xref: /aosp_15_r20/external/google-cloud-java/java-dialogflow-cx/proto-google-cloud-dialogflow-cx-v3/src/main/proto/google/cloud/dialogflow/cx/v3/audio_config.proto (revision 55e87721aa1bc457b326496a7ca40f3ea1a63287)

// 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.
// 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.dialogflow.cx.v3;

import "google/api/field_behavior.proto";
import "google/api/resource.proto";
import "google/protobuf/duration.proto";

option cc_enable_arenas = true;
option csharp_namespace = "Google.Cloud.Dialogflow.Cx.V3";
option go_package = "cloud.google.com/go/dialogflow/cx/apiv3/cxpb;cxpb";
option java_multiple_files = true;
option java_outer_classname = "AudioConfigProto";
option java_package = "com.google.cloud.dialogflow.cx.v3";
option objc_class_prefix = "DF";
option ruby_package = "Google::Cloud::Dialogflow::CX::V3";
option (google.api.resource_definition) = {
  type: "automl.googleapis.com/Model"
  pattern: "projects/{project}/locations/{location}/models/{model}"
};

// Audio encoding of the audio content sent in the conversational query request.
// Refer to the
// [Cloud Speech API
// documentation](https://cloud.google.com/speech-to-text/docs/basics) for more
// details.
enum AudioEncoding {
  // Not specified.
  AUDIO_ENCODING_UNSPECIFIED = 0;

  // Uncompressed 16-bit signed little-endian samples (Linear PCM).
  AUDIO_ENCODING_LINEAR_16 = 1;

  // [`FLAC`](https://xiph.org/flac/documentation.html) (Free Lossless Audio
  // Codec) is the recommended encoding because it is lossless (therefore
  // recognition is not compromised) and requires only about half the
  // bandwidth of `LINEAR16`. `FLAC` stream encoding supports 16-bit and
  // 24-bit samples, however, not all fields in `STREAMINFO` are supported.
  AUDIO_ENCODING_FLAC = 2;

  // 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
  AUDIO_ENCODING_MULAW = 3;

  // Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
  AUDIO_ENCODING_AMR = 4;

  // Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
  AUDIO_ENCODING_AMR_WB = 5;

  // Opus encoded audio frames in Ogg container
  // ([OggOpus](https://wiki.xiph.org/OggOpus)).
  // `sample_rate_hertz` must be 16000.
  AUDIO_ENCODING_OGG_OPUS = 6;

  // Although the use of lossy encodings is not recommended, if a very low
  // bitrate encoding is required, `OGG_OPUS` is highly preferred over
  // Speex encoding. The [Speex](https://speex.org/) encoding supported by
  // Dialogflow API has a header byte in each block, as in MIME type
  // `audio/x-speex-with-header-byte`.
  // It is a variant of the RTP Speex encoding defined in
  // [RFC 5574](https://tools.ietf.org/html/rfc5574).
  // The stream is a sequence of blocks, one block per RTP packet. Each block
  // starts with a byte containing the length of the block, in bytes, followed
  // by one or more frames of Speex data, padded to an integral number of
  // bytes (octets) as specified in RFC 5574. In other words, each RTP header
  // is replaced with a single byte containing the block length. Only Speex
  // wideband is supported. `sample_rate_hertz` must be 16000.
  AUDIO_ENCODING_SPEEX_WITH_HEADER_BYTE = 7;
}

// Variant of the specified [Speech
// model][google.cloud.dialogflow.cx.v3.InputAudioConfig.model] to use.
//
// See the [Cloud Speech
// documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
// for which models have different variants. For example, the "phone_call" model
// has both a standard and an enhanced variant. When you use an enhanced model,
// you will generally receive higher quality results than for a standard model.
enum SpeechModelVariant {
  // No model variant specified. In this case Dialogflow defaults to
  // USE_BEST_AVAILABLE.
  SPEECH_MODEL_VARIANT_UNSPECIFIED = 0;

  // Use the best available variant of the [Speech
  // model][InputAudioConfig.model] that the caller is eligible for.
  //
  // Please see the [Dialogflow
  // docs](https://cloud.google.com/dialogflow/docs/data-logging) for
  // how to make your project eligible for enhanced models.
  USE_BEST_AVAILABLE = 1;

  // Use standard model variant even if an enhanced model is available.  See the
  // [Cloud Speech
  // documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
  // for details about enhanced models.
  USE_STANDARD = 2;

