Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
// 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.speech.v1p1beta1;
import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";
import "google/cloud/speech/v1p1beta1/resource.proto";
import "google/longrunning/operations.proto";
import "google/protobuf/duration.proto";
import "google/protobuf/timestamp.proto";
import "google/protobuf/wrappers.proto";
import "google/rpc/status.proto";
option cc_enable_arenas = true;
option go_package = "cloud.google.com/go/speech/apiv1p1beta1/speechpb;speechpb";
option java_multiple_files = true;
option java_outer_classname = "SpeechProto";
option java_package = "com.google.cloud.speech.v1p1beta1";
option objc_class_prefix = "GCS";
// Service that implements Google Cloud Speech API.
service Speech {
option (google.api.default_host) = "speech.googleapis.com";
option (google.api.oauth_scopes) =
"https://www.googleapis.com/auth/cloud-platform";
// Performs synchronous speech recognition: receive results after all audio
// has been sent and processed.
rpc Recognize(RecognizeRequest) returns (RecognizeResponse) {
option (google.api.http) = {
post: "/v1p1beta1/speech:recognize"
body: "*"
};
option (google.api.method_signature) = "config,audio";
}
// 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.
// For more information on asynchronous speech recognition, see the
// [how-to](https://cloud.google.com/speech-to-text/docs/async-recognize).
rpc LongRunningRecognize(LongRunningRecognizeRequest)
returns (google.longrunning.Operation) {
option (google.api.http) = {
post: "/v1p1beta1/speech:longrunningrecognize"
body: "*"
};
option (google.api.method_signature) = "config,audio";
option (google.longrunning.operation_info) = {
response_type: "LongRunningRecognizeResponse"
metadata_type: "LongRunningRecognizeMetadata"
};
}
// 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 [(google.api.field_behavior) = REQUIRED];
// Required. The audio data to be recognized.
RecognitionAudio audio = 2 [(google.api.field_behavior) = REQUIRED];
}
// 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 [(google.api.field_behavior) = REQUIRED];
// Required. The audio data to be recognized.
RecognitionAudio audio = 2 [(google.api.field_behavior) = REQUIRED];
// Optional. Specifies an optional destination for the recognition results.
TranscriptOutputConfig output_config = 4
[(google.api.field_behavior) = OPTIONAL];
}
// Specifies an optional destination for the recognition results.
message TranscriptOutputConfig {
oneof output_type {
// Specifies a Cloud Storage URI for the recognition results. Must be
// specified in the format: `gs://bucket_name/object_name`, and the bucket
// must already exist.
string gcs_uri = 1;
}
}
// 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_content`. All subsequent messages must contain `audio_content` 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, proto buffers use a
// pure binary representation (not base64). See
// [content limits](https://cloud.google.com/speech-to-text/quotas#content).
bytes audio_content = 2;
}
}
// Provides information to the recognizer that specifies how to process the
// request.
message StreamingRecognitionConfig {
// Events that a timeout can be set on for voice activity.
message VoiceActivityTimeout {
// Duration to timeout the stream if no speech begins.
google.protobuf.Duration speech_start_timeout = 1;
// Duration to timeout the stream after speech ends.
google.protobuf.Duration speech_end_timeout = 2;
}
// Required. Provides information to the recognizer that specifies how to
// process the request.
RecognitionConfig config = 1 [(google.api.field_behavior) = REQUIRED];
// 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`.
//
// The `single_utterance` field can only be used with specified models,
// otherwise an error is thrown. The `model` field in [`RecognitionConfig`][]
// must be set to:
//
// * `command_and_search`
// * `phone_call` AND additional field `useEnhanced`=`true`
// * The `model` field is left undefined. In this case the API auto-selects
// a model based on any other parameters that you set in
// `RecognitionConfig`.
bool single_utterance = 2;
// 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;
// If `true`, responses with voice activity speech events will be returned as
// they are detected.
bool enable_voice_activity_events = 5;
// If set, the server will automatically close the stream after the specified
// duration has elapsed after the last VOICE_ACTIVITY speech event has been
// sent. The field `voice_activity_events` must also be set to true.
