kratos/third_party/google/cloud/speech/v1/cloud_speech.proto

// Copyright 2018 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.speech.v1;

import "google/api/annotations.proto";
import "google/longrunning/operations.proto";
import "google/protobuf/any.proto";
import "google/protobuf/duration.proto";
import "google/protobuf/empty.proto";
import "google/protobuf/timestamp.proto";
import "google/rpc/status.proto";

option cc_enable_arenas = true;
option go_package = "google.golang.org/genproto/googleapis/cloud/speech/v1;speech";
option java_multiple_files = true;
option java_outer_classname = "SpeechProto";
option java_package = "com.google.cloud.speech.v1";

// Service that implements Google Cloud Speech API.
service Speech {
  // Performs synchronous speech recognition: receive results after all audio
  // has been sent and processed.
  rpc Recognize(RecognizeRequest) returns (RecognizeResponse) {
    option (google.api.http) = {
      post: "/v1/speech:recognize"
      body: "*"
    };
  }

  // Performs asynchronous speech recognition: receive results via the
  // google.longrunning.Operations interface. Returns either an
  // `Operation.error` or an `Operation.response` which contains
  // a `LongRunningRecognizeResponse` message.
  rpc LongRunningRecognize(LongRunningRecognizeRequest)
      returns (google.longrunning.Operation) {
    option (google.api.http) = {
      post: "/v1/speech:longrunningrecognize"
      body: "*"
    };
  }

  // Performs bidirectional streaming speech recognition: receive results while
  // sending audio. This method is only available via the gRPC API (not REST).
  rpc StreamingRecognize(stream StreamingRecognizeRequest)
      returns (stream StreamingRecognizeResponse) {}
}

// The top-level message sent by the client for the `Recognize` method.
message RecognizeRequest {
  // *Required* Provides information to the recognizer that specifies how to
  // process the request.
  RecognitionConfig config = 1;

  // *Required* The audio data to be recognized.
  RecognitionAudio audio = 2;
}

// The top-level message sent by the client for the `LongRunningRecognize`
// method.
message LongRunningRecognizeRequest {
  // *Required* Provides information to the recognizer that specifies how to
  // process the request.
  RecognitionConfig config = 1;

  // *Required* The audio data to be recognized.
  RecognitionAudio audio = 2;
}

// The top-level message sent by the client for the `StreamingRecognize` method.
// Multiple `StreamingRecognizeRequest` messages are sent. The first message
// must contain a `streaming_config` message and must not contain `audio` data.
// All subsequent messages must contain `audio` data and must not contain a
// `streaming_config` message.
message StreamingRecognizeRequest {
  // The streaming request, which is either a streaming config or audio content.
  oneof streaming_request {
    // Provides information to the recognizer that specifies how to process the
    // request. The first `StreamingRecognizeRequest` message must contain a
    // `streaming_config`  message.
    StreamingRecognitionConfig streaming_config = 1;

    // The audio data to be recognized. Sequential chunks of audio data are sent
    // in sequential `StreamingRecognizeRequest` messages. The first
    // `StreamingRecognizeRequest` message must not contain `audio_content` data
    // and all subsequent `StreamingRecognizeRequest` messages must contain
    // `audio_content` data. The audio bytes must be encoded as specified in
    // `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
    // pure binary representation (not base64). See
    // [content limits](/speech-to-text/quotas#content).
    bytes audio_content = 2;
  }
}

// Provides information to the recognizer that specifies how to process the
// request.
message StreamingRecognitionConfig {
  // *Required* Provides information to the recognizer that specifies how to
  // process the request.
  RecognitionConfig config = 1;

  // *Optional* If `false` or omitted, the recognizer will perform continuous
  // recognition (continuing to wait for and process audio even if the user
  // pauses speaking) until the client closes the input stream (gRPC API) or
  // until the maximum time limit has been reached. May return multiple
  // `StreamingRecognitionResult`s with the `is_final` flag set to `true`.
  //
  // If `true`, the recognizer will detect a single spoken utterance. When it
  // detects that the user has paused or stopped speaking, it will return an
  // `END_OF_SINGLE_UTTERANCE` event and cease recognition. It will return no
  // more than one `StreamingRecognitionResult` with the `is_final` flag set to
  // `true`.
  bool single_utterance = 2;

