feat(client-transcribe-streaming): This release enables customers to …

…call the AWS Transcribe streaming service with the capability of identifying multiple languages in the stream.
aws · Nov 13, 2023 · 09ffb2a · 09ffb2a
1 parent 0b47053
commit 09ffb2a
Show file tree

Hide file tree

Showing 4 changed files with 45 additions and 4 deletions.
diff --git a/clients/client-transcribe-streaming/src/commands/StartStreamTranscriptionCommand.ts b/clients/client-transcribe-streaming/src/commands/StartStreamTranscriptionCommand.ts
@@ -55,7 +55,7 @@ export interface StartStreamTranscriptionCommandOutput extends StartStreamTransc
  *          <ul>
  *             <li>
  *                <p>
- *                   <code>language-code</code> or <code>identify-language</code>
+ *                   <code>language-code</code> or <code>identify-language</code> or <code>identify-multiple-language</code>
  *                </p>
  *             </li>
  *             <li>
@@ -115,6 +115,7 @@ export interface StartStreamTranscriptionCommandOutput extends StartStreamTransc
  *   IdentifyLanguage: true || false,
  *   LanguageOptions: "STRING_VALUE",
  *   PreferredLanguage: "en-US" || "en-GB" || "es-US" || "fr-CA" || "fr-FR" || "en-AU" || "it-IT" || "de-DE" || "pt-BR" || "ja-JP" || "ko-KR" || "zh-CN" || "hi-IN" || "th-TH",
+ *   IdentifyMultipleLanguages: true || false,
  *   VocabularyNames: "STRING_VALUE",
  *   VocabularyFilterNames: "STRING_VALUE",
  * };
@@ -205,6 +206,7 @@ export interface StartStreamTranscriptionCommandOutput extends StartStreamTransc
  * //   IdentifyLanguage: true || false,
  * //   LanguageOptions: "STRING_VALUE",
  * //   PreferredLanguage: "en-US" || "en-GB" || "es-US" || "fr-CA" || "fr-FR" || "en-AU" || "it-IT" || "de-DE" || "pt-BR" || "ja-JP" || "ko-KR" || "zh-CN" || "hi-IN" || "th-TH",
+ * //   IdentifyMultipleLanguages: true || false,
  * //   VocabularyNames: "STRING_VALUE",
  * //   VocabularyFilterNames: "STRING_VALUE",
  * // };

diff --git a/clients/client-transcribe-streaming/src/models/models_0.ts b/clients/client-transcribe-streaming/src/models/models_0.ts
@@ -2226,7 +2226,7 @@ export interface StartStreamTranscriptionRequest {
    *       enabled channel identification, automatic language identification identifies the dominant language on
    *       each audio channel.</p>
    *          <p>Note that you must include either <code>LanguageCode</code> or
-   *       <code>IdentifyLanguage</code> in your request. If you include both parameters, your request
+   *       <code>IdentifyLanguage</code> or <code>IdentifyMultipleLanguages</code> in your request. If you include more than one of these parameters, your transcription job
    *       fails.</p>
    *          <p>Streaming language identification can't be combined with custom language models or
    *       redaction.</p>
@@ -2260,6 +2260,15 @@ export interface StartStreamTranscriptionRequest {
    */
   PreferredLanguage?: LanguageCode;
 
+  /**
+   * @public
+   * <p>Enables automatic multi-language identification in your transcription job request. Use this parameter if your stream contains more than one language. If your stream contains only one language, use IdentifyLanguage instead.</p>
+   *          <p>If you include <code>IdentifyMultipleLanguages</code>, you can optionally include a list of language codes, using <code>LanguageOptions</code>, that you think may be present in your stream. Including <code>LanguageOptions</code> restricts <code>IdentifyMultipleLanguages</code> to only the language options that you specify, which can improve transcription accuracy.</p>
+   *          <p>If you want to apply a custom vocabulary or a custom vocabulary filter to your automatic multiple language identification request, include <code>VocabularyNames</code> or <code>VocabularyFilterNames</code>.</p>
+   *          <p>Note that you must include one of <code>LanguageCode</code>, <code>IdentifyLanguage</code>, or <code>IdentifyMultipleLanguages</code> in your request. If you include more than one of these parameters, your transcription job fails.</p>
+   */
+  IdentifyMultipleLanguages?: boolean;
+
   /**
    * @public
    * <p>Specify the names of the custom vocabularies that you want to use when processing your
@@ -2608,6 +2617,12 @@ export interface StartStreamTranscriptionResponse {
    */
   PreferredLanguage?: LanguageCode;
 
