google.cloud.dialogflow.v2.audio_config.proto Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of proto-google-cloud-dialogflow-v2 Show documentation
Show all versions of proto-google-cloud-dialogflow-v2 Show documentation
PROTO library for proto-google-cloud-dialogflow-v2
// 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.dialogflow.v2;
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.V2";
option go_package = "cloud.google.com/go/dialogflow/apiv2/dialogflowpb;dialogflowpb";
option java_multiple_files = true;
option java_outer_classname = "AudioConfigProto";
option java_package = "com.google.cloud.dialogflow.v2";
option objc_class_prefix = "DF";
option (google.api.resource_definition) = {
type: "automl.googleapis.com/Model"
pattern: "projects/{project}/locations/{location}/models/{model}"
};
option (google.api.resource_definition) = {
type: "speech.googleapis.com/PhraseSet"
pattern: "projects/{project}/locations/{location}/phraseSets/{phrase_set}"
};
// Hints for the speech recognizer to help with recognition in a specific
// conversation state.
message SpeechContext {
// Optional. A list of strings containing words and phrases that the speech
// recognizer should recognize with higher likelihood.
//
// This list can be used to:
//
// * improve accuracy for words and phrases you expect the user to say,
// e.g. typical commands for your Dialogflow agent
// * add additional words to the speech recognizer vocabulary
// * ...
//
// See the [Cloud Speech
// documentation](https://cloud.google.com/speech-to-text/quotas) for usage
// limits.
repeated string phrases = 1 [(google.api.field_behavior) = OPTIONAL];
// Optional. Boost for this context compared to other contexts:
//
// * If the boost is positive, Dialogflow will increase the probability that
// the phrases in this context are recognized over similar sounding phrases.
// * If the boost is unspecified or non-positive, Dialogflow will not apply
// any boost.
//
// Dialogflow recommends that you use boosts in the range (0, 20] and that you
// find a value that fits your use case with binary search.
float boost = 2 [(google.api.field_behavior) = OPTIONAL];
}
// 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 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];
// 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 [(google.api.field_behavior) = REQUIRED];
// Required. The language of the supplied audio. Dialogflow does not do
// translations. See [Language
// Support](https://cloud.google.com/dialogflow/docs/reference/language)
// for a list of the currently supported language codes. Note that queries in
// the same session do not necessarily need to specify the same language.
string language_code = 3 [(google.api.field_behavior) = REQUIRED];
// If `true`, Dialogflow returns
// [SpeechWordInfo][google.cloud.dialogflow.v2.SpeechWordInfo] in
// [StreamingRecognitionResult][google.cloud.dialogflow.v2.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;
// 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.
//
// This field is deprecated. Please use [`speech_contexts`]() instead. If you
// specify both [`phrase_hints`]() and [`speech_contexts`](), Dialogflow will
// treat the [`phrase_hints`]() as a single additional [`SpeechContext`]().
repeated string phrase_hints = 4 [deprecated = true];
// Context information to assist speech recognition.
//
// See [the Cloud Speech
// documentation](https://cloud.google.com/speech-to-text/docs/basics#phrase-hints)
// for more details.
repeated SpeechContext speech_contexts = 11;
// Optional. Which Speech model to select for the given request.
// For more information, see
// [Speech models](https://cloud.google.com/dialogflow/es/docs/speech-models).
string model = 7;
// Which variant of the [Speech
// model][google.cloud.dialogflow.v2.InputAudioConfig.model] to use.
SpeechModelVariant model_variant = 10;
// 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.
// Note: When specified, InputAudioConfig.single_utterance takes precedence
// over StreamingDetectIntentRequest.single_utterance.
bool single_utterance = 8;
// Only used in
// [Participants.AnalyzeContent][google.cloud.dialogflow.v2.Participants.AnalyzeContent]
// and
// [Participants.StreamingAnalyzeContent][google.cloud.dialogflow.v2.Participants.StreamingAnalyzeContent].
// If `false` and recognition doesn't return any result, trigger
// `NO_SPEECH_RECOGNIZED` event to Dialogflow agent.
bool disable_no_speech_recognized_event = 14;
// Enable automatic punctuation option at the speech backend.
bool enable_automatic_punctuation = 17;
// If `true`, the request will opt out for STT conformer model migration.
// This field will be deprecated once force migration takes place in June
// 2024. Please refer to [Dialogflow ES Speech model
// migration](https://cloud.google.com/dialogflow/es/docs/speech-model-migration).
bool opt_out_conformer_model_migration = 26;
}
// 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.v2.VoiceSelectionParams.ssml_gender].
string name = 1 [(google.api.field_behavior) = OPTIONAL];
// 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.v2.VoiceSelectionParams.name]. Note that
// this is only a preference, not requirement. If a voice of the appropriate
// gender is not available, the synthesizer should substitute a voice with a
// different gender rather than failing the request.