  // *Optional* If `true`, interim results (tentative hypotheses) may be
  // returned as they become available (these interim results are indicated with
  // the `is_final=false` flag).
  // If `false` or omitted, only `is_final=true` result(s) are returned.
  bool interim_results = 3;
}

// Provides information to the recognizer that specifies how to process the
// request.
message RecognitionConfig {
  // The encoding of the audio data sent in the request.
  //
  // All encodings support only 1 channel (mono) audio.
  //
  // For best results, the audio source should be captured and transmitted using
  // a lossless encoding (`FLAC` or `LINEAR16`). The accuracy of the speech
  // recognition can be reduced if lossy codecs are used to capture or transmit
  // audio, particularly if background noise is present. Lossy codecs include
  // `MULAW`, `AMR`, `AMR_WB`, `OGG_OPUS`, and `SPEEX_WITH_HEADER_BYTE`.
  //
  // The `FLAC` and `WAV` audio file formats include a header that describes the
  // included audio content. You can request recognition for `WAV` files that
  // contain either `LINEAR16` or `MULAW` encoded audio.
  // If you send `FLAC` or `WAV` audio file format in
  // your request, you do not need to specify an `AudioEncoding`; the audio
  // encoding format is determined from the file header. If you specify
  // an `AudioEncoding` when you send  send `FLAC` or `WAV` audio, the
  // encoding configuration must match the encoding described in the audio
  // header; otherwise the request returns an
  // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
  // code.
  enum AudioEncoding {
    // Not specified.
    ENCODING_UNSPECIFIED = 0;

    // Uncompressed 16-bit signed little-endian samples (Linear PCM).
    LINEAR16 = 1;

    // `FLAC` (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.
    FLAC = 2;

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

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

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

    // Opus encoded audio frames in Ogg container
    // ([OggOpus](https://wiki.xiph.org/OggOpus)).
    // `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000.
    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
    // Cloud Speech 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.
    SPEEX_WITH_HEADER_BYTE = 7;
  }

  // Encoding of audio data sent in all `RecognitionAudio` messages.
  // This field is optional for `FLAC` and `WAV` audio files and required
  // for all other audio formats. For details, see
  // [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
  AudioEncoding encoding = 1;

  // Sample rate in Hertz of the audio data sent in all
  // `RecognitionAudio` messages. Valid values are: 8000-48000.
  // 16000 is optimal. For best results, set the sampling rate of the audio
  // source to 16000 Hz. If that's not possible, use the native sample rate of
  // the audio source (instead of re-sampling).
  // This field is optional for `FLAC` and `WAV` audio files and required
  // for all other audio formats. For details, see
  // [AudioEncoding][google.cloud.speech.v1.RecognitionConfig.AudioEncoding].
  int32 sample_rate_hertz = 2;

  // *Optional* The number of channels in the input audio data.
  // ONLY set this for MULTI-CHANNEL recognition.
  // Valid values for LINEAR16 and FLAC are `1`-`8`.
  // Valid values for OGG_OPUS are '1'-'254'.
  // Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
  // If `0` or omitted, defaults to one channel (mono).
  // Note: We only recognize the first channel by default.
  // To perform independent recognition on each channel set
  // `enable_separate_recognition_per_channel` to 'true'.
  int32 audio_channel_count = 7;

  // This needs to be set to `true` explicitly and `audio_channel_count` > 1
  // to get each channel recognized separately. The recognition result will
  // contain a `channel_tag` field to state which channel that result belongs
  // to. If this is not true, we will only recognize the first channel. The
  // request is billed cumulatively for all channels recognized:
  // `audio_channel_count` multiplied by the length of the audio.
  bool enable_separate_recognition_per_channel = 12;

  // *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](/speech-to-text/docs/languages)
  // for a list of the currently supported language codes.
  string language_code = 3;

  // *Optional* Maximum number of recognition hypotheses to be returned.
  // Specifically, the maximum number of `SpeechRecognitionAlternative` messages
  // within each `SpeechRecognitionResult`.
  // The server may return fewer than `max_alternatives`.
  // Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of
  // one. If omitted, will return a maximum of one.
  int32 max_alternatives = 4;