  // Use an enhanced model variant:
  //
  // * If an enhanced variant does not exist for the given
  //   [model][google.cloud.dialogflow.cx.v3.InputAudioConfig.model] and request
  //   language, Dialogflow falls back to the standard variant.
  //
  //   The [Cloud Speech
  //   documentation](https://cloud.google.com/speech-to-text/docs/enhanced-models)
  //   describes which models have enhanced variants.
  //
  // * If the API caller isn't eligible for enhanced models, Dialogflow returns
  //   an error.  Please see the [Dialogflow
  //   docs](https://cloud.google.com/dialogflow/docs/data-logging)
  //   for how to make your project eligible.
  USE_ENHANCED = 3;
}

// Information for a word recognized by the speech recognizer.
message SpeechWordInfo {
  // The word this info is for.
  string word = 3;

  // Time offset relative to the beginning of the audio that corresponds to the
  // start of the spoken word. This is an experimental feature and the accuracy
  // of the time offset can vary.
  google.protobuf.Duration start_offset = 1;

  // Time offset relative to the beginning of the audio that corresponds to the
  // end of the spoken word. This is an experimental feature and the accuracy of
  // the time offset can vary.
  google.protobuf.Duration end_offset = 2;

  // The Speech confidence between 0.0 and 1.0 for this word. A higher number
  // indicates an estimated greater likelihood that the recognized word is
  // correct. The default of 0.0 is a sentinel value indicating that confidence
  // was not set.
  //
  // This field is not guaranteed to be fully stable over time for the same
  // audio input. Users should also not rely on it to always be provided.
  float confidence = 4;
}

// Instructs the speech recognizer on how to process the audio content.
message InputAudioConfig {
  // Required. Audio encoding of the audio content to process.
  AudioEncoding audio_encoding = 1 [(google.api.field_behavior) = REQUIRED];

  // Sample rate (in Hertz) of the audio content sent in the query.
  // Refer to
  // [Cloud Speech API
  // documentation](https://cloud.google.com/speech-to-text/docs/basics) for
  // more details.
  int32 sample_rate_hertz = 2;

  // Optional. If `true`, Dialogflow returns
  // [SpeechWordInfo][google.cloud.dialogflow.cx.v3.SpeechWordInfo] in
  // [StreamingRecognitionResult][google.cloud.dialogflow.cx.v3.StreamingRecognitionResult]
  // with information about the recognized speech words, e.g. start and end time
  // offsets. If false or unspecified, Speech doesn't return any word-level
  // information.
  bool enable_word_info = 13;

  // Optional. A list of strings containing words and phrases that the speech
  // recognizer should recognize with higher likelihood.
  //
  // See [the Cloud Speech
  // documentation](https://cloud.google.com/speech-to-text/docs/basics#phrase-hints)
  // for more details.
  repeated string phrase_hints = 4;

  // Optional. Which Speech model to select for the given request. Select the
  // model best suited to your domain to get best results. If a model is not
  // explicitly specified, then we auto-select a model based on the parameters
  // in the InputAudioConfig.
  // If enhanced speech model is enabled for the agent and an enhanced
  // version of the specified model for the language does not exist, then the
  // speech is recognized using the standard version of the specified model.
  // Refer to
  // [Cloud Speech API
  // documentation](https://cloud.google.com/speech-to-text/docs/basics#select-model)
  // for more details.
  // If you specify a model, the following models typically have the best
  // performance:
  //
  // - phone_call (best for Agent Assist and telephony)
  // - latest_short (best for Dialogflow non-telephony)
  // - command_and_search (best for very short utterances and commands)
  string model = 7;

  // Optional. Which variant of the [Speech
  // model][google.cloud.dialogflow.cx.v3.InputAudioConfig.model] to use.
  SpeechModelVariant model_variant = 10;

  // Optional. If `false` (default), recognition does not cease until the
  // client closes the stream.
  // If `true`, the recognizer will detect a single spoken utterance in input
  // audio. Recognition ceases when it detects the audio's voice has
  // stopped or paused. In this case, once a detected intent is received, the
  // client should close the stream and start a new request with a new stream as
  // needed.
  // Note: This setting is relevant only for streaming methods.
  bool single_utterance = 8;
}

// Gender of the voice as described in
// [SSML voice element](https://www.w3.org/TR/speech-synthesis11/#edef_voice).
enum SsmlVoiceGender {
  // An unspecified gender, which means that the client doesn't care which
  // gender the selected voice will have.
  SSML_VOICE_GENDER_UNSPECIFIED = 0;

  // A male voice.
  SSML_VOICE_GENDER_MALE = 1;

  // A female voice.
  SSML_VOICE_GENDER_FEMALE = 2;

  // A gender-neutral voice.
  SSML_VOICE_GENDER_NEUTRAL = 3;
}

// Description of which voice to use for speech synthesis.
message VoiceSelectionParams {
  // Optional. The name of the voice. If not set, the service will choose a
  // voice based on the other parameters such as language_code and
  // [ssml_gender][google.cloud.dialogflow.cx.v3.VoiceSelectionParams.ssml_gender].
  //
  // For the list of available voices, please refer to [Supported voices and
  // languages](https://cloud.google.com/text-to-speech/docs/voices).
  string name = 1;