SsmlVoiceGender ssml_gender = 2 [(google.api.field_behavior) = OPTIONAL];
}
// 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 [(google.api.field_behavior) = OPTIONAL];
// 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 [(google.api.field_behavior) = OPTIONAL];
// 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 [(google.api.field_behavior) = OPTIONAL];
// 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
[(google.api.field_behavior) = OPTIONAL];
// Optional. The desired voice of the synthesized audio.
VoiceSelectionParams voice = 4 [(google.api.field_behavior) = OPTIONAL];
}
// Instructs the speech synthesizer on how to generate the output audio content.
// If this audio config is supplied in a request, it overrides all existing
// text-to-speech settings applied to the agent.
message OutputAudioConfig {
// Required. Audio encoding of the synthesized audio content.
OutputAudioEncoding audio_encoding = 1
[(google.api.field_behavior) = REQUIRED];
// 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;
// Configuration of how speech should be synthesized.
SynthesizeSpeechConfig synthesize_speech_config = 3;
}
// A wrapper of repeated TelephonyDtmf digits.
message TelephonyDtmfEvents {
// A sequence of TelephonyDtmf digits.
repeated TelephonyDtmf dtmf_events = 1;
}
// Configures speech transcription for
// [ConversationProfile][google.cloud.dialogflow.v2.ConversationProfile].
message SpeechToTextConfig {
// The speech model used in speech to text.
// `SPEECH_MODEL_VARIANT_UNSPECIFIED`, `USE_BEST_AVAILABLE` will be treated as
// `USE_ENHANCED`. It can be overridden in
// [AnalyzeContentRequest][google.cloud.dialogflow.v2.AnalyzeContentRequest]
// and
// [StreamingAnalyzeContentRequest][google.cloud.dialogflow.v2.StreamingAnalyzeContentRequest]
// request. If enhanced model variant is specified and an enhanced version of
// the specified model for the language does not exist, then it would emit an
// error.
SpeechModelVariant speech_model_variant = 1;
// Which Speech model to select. Select the
// model best suited to your domain to get best results. If a model is not
// explicitly specified, then Dialogflow auto-selects a model based on other
// parameters in the SpeechToTextConfig and Agent settings.
// 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
//
// Leave this field unspecified to use
// [Agent Speech
// settings](https://cloud.google.com/dialogflow/cx/docs/concept/agent#settings-speech)
// for model selection.
string model = 2;
// Audio encoding of the audio content to process.
AudioEncoding audio_encoding = 6;
// 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 = 7;
// The language of the supplied audio. Dialogflow does not do
// translations. See [Language
// Support](https://cloud.google.com/dialogflow/docs/reference/language)
// for a list of the currently supported language codes. Note that queries in
// the same session do not necessarily need to specify the same language.
string language_code = 8;
// If `true`, Dialogflow returns
// [SpeechWordInfo][google.cloud.dialogflow.v2.SpeechWordInfo] in
// [StreamingRecognitionResult][google.cloud.dialogflow.v2.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 = 9;
// Use timeout based endpointing, interpreting endpointer sensitivy as
// seconds of timeout value.
bool use_timeout_based_endpointing = 11;
}
// [DTMF](https://en.wikipedia.org/wiki/Dual-tone_multi-frequency_signaling)
// digit in Telephony Gateway.
enum TelephonyDtmf {
// Not specified. This value may be used to indicate an absent digit.
TELEPHONY_DTMF_UNSPECIFIED = 0;
// Number: '1'.
DTMF_ONE = 1;
// Number: '2'.
DTMF_TWO = 2;
// Number: '3'.
DTMF_THREE = 3;
// Number: '4'.
DTMF_FOUR = 4;
// Number: '5'.
DTMF_FIVE = 5;
// Number: '6'.
DTMF_SIX = 6;
// Number: '7'.
DTMF_SEVEN = 7;
// Number: '8'.
DTMF_EIGHT = 8;
// Number: '9'.
DTMF_NINE = 9;
// Number: '0'.
DTMF_ZERO = 10;
// Letter: 'A'.
DTMF_A = 11;
// Letter: 'B'.
DTMF_B = 12;
// Letter: 'C'.
DTMF_C = 13;
// Letter: 'D'.
DTMF_D = 14;
// Asterisk/star: '*'.
DTMF_STAR = 15;
// Pound/diamond/hash/square/gate/octothorpe: '#'.
DTMF_POUND = 16;
}
// 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.v2.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.v2.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;
}
// 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;
}
// 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;
}