  // *Optional* If set to `true`, the server will attempt to filter out
  // profanities, replacing all but the initial character in each filtered word
  // with asterisks, e.g. "f***". If set to `false` or omitted, profanities
  // won't be filtered out.
  bool profanity_filter = 5;

  // *Optional* array of [SpeechContext][google.cloud.speech.v1.SpeechContext].
  // A means to provide context to assist the speech recognition. For more
  // information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
  repeated SpeechContext speech_contexts = 6;

  // *Optional* If `true`, the top result includes a list of words and
  // the start and end time offsets (timestamps) for those words. If
  // `false`, no word-level time offset information is returned. The default is
  // `false`.
  bool enable_word_time_offsets = 8;

  // *Optional* If 'true', adds punctuation to recognition result hypotheses.
  // This feature is only available in select languages. Setting this for
  // requests in other languages has no effect at all.
  // The default 'false' value does not add punctuation to result hypotheses.
  // Note: This is currently offered as an experimental service, complimentary
  // to all users. In the future this may be exclusively available as a
  // premium feature.
  bool enable_automatic_punctuation = 11;

  // *Optional* Which 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 RecognitionConfig.
  // <table>
  //   <tr>
  //     <td><b>Model</b></td>
  //     <td><b>Description</b></td>
  //   </tr>
  //   <tr>
  //     <td><code>command_and_search</code></td>
  //     <td>Best for short queries such as voice commands or voice search.</td>
  //   </tr>
  //   <tr>
  //     <td><code>phone_call</code></td>
  //     <td>Best for audio that originated from a phone call (typically
  //     recorded at an 8khz sampling rate).</td>
  //   </tr>
  //   <tr>
  //     <td><code>video</code></td>
  //     <td>Best for audio that originated from from video or includes multiple
  //         speakers. Ideally the audio is recorded at a 16khz or greater
  //         sampling rate. This is a premium model that costs more than the
  //         standard rate.</td>
  //   </tr>
  //   <tr>
  //     <td><code>default</code></td>
  //     <td>Best for audio that is not one of the specific audio models.
  //         For example, long-form audio. Ideally the audio is high-fidelity,
  //         recorded at a 16khz or greater sampling rate.</td>
  //   </tr>
  // </table>
  string model = 13;

  // *Optional* Set to true to use an enhanced model for speech recognition.
  // If `use_enhanced` is set to true and the `model` field is not set, then
  // an appropriate enhanced model is chosen if:
  // 1. project is eligible for requesting enhanced models
  // 2. an enhanced model exists for the audio
  //
  // If `use_enhanced` is true and an enhanced version of the specified model
  // does not exist, then the speech is recognized using the standard version
  // of the specified model.
  //
  // Enhanced speech models require that you opt-in to data logging using
  // instructions in the
  // [documentation](/speech-to-text/docs/enable-data-logging). If you set
  // `use_enhanced` to true and you have not enabled audio logging, then you
  // will receive an error.
  bool use_enhanced = 14;
}

// Provides "hints" to the speech recognizer to favor specific words and phrases
// in the results.
message SpeechContext {
  // *Optional* A list of strings containing words and phrases "hints" so that
  // the speech recognition is more likely to recognize them. This can be used
  // to improve the accuracy for specific words and phrases, for example, if
  // specific commands are typically spoken by the user. This can also be used
  // to add additional words to the vocabulary of the recognizer. See
  // [usage limits](/speech-to-text/quotas#content).
  repeated string phrases = 1;
}

// Contains audio data in the encoding specified in the `RecognitionConfig`.
// Either `content` or `uri` must be supplied. Supplying both or neither
// returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
// See [content limits](/speech-to-text/quotas#content).
message RecognitionAudio {
  // The audio source, which is either inline content or a Google Cloud
  // Storage uri.
  oneof audio_source {
    // The audio data bytes encoded as specified in
    // `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
    // pure binary representation, whereas JSON representations use base64.
    bytes content = 1;