  // Optional. The preferred gender of the voice. If not set, the service will
  // choose a voice based on the other parameters such as language_code and
  // [name][google.cloud.dialogflow.cx.v3.VoiceSelectionParams.name]. Note that
  // this is only a preference, not requirement. If a voice of the appropriate
  // gender is not available, the synthesizer substitutes a voice with a
  // different gender rather than failing the request.
  SsmlVoiceGender ssml_gender = 2;
}

// Configuration of how speech should be synthesized.
message SynthesizeSpeechConfig {
  // Optional. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is the normal
  // native speed supported by the specific voice. 2.0 is twice as fast, and
  // 0.5 is half as fast. If unset(0.0), defaults to the native 1.0 speed. Any
  // other values < 0.25 or > 4.0 will return an error.
  double speaking_rate = 1;

  // Optional. Speaking pitch, in the range [-20.0, 20.0]. 20 means increase 20
  // semitones from the original pitch. -20 means decrease 20 semitones from the
  // original pitch.
  double pitch = 2;

  // Optional. Volume gain (in dB) of the normal native volume supported by the
  // specific voice, in the range [-96.0, 16.0]. If unset, or set to a value of
  // 0.0 (dB), will play at normal native signal amplitude. A value of -6.0 (dB)
  // will play at approximately half the amplitude of the normal native signal
  // amplitude. A value of +6.0 (dB) will play at approximately twice the
  // amplitude of the normal native signal amplitude. We strongly recommend not
  // to exceed +10 (dB) as there's usually no effective increase in loudness for
  // any value greater than that.
  double volume_gain_db = 3;

  // Optional. An identifier which selects 'audio effects' profiles that are
  // applied on (post synthesized) text to speech. Effects are applied on top of
  // each other in the order they are given.
  repeated string effects_profile_id = 5;

  // Optional. The desired voice of the synthesized audio.
  VoiceSelectionParams voice = 4;
}

// Audio encoding of the output audio format in Text-To-Speech.
enum OutputAudioEncoding {
  // Not specified.
  OUTPUT_AUDIO_ENCODING_UNSPECIFIED = 0;

  // Uncompressed 16-bit signed little-endian samples (Linear PCM).
  // Audio content returned as LINEAR16 also contains a WAV header.
  OUTPUT_AUDIO_ENCODING_LINEAR_16 = 1;

  // MP3 audio at 32kbps.
  OUTPUT_AUDIO_ENCODING_MP3 = 2;

  // MP3 audio at 64kbps.
  OUTPUT_AUDIO_ENCODING_MP3_64_KBPS = 4;

  // Opus encoded audio wrapped in an ogg container. The result will be a
  // file which can be played natively on Android, and in browsers (at least
  // Chrome and Firefox). The quality of the encoding is considerably higher
  // than MP3 while using approximately the same bitrate.
  OUTPUT_AUDIO_ENCODING_OGG_OPUS = 3;

  // 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
  OUTPUT_AUDIO_ENCODING_MULAW = 5;
}

// Instructs the speech synthesizer how to generate the output audio content.
message OutputAudioConfig {
  // Required. Audio encoding of the synthesized audio content.
  OutputAudioEncoding audio_encoding = 1
      [(google.api.field_behavior) = REQUIRED];

  // Optional. The synthesis sample rate (in hertz) for this audio. If not
  // provided, then the synthesizer will use the default sample rate based on
  // the audio encoding. If this is different from the voice's natural sample
  // rate, then the synthesizer will honor this request by converting to the
  // desired sample rate (which might result in worse audio quality).
  int32 sample_rate_hertz = 2;

  // Optional. Configuration of how speech should be synthesized.
  SynthesizeSpeechConfig synthesize_speech_config = 3;
}

// Settings related to speech synthesizing.
message TextToSpeechSettings {
  // Configuration of how speech should be synthesized, mapping from language
  // (https://cloud.google.com/dialogflow/cx/docs/reference/language) to
  // SynthesizeSpeechConfig.
  //
  // These settings affect:
  //
  //  - The synthesize configuration used in [phone
  //    gateway](https://cloud.google.com/dialogflow/cx/docs/concept/integration/phone-gateway).
  //
  //  - You no longer need to specify
  //    [OutputAudioConfig.synthesize_speech_config][google.cloud.dialogflow.cx.v3.OutputAudioConfig.synthesize_speech_config]
  //    when invoking API calls. Your agent will use the pre-configured options
  //    for speech synthesizing.
  map<string, SynthesizeSpeechConfig> synthesize_speech_configs = 1;
}