@maxim_mazurok/gapi.client.texttospeech-v1beta1 - npm Package Compare versions

Comparing version 0.0.20240925 to 0.0.20241001

index.d.ts

@@ -12,3 +12,3 @@ /* Type definitions for non-npm package Cloud Text-to-Speech API v1beta1 0.0 */
 // Generated from: https://texttospeech.googleapis.com/$discovery/rest?version=v1beta1
-// Revision: 20240925
+// Revision: 20241001
 
@@ -32,2 +32,6 @@ /// <reference types="gapi.client" />
   namespace texttospeech {
+    interface AdvancedVoiceOptions {
+      /** Only for Jounrney voices. If false, the synthesis will be context aware and have higher latency. */
+      lowLatencyJourneySynthesis?: boolean;
+    }
     interface AudioConfig {
@@ -47,2 +51,14 @@ /** Required. The format of the audio byte stream. */
     }
+    interface CustomPronunciationParams {
+      /** The phonetic encoding of the phrase. */
+      phoneticEncoding?: string;
+      /** The phrase to which the customization will be applied. The phrase can be multiple words (in the case of proper nouns etc), but should not span to a whole sentence. */
+      phrase?: string;
+      /** The pronunciation of the phrase. This must be in the phonetic encoding specified above. */
+      pronunciation?: string;
+    }
+    interface CustomPronunciations {
+      /** The pronunciation customizations to be applied. */
+      pronunciations?: CustomPronunciationParams[];
+    }
     interface CustomVoiceParams {
@@ -54,2 +70,16 @@ /** Required. The name of the AutoML model that synthesizes the custom voice. */
     }
+    interface GenerateVoiceCloningKeyRequest {
+      /** Required. The script used for the voice talent statement. The script will be provided to the caller through other channels. It must be returned unchanged in this field. */
+      consentScript?: string;
+      /** Required. The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: "en-US". See [Language Support](https://cloud.google.com/speech-to-text/docs/languages) for a list of the currently supported language codes. */
+      languageCode?: string;
+      /** Required. The training audio used to create voice clone. This is currently limited to LINEAR16 PCM WAV files mono audio with 24khz sample rate. This needs to be specified in [InputAudio.audio_config], other values will be explicitly rejected. */
+      referenceAudio?: InputAudio;
+      /** Required. The voice talent audio used to verify consent to voice clone. */
+      voiceTalentConsent?: InputAudio;
+    }
+    interface GenerateVoiceCloningKeyResponse {
+      /** The voice clone key. Use it in the SynthesizeSpeechRequest by setting [voice.voice_clone.voice_cloning_key]. */
+      voiceCloningKey?: string;
+    }
     interface GoogleCloudTexttospeechV1beta1SynthesizeLongAudioMetadata {
@@ -63,2 +93,14 @@ /** Deprecated. Do not use. */
     }
+    interface InputAudio {
+      /** Required. Provides information that specifies how to process content. */
+      audioConfig?: InputAudioConfig;
+      /** Required. The audio data bytes encoded as specified in `InputAudioConfig`. Note: as with all bytes fields, proto buffers use a pure binary representation, whereas JSON representations use base64. Audio samples should be between 5-25 seconds in length. */
+      content?: string;
+    }
+    interface InputAudioConfig {
+      /** Required. The format of the audio byte stream. */
+      audioEncoding?: string;
+      /** Required. The sample rate (in hertz) for this audio. */
+      sampleRateHertz?: number;
+    }
     interface ListOperationsResponse {
@@ -95,2 +137,4 @@ /** The standard List next-page token. */
     interface SynthesisInput {
+      /** Optional. The pronunciation customizations to be applied to the input. If this is set, the input will be synthesized using the given pronunciation customizations. The initial support will be for EFIGS (English, French, Italian, German, Spanish) languages, as provided in VoiceSelectionParams. Journey and Instant Clone voices are not supported yet. In order to customize the pronunciation of a phrase, there must be an exact match of the phrase in the input types. If using SSML, the phrase must not be inside a phoneme tag (entirely or partially). */
+      customPronunciations?: CustomPronunciations;
       /** The SSML document to be synthesized. The SSML document must be valid and well-formed. Otherwise the RPC will fail and return google.rpc.Code.INVALID_ARGUMENT. For more information, see [SSML](https://cloud.google.com/text-to-speech/docs/ssml). */
