feat(client-polly): Add new engine - generative - that builds the mos…

…t expressive conversational voices.
aws · May 8, 2024 · daf6bd4 · daf6bd4
1 parent 711a8ff
commit daf6bd4
Show file tree

Hide file tree

Showing 7 changed files with 47 additions and 58 deletions.
diff --git a/clients/client-polly/src/commands/DescribeVoicesCommand.ts b/clients/client-polly/src/commands/DescribeVoicesCommand.ts
@@ -50,7 +50,7 @@ export interface DescribeVoicesCommandOutput extends DescribeVoicesOutput, __Met
  * // const { PollyClient, DescribeVoicesCommand } = require("@aws-sdk/client-polly"); // CommonJS import
  * const client = new PollyClient(config);
  * const input = { // DescribeVoicesInput
- *   Engine: "standard" || "neural" || "long-form",
+ *   Engine: "standard" || "neural" || "long-form" || "generative",
  *   LanguageCode: "arb" || "cmn-CN" || "cy-GB" || "da-DK" || "de-DE" || "en-AU" || "en-GB" || "en-GB-WLS" || "en-IN" || "en-US" || "es-ES" || "es-MX" || "es-US" || "fr-CA" || "fr-FR" || "is-IS" || "it-IT" || "ja-JP" || "hi-IN" || "ko-KR" || "nb-NO" || "nl-NL" || "pl-PL" || "pt-BR" || "pt-PT" || "ro-RO" || "ru-RU" || "sv-SE" || "tr-TR" || "en-NZ" || "en-ZA" || "ca-ES" || "de-AT" || "yue-CN" || "ar-AE" || "fi-FI" || "en-IE" || "nl-BE" || "fr-BE",
  *   IncludeAdditionalLanguageCodes: true || false,
  *   NextToken: "STRING_VALUE",
@@ -69,7 +69,7 @@ export interface DescribeVoicesCommandOutput extends DescribeVoicesOutput, __Met
  * //         "arb" || "cmn-CN" || "cy-GB" || "da-DK" || "de-DE" || "en-AU" || "en-GB" || "en-GB-WLS" || "en-IN" || "en-US" || "es-ES" || "es-MX" || "es-US" || "fr-CA" || "fr-FR" || "is-IS" || "it-IT" || "ja-JP" || "hi-IN" || "ko-KR" || "nb-NO" || "nl-NL" || "pl-PL" || "pt-BR" || "pt-PT" || "ro-RO" || "ru-RU" || "sv-SE" || "tr-TR" || "en-NZ" || "en-ZA" || "ca-ES" || "de-AT" || "yue-CN" || "ar-AE" || "fi-FI" || "en-IE" || "nl-BE" || "fr-BE",
  * //       ],
  * //       SupportedEngines: [ // EngineList
- * //         "standard" || "neural" || "long-form",
+ * //         "standard" || "neural" || "long-form" || "generative",
  * //       ],
  * //     },
  * //   ],

diff --git a/clients/client-polly/src/commands/GetSpeechSynthesisTaskCommand.ts b/clients/client-polly/src/commands/GetSpeechSynthesisTaskCommand.ts
@@ -44,7 +44,7 @@ export interface GetSpeechSynthesisTaskCommandOutput extends GetSpeechSynthesisT
  * const response = await client.send(command);
  * // { // GetSpeechSynthesisTaskOutput
  * //   SynthesisTask: { // SynthesisTask
- * //     Engine: "standard" || "neural" || "long-form",
+ * //     Engine: "standard" || "neural" || "long-form" || "generative",
  * //     TaskId: "STRING_VALUE",
  * //     TaskStatus: "scheduled" || "inProgress" || "completed" || "failed",
  * //     TaskStatusReason: "STRING_VALUE",

diff --git a/clients/client-polly/src/commands/ListSpeechSynthesisTasksCommand.ts b/clients/client-polly/src/commands/ListSpeechSynthesisTasksCommand.ts
@@ -47,7 +47,7 @@ export interface ListSpeechSynthesisTasksCommandOutput extends ListSpeechSynthes
  * //   NextToken: "STRING_VALUE",
  * //   SynthesisTasks: [ // SynthesisTasks
  * //     { // SynthesisTask
- * //       Engine: "standard" || "neural" || "long-form",
+ * //       Engine: "standard" || "neural" || "long-form" || "generative",
  * //       TaskId: "STRING_VALUE",
  * //       TaskStatus: "scheduled" || "inProgress" || "completed" || "failed",
  * //       TaskStatusReason: "STRING_VALUE",