VoiceActivityTimeout voice_activity_timeout = 6;
}
// 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, unless the
// `audio_channel_count` and `enable_separate_recognition_per_channel` fields
// are set.
//
// 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`, `SPEEX_WITH_HEADER_BYTE`, `MP3`,
// and `WEBM_OPUS`.
//
// 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;
// MP3 audio. MP3 encoding is a Beta feature and only available in
// v1p1beta1. Support all standard MP3 bitrates (which range from 32-320
// kbps). When using this encoding, `sample_rate_hertz` has to match the
// sample rate of the file being used.
MP3 = 8;
// Opus encoded audio frames in WebM container
// ([OggOpus](https://wiki.xiph.org/OggOpus)). `sample_rate_hertz` must be
// one of 8000, 12000, 16000, 24000, or 48000.
WEBM_OPUS = 9;
}
// 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.v1p1beta1.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, but is
// required for all other audio formats. For details, see
// [AudioEncoding][google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding].
int32 sample_rate_hertz = 2;
// The number of channels in the input audio data.
// ONLY set this for MULTI-CHANNEL recognition.
// Valid values for LINEAR16, OGG_OPUS and FLAC are `1`-`8`.
// 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](https://cloud.google.com/speech-to-text/docs/languages) for a list
// of the currently supported language codes.
string language_code = 3 [(google.api.field_behavior) = REQUIRED];
// A list of up to 3 additional
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
// listing possible alternative languages of the supplied audio.
// See [Language
// Support](https://cloud.google.com/speech-to-text/docs/languages) for a list
// of the currently supported language codes. If alternative languages are
// listed, recognition result will contain recognition in the most likely
// language detected including the main language_code. The recognition result
// will include the language tag of the language detected in the audio. Note:
// This feature is only supported for Voice Command and Voice Search use cases
// and performance may vary for other use cases (e.g., phone call
// transcription).
repeated string alternative_language_codes = 18;
// 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;
// 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;
// Speech adaptation configuration improves the accuracy of speech
// recognition. For more information, see the [speech
// adaptation](https://cloud.google.com/speech-to-text/docs/adaptation)
// documentation.
// When speech adaptation is set it supersedes the `speech_contexts` field.
SpeechAdaptation adaptation = 20;
// Use transcription normalization to automatically replace parts of the
// transcript with phrases of your choosing. For StreamingRecognize, this
// normalization only applies to stable partial transcripts (stability > 0.8)
// and final transcripts.
TranscriptNormalization transcript_normalization = 24;
// Array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
// A means to provide context to assist the speech recognition. For more
// information, see
// [speech
// adaptation](https://cloud.google.com/speech-to-text/docs/adaptation).
repeated SpeechContext speech_contexts = 6;
// 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;
// If `true`, the top result includes a list of words and the
// confidence for those words. If `false`, no word-level confidence
// information is returned. The default is `false`.
bool enable_word_confidence = 15;
// 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.
bool enable_automatic_punctuation = 11;
// The spoken punctuation behavior for the call
// If not set, uses default behavior based on model of choice
// e.g. command_and_search will enable spoken punctuation by default
// If 'true', replaces spoken punctuation with the corresponding symbols in
// the request. For example, "how are you question mark" becomes "how are
// you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation
// for support. If 'false', spoken punctuation is not replaced.
google.protobuf.BoolValue enable_spoken_punctuation = 22;
// The spoken emoji behavior for the call
// If not set, uses default behavior based on model of choice
// If 'true', adds spoken emoji formatting for the request. This will replace
// spoken emojis with the corresponding Unicode symbols in the final
// transcript. If 'false', spoken emojis are not replaced.
google.protobuf.BoolValue enable_spoken_emojis = 23;
// If 'true', enables speaker detection for each recognized word in
// the top alternative of the recognition result using a speaker_tag provided
// in the WordInfo.
// Note: Use diarization_config instead.
bool enable_speaker_diarization = 16 [deprecated = true];
// If set, specifies the estimated number of speakers in the conversation.
// Defaults to '2'. Ignored unless enable_speaker_diarization is set to true.