@@ -120,2 +164,4 @@ ssml?: string;
     interface SynthesizeSpeechRequest {
+      /** Adnanced voice options. */
+      advancedVoiceOptions?: AdvancedVoiceOptions;
       /** Required. The configuration of the synthesized audio. */
@@ -154,2 +200,6 @@ audioConfig?: AudioConfig;
     }
+    interface VoiceCloneParams {
+      /** Required. Created by GenerateVoiceCloningKey. */
+      voiceCloningKey?: string;
+    }
     interface VoiceSelectionParams {
@@ -164,2 +214,4 @@ /** The configuration for a custom voice. If [CustomVoiceParams.model] is set, the service will choose the custom voice matching the specified configuration. */
       ssmlGender?: string;
+      /** Optional. The configuration for a voice clone. If [VoiceCloneParams.voice_clone_key] is set, the service will choose the voice clone matching the specified configuration. */
+      voiceClone?: VoiceCloneParams;
     }
@@ -349,2 +401,56 @@ interface OperationsResource {
     interface VoicesResource {
+      /** Generates voice clone key given a short voice prompt. This method validates the voice prompts with a series of checks against the voice talent statement to verify the voice clone is safe to generate. */
+      generateVoiceCloningKey(request: {
+        /** V1 error format. */
+        '$.xgafv'?: string;
+        /** OAuth access token. */
+        access_token?: string;
+        /** Data format for response. */
+        alt?: string;
+        /** JSONP */
+        callback?: string;
+        /** Selector specifying which fields to include in a partial response. */
+        fields?: string;
+        /** API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token. */
+        key?: string;
+        /** OAuth 2.0 token for the current user. */
+        oauth_token?: string;
+        /** Returns response with indentations and line breaks. */
+        prettyPrint?: boolean;
+        /** Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters. */
+        quotaUser?: string;
+        /** Upload protocol for media (e.g. "raw", "multipart"). */
+        upload_protocol?: string;
+        /** Legacy upload protocol for media (e.g. "media", "multipart"). */
+        uploadType?: string;
+        /** Request body */
+        resource: GenerateVoiceCloningKeyRequest;
+      }): Request<GenerateVoiceCloningKeyResponse>;
+      generateVoiceCloningKey(
+        request: {
+          /** V1 error format. */
+          '$.xgafv'?: string;
+          /** OAuth access token. */
+          access_token?: string;
+          /** Data format for response. */
+          alt?: string;
+          /** JSONP */
+          callback?: string;
+          /** Selector specifying which fields to include in a partial response. */
+          fields?: string;
+          /** API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token. */
+          key?: string;
+          /** OAuth 2.0 token for the current user. */
+          oauth_token?: string;
+          /** Returns response with indentations and line breaks. */
+          prettyPrint?: boolean;
+          /** Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters. */
+          quotaUser?: string;
+          /** Upload protocol for media (e.g. "raw", "multipart"). */
+          upload_protocol?: string;
+          /** Legacy upload protocol for media (e.g. "media", "multipart"). */
+          uploadType?: string;
+        },
+        body: GenerateVoiceCloningKeyRequest
+      ): Request<GenerateVoiceCloningKeyResponse>;
       /** Returns a list of Voice supported for synthesis. */
@@ -351,0 +457,0 @@ list(request?: {

package.json

 {
   "name": "@maxim_mazurok/gapi.client.texttospeech-v1beta1",
-  "version": "0.0.20240925",
+  "version": "0.0.20241001",
   "description": "TypeScript typings for Cloud Text-to-Speech API v1beta1",
@@ -5,0 +5,0 @@ "repository": {

readme.md

@@ -78,2 +78,7 @@ # TypeScript typings for Cloud Text-to-Speech API v1beta1
 /*
+Generates voice clone key given a short voice prompt. This method validates the voice prompts with a series of checks against the voice talent statement to verify the voice clone is safe to generate.
+*/
+await gapi.client.texttospeech.voices.generateVoiceCloningKey({});
+
+/*
 Returns a list of Voice supported for synthesis.
@@ -80,0 +85,0 @@ */

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

31187

increased by27.99%

Lines of code

484

increased by28.38%

Number of lines in readme file

87

increased by6.1%

No dependency changes