diff --git a/clients/client-polly/src/commands/StartSpeechSynthesisTaskCommand.ts b/clients/client-polly/src/commands/StartSpeechSynthesisTaskCommand.ts
@@ -44,7 +44,7 @@ export interface StartSpeechSynthesisTaskCommandOutput extends StartSpeechSynthe
  * // const { PollyClient, StartSpeechSynthesisTaskCommand } = require("@aws-sdk/client-polly"); // CommonJS import
  * const client = new PollyClient(config);
  * const input = { // StartSpeechSynthesisTaskInput
- *   Engine: "standard" || "neural" || "long-form",
+ *   Engine: "standard" || "neural" || "long-form" || "generative",
  *   LanguageCode: "arb" || "cmn-CN" || "cy-GB" || "da-DK" || "de-DE" || "en-AU" || "en-GB" || "en-GB-WLS" || "en-IN" || "en-US" || "es-ES" || "es-MX" || "es-US" || "fr-CA" || "fr-FR" || "is-IS" || "it-IT" || "ja-JP" || "hi-IN" || "ko-KR" || "nb-NO" || "nl-NL" || "pl-PL" || "pt-BR" || "pt-PT" || "ro-RO" || "ru-RU" || "sv-SE" || "tr-TR" || "en-NZ" || "en-ZA" || "ca-ES" || "de-AT" || "yue-CN" || "ar-AE" || "fi-FI" || "en-IE" || "nl-BE" || "fr-BE",
  *   LexiconNames: [ // LexiconNameList
  *     "STRING_VALUE",
@@ -65,7 +65,7 @@ export interface StartSpeechSynthesisTaskCommandOutput extends StartSpeechSynthe
  * const response = await client.send(command);
  * // { // StartSpeechSynthesisTaskOutput
  * //   SynthesisTask: { // SynthesisTask
- * //     Engine: "standard" || "neural" || "long-form",
+ * //     Engine: "standard" || "neural" || "long-form" || "generative",
  * //     TaskId: "STRING_VALUE",
  * //     TaskStatus: "scheduled" || "inProgress" || "completed" || "failed",
  * //     TaskStatusReason: "STRING_VALUE",

diff --git a/clients/client-polly/src/commands/SynthesizeSpeechCommand.ts b/clients/client-polly/src/commands/SynthesizeSpeechCommand.ts
@@ -45,7 +45,7 @@ export interface SynthesizeSpeechCommandOutput extends Omit<SynthesizeSpeechOutp
  * // const { PollyClient, SynthesizeSpeechCommand } = require("@aws-sdk/client-polly"); // CommonJS import
  * const client = new PollyClient(config);
  * const input = { // SynthesizeSpeechInput
- *   Engine: "standard" || "neural" || "long-form",
+ *   Engine: "standard" || "neural" || "long-form" || "generative",
  *   LanguageCode: "arb" || "cmn-CN" || "cy-GB" || "da-DK" || "de-DE" || "en-AU" || "en-GB" || "en-GB-WLS" || "en-IN" || "en-US" || "es-ES" || "es-MX" || "es-US" || "fr-CA" || "fr-FR" || "is-IS" || "it-IT" || "ja-JP" || "hi-IN" || "ko-KR" || "nb-NO" || "nl-NL" || "pl-PL" || "pt-BR" || "pt-PT" || "ro-RO" || "ru-RU" || "sv-SE" || "tr-TR" || "en-NZ" || "en-ZA" || "ca-ES" || "de-AT" || "yue-CN" || "ar-AE" || "fi-FI" || "en-IE" || "nl-BE" || "fr-BE",
  *   LexiconNames: [ // LexiconNameList
  *     "STRING_VALUE",

diff --git a/clients/client-polly/src/models/models_0.ts b/clients/client-polly/src/models/models_0.ts
@@ -71,6 +71,7 @@ export class ServiceFailureException extends __BaseException {
  * @enum
  */
 export const Engine = {
+  GENERATIVE: "generative",
   LONG_FORM: "long-form",
   NEURAL: "neural",
   STANDARD: "standard",
@@ -137,9 +138,9 @@ export type LanguageCode = (typeof LanguageCode)[keyof typeof LanguageCode];
  */
 export interface DescribeVoicesInput {
   /**
-   * <p>Specifies the engine (<code>standard</code>, <code>neural</code> or
-   *       <code>long-form</code>) used by Amazon Polly when processing input text for
-   *       speech synthesis. </p>
+   * <p>Specifies the engine (<code>standard</code>, <code>neural</code>,
+   *       <code>long-form</code> or <code>generative</code>) used by Amazon Polly when
+   *       processing input text for speech synthesis. </p>
    * @public
    */
   Engine?: Engine;
@@ -345,8 +346,8 @@ export interface Voice {
   AdditionalLanguageCodes?: LanguageCode[];
 