    // URI that points to a file that contains audio data bytes as specified in
    // `RecognitionConfig`. The file must not be compressed (for example, gzip).
    // Currently, only Google Cloud Storage URIs are
    // supported, which must be specified in the following format:
    // `gs://bucket_name/object_name` (other URI formats return
    // [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
    // For more information, see [Request
    // URIs](https://cloud.google.com/storage/docs/reference-uris).
    string uri = 2;
  }
}

// The only message returned to the client by the `Recognize` method. It
// contains the result as zero or more sequential `SpeechRecognitionResult`
// messages.
message RecognizeResponse {
  // Output only. Sequential list of transcription results corresponding to
  // sequential portions of audio.
  repeated SpeechRecognitionResult results = 2;
}

// The only message returned to the client by the `LongRunningRecognize` method.
// It contains the result as zero or more sequential `SpeechRecognitionResult`
// messages. It is included in the `result.response` field of the `Operation`
// returned by the `GetOperation` call of the `google::longrunning::Operations`
// service.
message LongRunningRecognizeResponse {
  // Output only. Sequential list of transcription results corresponding to
  // sequential portions of audio.
  repeated SpeechRecognitionResult results = 2;
}

// Describes the progress of a long-running `LongRunningRecognize` call. It is
// included in the `metadata` field of the `Operation` returned by the
// `GetOperation` call of the `google::longrunning::Operations` service.
message LongRunningRecognizeMetadata {
  // Approximate percentage of audio processed thus far. Guaranteed to be 100
  // when the audio is fully processed and the results are available.
  int32 progress_percent = 1;

  // Time when the request was received.
  google.protobuf.Timestamp start_time = 2;

  // Time of the most recent processing update.
  google.protobuf.Timestamp last_update_time = 3;
}

// `StreamingRecognizeResponse` is the only message returned to the client by
// `StreamingRecognize`. A series of zero or more `StreamingRecognizeResponse`
// messages are streamed back to the client. If there is no recognizable
// audio, and `single_utterance` is set to false, then no messages are streamed
// back to the client.
//
// Here's an example of a series of ten `StreamingRecognizeResponse`s that might
// be returned while processing audio:
//
// 1. results { alternatives { transcript: "tube" } stability: 0.01 }
//
// 2. results { alternatives { transcript: "to be a" } stability: 0.01 }
//
// 3. results { alternatives { transcript: "to be" } stability: 0.9 }
//    results { alternatives { transcript: " or not to be" } stability: 0.01 }
//
// 4. results { alternatives { transcript: "to be or not to be"
//                             confidence: 0.92 }
//              alternatives { transcript: "to bee or not to bee" }
//              is_final: true }
//
// 5. results { alternatives { transcript: " that's" } stability: 0.01 }
//
// 6. results { alternatives { transcript: " that is" } stability: 0.9 }
//    results { alternatives { transcript: " the question" } stability: 0.01 }
//
// 7. results { alternatives { transcript: " that is the question"
//                             confidence: 0.98 }
//              alternatives { transcript: " that was the question" }
//              is_final: true }
//
// Notes:
//
// - Only two of the above responses #4 and #7 contain final results; they are
//   indicated by `is_final: true`. Concatenating these together generates the
//   full transcript: "to be or not to be that is the question".
//
// - The others contain interim `results`. #3 and #6 contain two interim
//   `results`: the first portion has a high stability and is less likely to
//   change; the second portion has a low stability and is very likely to
//   change. A UI designer might choose to show only high stability `results`.
//
// - The specific `stability` and `confidence` values shown above are only for
//   illustrative purposes. Actual values may vary.
//
// - In each response, only one of these fields will be set:
//     `error`,
//     `speech_event_type`, or
//     one or more (repeated) `results`.
message StreamingRecognizeResponse {
  // Indicates the type of speech event.
  enum SpeechEventType {
    // No speech event specified.
    SPEECH_EVENT_UNSPECIFIED = 0;

    // This event indicates that the server has detected the end of the user's
    // speech utterance and expects no additional speech. Therefore, the server
    // will not process additional audio (although it may subsequently return
    // additional results). The client should stop sending additional audio
    // data, half-close the gRPC connection, and wait for any additional results
    // until the server closes the gRPC connection. This event is only sent if
    // `single_utterance` was set to `true`, and is not used otherwise.
    END_OF_SINGLE_UTTERANCE = 1;
  }

