// Copyright 2024 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

syntax = "proto3";

package google.cloud.texttospeech.v1;

import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";
import "google/cloud/texttospeech/v1/cloud_tts.proto";
import "google/longrunning/operations.proto";
import "google/protobuf/timestamp.proto";

option cc_enable_arenas = true;
option csharp_namespace = "Google.Cloud.TextToSpeech.V1";
option go_package = "cloud.google.com/go/texttospeech/apiv1/texttospeechpb;texttospeechpb";
option java_multiple_files = true;
option java_outer_classname = "TextToSpeechLongAudioSynthesisProto";
option java_package = "com.google.cloud.texttospeech.v1";
option php_namespace = "Google\\Cloud\\TextToSpeech\\V1";
option ruby_package = "Google::Cloud::TextToSpeech::V1";

// Service that implements Google Cloud Text-to-Speech API.
service TextToSpeechLongAudioSynthesize {
  option (google.api.default_host) = "texttospeech.googleapis.com";
  option (google.api.oauth_scopes) =
      "https://www.googleapis.com/auth/cloud-platform";

  // Synthesizes long form text asynchronously.
  rpc SynthesizeLongAudio(SynthesizeLongAudioRequest)
      returns (google.longrunning.Operation) {
    option (google.api.http) = {
      post: "/v1/{parent=projects/*/locations/*}:synthesizeLongAudio"
      body: "*"
    };
    option (google.longrunning.operation_info) = {
      response_type: "google.cloud.texttospeech.v1.SynthesizeLongAudioResponse"
      metadata_type: "google.cloud.texttospeech.v1.SynthesizeLongAudioMetadata"
    };
  }
}

// The top-level message sent by the client for the
// `SynthesizeLongAudio` method.
message SynthesizeLongAudioRequest {
  // The resource states of the request in the form of
  // `projects/*/locations/*`.
  string parent = 1;

  // Required. The Synthesizer requires either plain text or SSML as input.
  // While Long Audio is in preview, SSML is temporarily unsupported.
  SynthesisInput input = 2 [(google.api.field_behavior) = REQUIRED];

  // Required. The configuration of the synthesized audio.
  AudioConfig audio_config = 3 [(google.api.field_behavior) = REQUIRED];

  // Required. Specifies a Cloud Storage URI for the synthesis results. Must be
  // specified in the format: `gs://bucket_name/object_name`, and the bucket
  // must already exist.
  string output_gcs_uri = 4 [(google.api.field_behavior) = REQUIRED];

  // Required. The desired voice of the synthesized audio.
  VoiceSelectionParams voice = 5 [(google.api.field_behavior) = REQUIRED];
}

// The message returned to the client by the `SynthesizeLongAudio` method.
message SynthesizeLongAudioResponse {}

// Metadata for response returned by the `SynthesizeLongAudio` method.
message SynthesizeLongAudioMetadata {
  // Time when the request was received.
  google.protobuf.Timestamp start_time = 1;

  // 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;
}