   /**
-   * <p>Specifies which engines (<code>standard</code>, <code>neural</code> or
-   *       <code>long-form</code>) are supported by a given voice.</p>
+   * <p>Specifies which engines (<code>standard</code>, <code>neural</code>,
+   *       <code>long-form</code> or <code>generative</code>) are supported by a given voice.</p>
    * @public
    */
   SupportedEngines?: Engine[];
@@ -592,10 +593,10 @@ export type TextType = (typeof TextType)[keyof typeof TextType];
  */
 export interface SynthesisTask {
   /**
-   * <p>Specifies the engine (<code>standard</code>, <code>neural</code> or
-   *       <code>long-form</code>) for Amazon Polly to use when processing input text for
-   *       speech synthesis. Using a voice that is not supported for the engine
-   *       selected will result in an error.</p>
+   * <p>Specifies the engine (<code>standard</code>, <code>neural</code>,
+   *       <code>long-form</code> or <code>generative</code>) for Amazon Polly to use
+   *       when processing input text for speech synthesis. Using a voice that
+   *       is not supported for the engine selected will result in an error.</p>
    * @public
    */
   Engine?: Engine;
@@ -665,7 +666,7 @@ export interface SynthesisTask {
    *          <p>The valid values for mp3 and ogg_vorbis are "8000", "16000", "22050",
    *       and "24000". The default value for standard voices is "22050". The default
    *       value for neural voices is "24000". The default value for long-form voices
-   *       is "24000".</p>
+   *       is "24000". The default value for generative voices is "24000".</p>
    *          <p>Valid values for pcm are "8000" and "16000" The default value is
    *       "16000". </p>
    * @public
@@ -1180,10 +1181,10 @@ export class SsmlMarksNotSupportedForTextTypeException extends __BaseException {
  */
 export interface StartSpeechSynthesisTaskInput {
   /**
-   * <p>Specifies the engine (<code>standard</code>, <code>neural</code> or
-   *       <code>long-form</code>) for Amazon Polly to use when processing input text for
-   *       speech synthesis. Using a voice that is not supported for the engine
-   *       selected will result in an error.</p>
+   * <p>Specifies the engine (<code>standard</code>, <code>neural</code>,
+   *       <code>long-form</code> or <code>generative</code>) for Amazon Polly to use
+   *       when processing input text for speech synthesis. Using a voice that
+   *       is not supported for the engine selected will result in an error.</p>
    * @public
    */
   Engine?: Engine;
@@ -1234,7 +1235,7 @@ export interface StartSpeechSynthesisTaskInput {
    *          <p>The valid values for mp3 and ogg_vorbis are "8000", "16000", "22050",
    *       and "24000". The default value for standard voices is "22050". The default
    *       value for neural voices is "24000". The default value for long-form voices
-   *       is "24000".</p>
+   *       is "24000". The default value for generative voices is "24000".</p>
    *          <p>Valid values for pcm are "8000" and "16000" The default value is
    *       "16000". </p>
    * @public
@@ -1318,36 +1319,18 @@ export class TextLengthExceededException extends __BaseException {
  */
 export interface SynthesizeSpeechInput {
   /**
-   * <p>Specifies the engine (<code>standard</code>, <code>neural</code> or
-   *       <code>long-form</code>) for Amazon Polly to use when processing input text for
-   *       speech synthesis. For information on Amazon Polly voices and which voices are
-   *       available for each engine, see <a href="https://docs.aws.amazon.com/polly/latest/dg/voicelist.html">Available Voices</a>.</p>
-   *          <p>
-   *             <b>NTTS-only voices</b>
-   *          </p>
-   *          <p>When using NTTS-only voices such as Kevin (en-US), this parameter is
-   *       required and must be set to <code>neural</code>. If the engine is not
-   *       specified, or is set to <code>standard</code>, this will result in an
-   *       error. </p>
-   *          <p>
-   *             <b>long-form-only voices</b>
-   *          </p>
-   *          <p>When using long-form-only voices such as Danielle (en-US), this
-   *       parameter is required and must be set to <code>long-form</code>. If the
-   *       engine is not specified, or is set to <code>standard</code> or
-   *       <code>neural</code>, this will result in an error. </p>
+   * <p>Specifies the engine (<code>standard</code>, <code>neural</code>,
+   *       <code>long-form</code>, or <code>generative</code>) for Amazon Polly
+   *       to use when processing input text for speech synthesis. Provide an engine
+   *       that is supported by the voice you select. If you don't provide an engine,
+   *       the standard engine is selected by default. If a chosen voice isn't supported
+   *       by the standard engine, this will result in an error. For information on
+   *       Amazon Polly voices and which voices are available for each engine, see <a href="https://docs.aws.amazon.com/polly/latest/dg/voicelist.html">Available Voices</a>.</p>
    *          <p>Type: String</p>
    *          <p>Valid Values: <code>standard</code> | <code>neural</code> |
-   *       <code>long-form</code>
+   *       <code>long-form</code> | <code>generative</code>
    *          </p>
    *          <p>Required: Yes</p>
-   *          <p>
-   *             <b>Standard voices</b>
-   *          </p>
-   *          <p>For standard voices, this is not required; the engine parameter
-   *       defaults to <code>standard</code>. If the engine is not specified, or is
-   *       set to <code>standard</code> and an NTTS-only voice is selected, this will
-   *       result in an error. </p>
    * @public
    */
   Engine?: Engine;
@@ -1389,7 +1372,7 @@ export interface SynthesizeSpeechInput {
    *          <p>The valid values for mp3 and ogg_vorbis are "8000", "16000", "22050",
    *       and "24000". The default value for standard voices is "22050". The default
    *       value for neural voices is "24000". The default value for long-form voices
-   *       is "24000".</p>
+   *       is "24000". The default value for generative voices is "24000".</p>
    *          <p>Valid values for pcm are "8000" and "16000" The default value is
    *       "16000". </p>
    * @public