fix!: correct long audio synthesis HTTP binding

Google APIs · copybara-github · commit 8681efd97b8e · 2024-01-02T10:56:40.000-08:00
docs: Deprecate the custom voice usage field

PiperOrigin-RevId: 595159412
diff --git a/google/cloud/texttospeech/v1beta1/cloud_tts.proto b/google/cloud/texttospeech/v1beta1/cloud_tts.proto
@@ -1,4 +1,4 @@
-// Copyright 2022 Google LLC
+// Copyright 2023 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -37,7 +37,8 @@ option (google.api.resource_definition) = {
 // Service that implements Google Cloud Text-to-Speech API.
 service TextToSpeech {
   option (google.api.default_host) = "texttospeech.googleapis.com";
-  option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";
+  option (google.api.oauth_scopes) =
+      "https://www.googleapis.com/auth/cloud-platform";
 
   // Returns a list of Voice supported for synthesis.
   rpc ListVoices(ListVoicesRequest) returns (ListVoicesResponse) {
@@ -49,7 +50,8 @@ service TextToSpeech {
 
   // Synthesizes speech synchronously: receive results after all text input
   // has been processed.
-  rpc SynthesizeSpeech(SynthesizeSpeechRequest) returns (SynthesizeSpeechResponse) {
+  rpc SynthesizeSpeech(SynthesizeSpeechRequest)
+      returns (SynthesizeSpeechResponse) {
     option (google.api.http) = {
       post: "/v1beta1/text:synthesize"
       body: "*"
@@ -81,7 +83,8 @@ enum SsmlVoiceGender {
 // Configuration to set up audio encoder. The encoding determines the output
 // audio format that we'd like.
 enum AudioEncoding {
-  // Not specified. Will return result [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
+  // Not specified. Will return result
+  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
   AUDIO_ENCODING_UNSPECIFIED = 0;
 
   // Uncompressed 16-bit signed little-endian samples (Linear PCM).
@@ -171,8 +174,8 @@ message SynthesizeSpeechRequest {
 
 // Contains text input to be synthesized. Either `text` or `ssml` must be
 // supplied. Supplying both or neither returns
-// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. The input size is limited to 5000
-// bytes.
+// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. The
+// input size is limited to 5000 bytes.
 message SynthesisInput {
   // The input source, which is either plain text or SSML.
   oneof input_source {
@@ -181,17 +184,18 @@ message SynthesisInput {
 
     // 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][google.rpc.Code.INVALID_ARGUMENT]. For more information, see
+    // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. For
+    // more information, see
     // [SSML](https://cloud.google.com/text-to-speech/docs/ssml).
     string ssml = 2;
   }
 }
 
 // Description of which voice to use for a synthesis request.
 message VoiceSelectionParams {
-  // Required. The language (and potentially also the region) of the voice expressed as a
-  // [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag, e.g.
-  // "en-US". This should not include a script tag (e.g. use
+  // Required. The language (and potentially also the region) of the voice
+  // expressed as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
+  // language tag, e.g. "en-US". This should not include a script tag (e.g. use
   // "cmn-cn" rather than "cmn-Hant-cn"), because the script will be inferred
   // from the input provided in the SynthesisInput.  The TTS service
   // will use this parameter to help choose an appropriate voice.  Note that
@@ -277,9 +281,8 @@ message AudioConfig {
 
 // Description of the custom voice to be synthesized.
 message CustomVoiceParams {
-  // The usage of the synthesized audio. You must report your honest and
-  // correct usage of the service as it's regulated by contract and will cause
-  // significant difference in billing.
+  // Deprecated. The usage of the synthesized audio. Usage does not affect
+  // billing.
   enum ReportedUsage {
     // Request with reported usage unspecified will be rejected.
     REPORTED_USAGE_UNSPECIFIED = 0;
@@ -297,13 +300,12 @@ message CustomVoiceParams {
   // Required. The name of the AutoML model that synthesizes the custom voice.
   string model = 1 [
     (google.api.field_behavior) = REQUIRED,
-    (google.api.resource_reference) = {
-      type: "automl.googleapis.com/Model"
-    }
+    (google.api.resource_reference) = { type: "automl.googleapis.com/Model" }
   ];
 
-  // Optional. The usage of the synthesized audio to be reported.
-  ReportedUsage reported_usage = 3 [(google.api.field_behavior) = OPTIONAL];
+  // Optional. Deprecated. The usage of the synthesized audio to be reported.
+  ReportedUsage reported_usage = 3
+      [deprecated = true, (google.api.field_behavior) = OPTIONAL];
 }
 
 // The message returned to the client by the `SynthesizeSpeech` method.
diff --git a/google/cloud/texttospeech/v1beta1/cloud_tts_lrs.proto b/google/cloud/texttospeech/v1beta1/cloud_tts_lrs.proto
@@ -1,4 +1,4 @@
-// Copyright 2022 Google LLC
+// Copyright 2023 Google LLC
 //
 // Licensed under the Apache License, Version 2.0 (the "License");
 // you may not use this file except in compliance with the License.
@@ -42,12 +42,12 @@ service TextToSpeechLongAudioSynthesize {
   rpc SynthesizeLongAudio(SynthesizeLongAudioRequest)
       returns (google.longrunning.Operation) {
     option (google.api.http) = {
-      post: "/v1beta1/{parent=projects/*/locations/*/voices/*}:SynthesizeLongAudio"
+      post: "/v1beta1/{parent=projects/*/locations/*}:synthesizeLongAudio"
       body: "*"
     };
     option (google.longrunning.operation_info) = {
-      response_type: "SynthesizeLongAudioResponse"
-      metadata_type: "SynthesizeLongAudioMetadata"
+      response_type: "google.cloud.texttospeech.v1beta1.SynthesizeLongAudioResponse"
+      metadata_type: "google.cloud.texttospeech.v1beta1.SynthesizeLongAudioMetadata"
     };
   }
 }
@@ -83,8 +83,8 @@ message SynthesizeLongAudioMetadata {
   // Time when the request was received.
   google.protobuf.Timestamp start_time = 1;
 
-  // Time of the most recent processing update.
-  google.protobuf.Timestamp last_update_time = 2;
+  // Deprecated. Do not use.
+  google.protobuf.Timestamp last_update_time = 2 [deprecated = true];
 
   // The progress of the most recent processing update in percentage, ie. 70.0%.
   double progress_percentage = 3;
diff --git a/google/cloud/texttospeech/v1beta1/texttospeech_v1beta1.yaml b/google/cloud/texttospeech/v1beta1/texttospeech_v1beta1.yaml
@@ -8,6 +8,9 @@ apis:
 - name: google.cloud.texttospeech.v1beta1.TextToSpeechLongAudioSynthesize
 - name: google.longrunning.Operations
 
+types:
+- name: google.cloud.texttospeech.v1beta1.SynthesizeLongAudioMetadata
+
 documentation:
   summary: |-
     Synthesizes natural-sounding speech by applying powerful neural network
@@ -17,6 +20,13 @@ documentation:
 
     Google Cloud Text-to-Speech API provides speech synthesis as a service.
 
+http:
+  rules:
+  - selector: google.longrunning.Operations.GetOperation
+    get: '/v1beta1/{name=projects/*/locations/*/operations/*}'
+  - selector: google.longrunning.Operations.ListOperations
+    get: '/v1beta1/{name=projects/*/locations/*}/operations'
+
 authentication:
   rules:
   - selector: google.cloud.texttospeech.v1beta1.TextToSpeech.ListVoices