+  /**
+   * @public
+   * <p>Shows whether automatic multi-language identification was enabled for your transcription.</p>
+   */
+  IdentifyMultipleLanguages?: boolean;
+
   /**
    * @public
    * <p>Provides the names of the custom vocabularies that you specified in your request.</p>

diff --git a/clients/client-transcribe-streaming/src/protocols/Aws_restJson1.ts b/clients/client-transcribe-streaming/src/protocols/Aws_restJson1.ts
@@ -211,6 +211,10 @@ export const se_StartStreamTranscriptionCommand = async (
     ],
     "x-amzn-transcribe-language-options": input.LanguageOptions!,
     "x-amzn-transcribe-preferred-language": input.PreferredLanguage!,
+    "x-amzn-transcribe-identify-multiple-languages": [
+      () => isSerializableHeaderValue(input.IdentifyMultipleLanguages),
+      () => input.IdentifyMultipleLanguages!.toString(),
+    ],
     "x-amzn-transcribe-vocabulary-names": input.VocabularyNames!,
     "x-amzn-transcribe-vocabulary-filter-names": input.VocabularyFilterNames!,
   });
@@ -436,6 +440,10 @@ export const de_StartStreamTranscriptionCommand = async (
     ],
     LanguageOptions: [, output.headers["x-amzn-transcribe-language-options"]],
     PreferredLanguage: [, output.headers["x-amzn-transcribe-preferred-language"]],
+    IdentifyMultipleLanguages: [
+      () => void 0 !== output.headers["x-amzn-transcribe-identify-multiple-languages"],
+      () => __parseBoolean(output.headers["x-amzn-transcribe-identify-multiple-languages"]),
+    ],
     VocabularyNames: [, output.headers["x-amzn-transcribe-vocabulary-names"]],
     VocabularyFilterNames: [, output.headers["x-amzn-transcribe-vocabulary-filter-names"]],
   });

