter. If you don't specify a KMS key, Amazon Transcribe uses the default Amazon S3 key for server-side encryption of transcripts that are placed in your S3 bucket.</p> <p>If you don't set the <code>OutputBucketName</code>, Amazon Transcribe generates a pre-signed URL, a shareable URL that provides secure access to your transcription, and returns it in the <code>TranscriptFileUri</code> field. Use this URL to download the transcription.</p>"
         },
         "OutputEncryptionKMSKeyId":{
           "shape":"KMSKeyId",
@@ -801,6 +830,10 @@
         "JobExecutionSettings":{
           "shape":"JobExecutionSettings",
           "documentation":"<p>Provides information about how a transcription job is executed. Use this field to indicate that the job can be queued for deferred execution if the concurrency limit is reached and there are no slots available to immediately run the job.</p>"
+        },
+        "ContentRedaction":{
+          "shape":"ContentRedaction",
+          "documentation":"<p>An object that contains the request parameters for content redaction.</p>"
         }
       }
     },
@@ -819,7 +852,11 @@
       "members":{
         "TranscriptFileUri":{
           "shape":"Uri",
-          "documentation":"<p>The location where the transcription is stored.</p> <p>Use this URI to access the transcription. If you specified an S3 bucket in the <code>OutputBucketName</code> field when you created the job, this is the URI of that bucket. If you chose to store the transcription in Amazon Transcribe, this is a shareable URL that provides secure access to that location.</p>"
+          "documentation":"<p>The S3 object location of the the transcript.</p> <p>Use this URI to access the transcript. If you specified an S3 bucket in the <code>OutputBucketName</code> field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.</p>"
+        },
+        "RedactedTranscriptFileUri":{
+          "shape":"Uri",
+          "documentation":"<p>The S3 object location of the redacted transcript.</p> <p>Use this URI to access the redacated transcript. If you specified an S3 bucket in the <code>OutputBucketName</code> field when you created the job, this is the URI of that bucket. If you chose to store the transcript in Amazon Transcribe, this is a shareable URL that provides secure access to that location.</p>"
         }
       },
       "documentation":"<p>Identifies the location of a transcription.</p>"
@@ -878,6 +915,10 @@
         "JobExecutionSettings":{
           "shape":"JobExecutionSettings",
           "documentation":"<p>Provides information about how a transcription job is executed.</p>"
+        },
+        "ContentRedaction":{
+          "shape":"ContentRedaction",
+          "documentation":"<p>An object that describes content redaction settings for the transcription job.</p>"
         }
       },
       "documentation":"<p>Describes an asynchronous transcription job that was created with the <code>StartTranscriptionJob</code> operation. </p>"
@@ -935,6 +976,10 @@
         "OutputLocationType":{
           "shape":"OutputLocationType",
           "documentation":"<p>Indicates the location of the output of the transcription job.</p> <p>If the value is <code>CUSTOMER_BUCKET</code> then the location is the S3 bucket specified in the <code>outputBucketName</code> field when the transcription job was started with the <code>StartTranscriptionJob</code> operation.</p> <p>If the value is <code>SERVICE_BUCKET</code> then the output is stored by Amazon Transcribe and can be retrieved using the URI in the <code>GetTranscriptionJob</code> response's <code>TranscriptFileUri</code> field.</p>"
+        },
+        "ContentRedaction":{
+          "shape":"ContentRedaction",
+          "documentation":"<p>The content redaction settings of the transcription job.</p>"
         }
       },
       "documentation":"<p>Provides a summary of information about a transcription job.</p>"