  // Output only. If set, returns a [google.rpc.Status][google.rpc.Status]
  // message that specifies the error for the operation.
  google.rpc.Status error = 1;

  // Output only. This repeated list contains zero or more results that
  // correspond to consecutive portions of the audio currently being processed.
  // It contains zero or one `is_final=true` result (the newly settled portion),
  // followed by zero or more `is_final=false` results (the interim results).
  repeated StreamingRecognitionResult results = 2;

  // Output only. Indicates the type of speech event.
  SpeechEventType speech_event_type = 4;
}

// A streaming speech recognition result corresponding to a portion of the audio
// that is currently being processed.
message StreamingRecognitionResult {
  // Output only. May contain one or more recognition hypotheses (up to the
  // maximum specified in `max_alternatives`).
  // These alternatives are ordered in terms of accuracy, with the top (first)
  // alternative being the most probable, as ranked by the recognizer.
  repeated SpeechRecognitionAlternative alternatives = 1;

  // Output only. If `false`, this `StreamingRecognitionResult` represents an
  // interim result that may change. If `true`, this is the final time the
  // speech service will return this particular `StreamingRecognitionResult`,
  // the recognizer will not return any further hypotheses for this portion of
  // the transcript and corresponding audio.
  bool is_final = 2;

  // Output only. An estimate of the likelihood that the recognizer will not
  // change its guess about this interim result. Values range from 0.0
  // (completely unstable) to 1.0 (completely stable).
  // This field is only provided for interim results (`is_final=false`).
  // The default of 0.0 is a sentinel value indicating `stability` was not set.
  float stability = 3;

  // For multi-channel audio, this is the channel number corresponding to the
  // recognized result for the audio from that channel.
  // For audio_channel_count = N, its output values can range from '1' to 'N'.
  int32 channel_tag = 5;
}

// A speech recognition result corresponding to a portion of the audio.
message SpeechRecognitionResult {
  // Output only. May contain one or more recognition hypotheses (up to the
  // maximum specified in `max_alternatives`).
  // These alternatives are ordered in terms of accuracy, with the top (first)
  // alternative being the most probable, as ranked by the recognizer.
  repeated SpeechRecognitionAlternative alternatives = 1;

  // For multi-channel audio, this is the channel number corresponding to the
  // recognized result for the audio from that channel.
  // For audio_channel_count = N, its output values can range from '1' to 'N'.
  int32 channel_tag = 2;
}

// Alternative hypotheses (a.k.a. n-best list).
message SpeechRecognitionAlternative {
  // Output only. Transcript text representing the words that the user spoke.
  string transcript = 1;

  // Output only. The confidence estimate between 0.0 and 1.0. A higher number
  // indicates an estimated greater likelihood that the recognized words are
  // correct. This field is set only for the top alternative of a non-streaming
  // result or, of a streaming result where `is_final=true`.
  // This field is not guaranteed to be accurate and users should not rely on it
  // to be always provided.
  // The default of 0.0 is a sentinel value indicating `confidence` was not set.
  float confidence = 2;

  // Output only. A list of word-specific information for each recognized word.
  // Note: When `enable_speaker_diarization` is true, you will see all the words
  // from the beginning of the audio.
  repeated WordInfo words = 3;
}

// Word-specific information for recognized words.
message WordInfo {
  // Output only. Time offset relative to the beginning of the audio,
  // and corresponding to the start of the spoken word.
  // This field is only set if `enable_word_time_offsets=true` and only
  // in the top hypothesis.
  // This is an experimental feature and the accuracy of the time offset can
  // vary.
  google.protobuf.Duration start_time = 1;

  // Output only. Time offset relative to the beginning of the audio,
  // and corresponding to the end of the spoken word.
  // This field is only set if `enable_word_time_offsets=true` and only
  // in the top hypothesis.
  // This is an experimental feature and the accuracy of the time offset can
  // vary.
  google.protobuf.Duration end_time = 2;

  // Output only. The word corresponding to this set of information.
  string word = 3;
}