diff --git a/codegen/sdk-codegen/aws-models/transcribe-streaming.json b/codegen/sdk-codegen/aws-models/transcribe-streaming.json
@@ -1890,7 +1890,7 @@
         }
       ],
       "traits": {
-        "smithy.api#documentation": "<p>Starts a bidirectional HTTP/2 or WebSocket stream where audio is streamed to \n      Amazon Transcribe and the transcription results are streamed to your application.</p>\n         <p>The following parameters are required:</p>\n         <ul>\n            <li>\n               <p>\n                  <code>language-code</code> or <code>identify-language</code>\n               </p>\n            </li>\n            <li>\n               <p>\n                  <code>media-encoding</code>\n               </p>\n            </li>\n            <li>\n               <p>\n                  <code>sample-rate</code>\n               </p>\n            </li>\n         </ul>\n         <p>For more information on streaming with Amazon Transcribe, see <a href=\"https://docs.aws.amazon.com/transcribe/latest/dg/streaming.html\">Transcribing streaming audio</a>.</p>",
+        "smithy.api#documentation": "<p>Starts a bidirectional HTTP/2 or WebSocket stream where audio is streamed to \n      Amazon Transcribe and the transcription results are streamed to your application.</p>\n         <p>The following parameters are required:</p>\n         <ul>\n            <li>\n               <p>\n                  <code>language-code</code> or <code>identify-language</code> or <code>identify-multiple-language</code>\n               </p>\n            </li>\n            <li>\n               <p>\n                  <code>media-encoding</code>\n               </p>\n            </li>\n            <li>\n               <p>\n                  <code>sample-rate</code>\n               </p>\n            </li>\n         </ul>\n         <p>For more information on streaming with Amazon Transcribe, see <a href=\"https://docs.aws.amazon.com/transcribe/latest/dg/streaming.html\">Transcribing streaming audio</a>.</p>",
         "smithy.api#http": {
           "method": "POST",
           "uri": "/stream-transcription",
@@ -2030,7 +2030,7 @@
           "target": "com.amazonaws.transcribestreaming#Boolean",
           "traits": {
             "smithy.api#default": false,
-            "smithy.api#documentation": "<p>Enables automatic language identification for your transcription.</p>\n         <p>If you include <code>IdentifyLanguage</code>, you can optionally include a list of \n      language codes, using <code>LanguageOptions</code>, that you think may be present in \n      your audio stream. Including language options can improve transcription accuracy.</p>\n         <p>You can also include a preferred language using <code>PreferredLanguage</code>. Adding a \n      preferred language can help Amazon Transcribe identify the language faster than if you omit this \n      parameter.</p>\n         <p>If you have multi-channel audio that contains different languages on each channel, and you've \n      enabled channel identification, automatic language identification identifies the dominant language on \n      each audio channel.</p>\n         <p>Note that you must include either <code>LanguageCode</code> or \n      <code>IdentifyLanguage</code> in your request. If you include both parameters, your request\n      fails.</p>\n         <p>Streaming language identification can't be combined with custom language models or \n      redaction.</p>",
+            "smithy.api#documentation": "<p>Enables automatic language identification for your transcription.</p>\n         <p>If you include <code>IdentifyLanguage</code>, you can optionally include a list of \n      language codes, using <code>LanguageOptions</code>, that you think may be present in \n      your audio stream. Including language options can improve transcription accuracy.</p>\n         <p>You can also include a preferred language using <code>PreferredLanguage</code>. Adding a \n      preferred language can help Amazon Transcribe identify the language faster than if you omit this \n      parameter.</p>\n         <p>If you have multi-channel audio that contains different languages on each channel, and you've \n      enabled channel identification, automatic language identification identifies the dominant language on \n      each audio channel.</p>\n         <p>Note that you must include either <code>LanguageCode</code> or \n      <code>IdentifyLanguage</code> or <code>IdentifyMultipleLanguages</code> in your request. If you include more than one of these parameters, your transcription job\n      fails.</p>\n         <p>Streaming language identification can't be combined with custom language models or \n      redaction.</p>",
             "smithy.api#httpHeader": "x-amzn-transcribe-identify-language"
           }
         },
@@ -2048,6 +2048,14 @@
             "smithy.api#httpHeader": "x-amzn-transcribe-preferred-language"
           }
         },
+        "IdentifyMultipleLanguages": {
+          "target": "com.amazonaws.transcribestreaming#Boolean",
+          "traits": {
+            "smithy.api#default": false,
+            "smithy.api#documentation": "<p>Enables automatic multi-language identification in your transcription job request. Use this parameter if your stream contains more than one language. If your stream contains only one language, use IdentifyLanguage instead.</p>\n         <p>If you include <code>IdentifyMultipleLanguages</code>, you can optionally include a list of language codes, using <code>LanguageOptions</code>, that you think may be present in your stream. Including <code>LanguageOptions</code> restricts <code>IdentifyMultipleLanguages</code> to only the language options that you specify, which can improve transcription accuracy.</p>\n         <p>If you want to apply a custom vocabulary or a custom vocabulary filter to your automatic multiple language identification request, include <code>VocabularyNames</code> or <code>VocabularyFilterNames</code>.</p>\n         <p>Note that you must include one of <code>LanguageCode</code>, <code>IdentifyLanguage</code>, or <code>IdentifyMultipleLanguages</code> in your request. If you include more than one of these parameters, your transcription job fails.</p>",
+            "smithy.api#httpHeader": "x-amzn-transcribe-identify-multiple-languages"
+          }
+        },
         "VocabularyNames": {
           "target": "com.amazonaws.transcribestreaming#VocabularyNames",
           "traits": {
@@ -2221,6 +2229,14 @@
             "smithy.api#httpHeader": "x-amzn-transcribe-preferred-language"
           }
         },
+        "IdentifyMultipleLanguages": {
+          "target": "com.amazonaws.transcribestreaming#Boolean",
+          "traits": {
+            "smithy.api#default": false,
+            "smithy.api#documentation": "<p>Shows whether automatic multi-language identification was enabled for your transcription.</p>",
+            "smithy.api#httpHeader": "x-amzn-transcribe-identify-multiple-languages"
+          }
+        },
         "VocabularyNames": {
           "target": "com.amazonaws.transcribestreaming#VocabularyNames",
           "traits": {