// Note: Use diarization_config instead.
int32 diarization_speaker_count = 17 [deprecated = true];
// Config to enable speaker diarization and set additional
// parameters to make diarization better suited for your application.
// Note: When this is enabled, we send all the words from the beginning of the
// audio for the top alternative in every consecutive STREAMING responses.
// This is done in order to improve our speaker tags as our models learn to
// identify the speakers in the conversation over time.
// For non-streaming requests, the diarization results will be provided only
// in the top alternative of the FINAL SpeechRecognitionResult.
SpeakerDiarizationConfig diarization_config = 19;
// Metadata regarding this request.
RecognitionMetadata metadata = 9;
// 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.
//
//
//
Model
//
Description
//
//
//
latest_long
//
Best for long form content like media or conversation.
//
//
//
latest_short
//
Best for short form content like commands or single shot directed
// speech.
//
//
//
command_and_search
//
Best for short queries such as voice commands or voice search.
//
//
//
phone_call
//
Best for audio that originated from a phone call (typically
// recorded at an 8khz sampling rate).
//
//
//
video
//
Best for audio that originated 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.
//
//
//
default
//
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.
//
//
//
medical_conversation
//
Best for audio that originated from a conversation between a
// medical provider and patient.
//
//
//
medical_dictation
//
Best for audio that originated from dictation notes by a medical
// provider.
//
//
string model = 13;
// 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 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.
bool use_enhanced = 14;
}
// Config to enable speaker diarization.
message SpeakerDiarizationConfig {
// If 'true', enables speaker detection for each recognized word in
// the top alternative of the recognition result using a speaker_tag provided
// in the WordInfo.
bool enable_speaker_diarization = 1;
// Minimum number of speakers in the conversation. This range gives you more
// flexibility by allowing the system to automatically determine the correct
// number of speakers. If not set, the default value is 2.
int32 min_speaker_count = 2;
// Maximum number of speakers in the conversation. This range gives you more
// flexibility by allowing the system to automatically determine the correct
// number of speakers. If not set, the default value is 6.
int32 max_speaker_count = 3;
// Output only. Unused.
int32 speaker_tag = 5
[deprecated = true, (google.api.field_behavior) = OUTPUT_ONLY];
}
// Description of audio data to be recognized.
message RecognitionMetadata {
option deprecated = true;
// Use case categories that the audio recognition request can be described
// by.
enum InteractionType {
// Use case is either unknown or is something other than one of the other
// values below.
INTERACTION_TYPE_UNSPECIFIED = 0;
// Multiple people in a conversation or discussion. For example in a
// meeting with two or more people actively participating. Typically
// all the primary people speaking would be in the same room (if not,
// see PHONE_CALL)
DISCUSSION = 1;
// One or more persons lecturing or presenting to others, mostly
// uninterrupted.
PRESENTATION = 2;
// A phone-call or video-conference in which two or more people, who are
// not in the same room, are actively participating.
PHONE_CALL = 3;
// A recorded message intended for another person to listen to.
VOICEMAIL = 4;
// Professionally produced audio (eg. TV Show, Podcast).
PROFESSIONALLY_PRODUCED = 5;
// Transcribe spoken questions and queries into text.
VOICE_SEARCH = 6;
// Transcribe voice commands, such as for controlling a device.
VOICE_COMMAND = 7;
// Transcribe speech to text to create a written document, such as a
// text-message, email or report.
DICTATION = 8;
}
// Enumerates the types of capture settings describing an audio file.
enum MicrophoneDistance {
// Audio type is not known.
MICROPHONE_DISTANCE_UNSPECIFIED = 0;
// The audio was captured from a closely placed microphone. Eg. phone,
// dictaphone, or handheld microphone. Generally if there speaker is within
// 1 meter of the microphone.
NEARFIELD = 1;
// The speaker if within 3 meters of the microphone.
MIDFIELD = 2;
// The speaker is more than 3 meters away from the microphone.
FARFIELD = 3;
}
// The original media the speech was recorded on.
enum OriginalMediaType {
// Unknown original media type.
ORIGINAL_MEDIA_TYPE_UNSPECIFIED = 0;
// The speech data is an audio recording.
AUDIO = 1;
// The speech data originally recorded on a video.
VIDEO = 2;
}
// The type of device the speech was recorded with.
enum RecordingDeviceType {
// The recording device is unknown.
RECORDING_DEVICE_TYPE_UNSPECIFIED = 0;
// Speech was recorded on a smartphone.
SMARTPHONE = 1;
// Speech was recorded using a personal computer or tablet.
PC = 2;
// Speech was recorded over a phone line.
PHONE_LINE = 3;
// Speech was recorded in a vehicle.
VEHICLE = 4;
// Speech was recorded outdoors.
OTHER_OUTDOOR_DEVICE = 5;
// Speech was recorded indoors.
OTHER_INDOOR_DEVICE = 6;
}
// The use case most closely describing the audio content to be recognized.
InteractionType interaction_type = 1;
// The industry vertical to which this speech recognition request most
// closely applies. This is most indicative of the topics contained
// in the audio. Use the 6-digit NAICS code to identify the industry
// vertical - see https://www.naics.com/search/.
uint32 industry_naics_code_of_audio = 3;
// The audio type that most closely describes the audio being recognized.
MicrophoneDistance microphone_distance = 4;
// The original media the speech was recorded on.
OriginalMediaType original_media_type = 5;
// The type of device the speech was recorded with.
RecordingDeviceType recording_device_type = 6;
// The device used to make the recording. Examples 'Nexus 5X' or
// 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
// 'Cardioid Microphone'.
string recording_device_name = 7;
// Mime type of the original audio file. For example `audio/m4a`,
// `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`.
// A list of possible audio mime types is maintained at
// http://www.iana.org/assignments/media-types/media-types.xhtml#audio
string original_mime_type = 8;
// Obfuscated (privacy-protected) ID of the user, to identify number of
// unique users using the service.
int64 obfuscated_id = 9 [deprecated = true];
// Description of the content. Eg. "Recordings of federal supreme court
// hearings from 2012".
string audio_topic = 10;
}
// Provides "hints" to the speech recognizer to favor specific words and phrases
// in the results.
message SpeechContext {
// 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](https://cloud.google.com/speech-to-text/quotas#content).
//
// List items can also be set to classes for groups of words that represent
// common concepts that occur in natural language. For example, rather than
// providing phrase hints for every month of the year, using the $MONTH class
// improves the likelihood of correctly transcribing audio that includes
// months.
repeated string phrases = 1;
// Hint Boost. Positive value will increase the probability that a specific
// phrase will be recognized over other similar sounding phrases. The higher
// the boost, the higher the chance of false positive recognition as well.
// Negative boost values would correspond to anti-biasing. Anti-biasing is not
// enabled, so negative boost will simply be ignored. Though `boost` can
// accept a wide range of positive values, most use cases are best served with
// values between 0 and 20. We recommend using a binary search approach to
// finding the optimal value for your use case.
float boost = 4;
}
// 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](https://cloud.google.com/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, proto buffers 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 {
// Sequential list of transcription results corresponding to
// sequential portions of audio.
repeated SpeechRecognitionResult results = 2;
// When available, billed audio seconds for the corresponding request.
google.protobuf.Duration total_billed_time = 3;
// Provides information on adaptation behavior in response
SpeechAdaptationInfo speech_adaptation_info = 7;
// The ID associated with the request. This is a unique ID specific only to
// the given request.
int64 request_id = 8;
}
// 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 {
// Sequential list of transcription results corresponding to
// sequential portions of audio.
repeated SpeechRecognitionResult results = 2;
// When available, billed audio seconds for the corresponding request.
google.protobuf.Duration total_billed_time = 3;
// Original output config if present in the request.
TranscriptOutputConfig output_config = 6;
// If the transcript output fails this field contains the relevant error.
google.rpc.Status output_error = 7;
// Provides information on speech adaptation behavior in response
SpeechAdaptationInfo speech_adaptation_info = 8;
// The ID associated with the request. This is a unique ID specific only to
// the given request.
int64 request_id = 9;
}
// 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;
// Output only. The URI of the audio file being transcribed. Empty if the
// audio was sent as byte content.
string uri = 4 [(google.api.field_behavior) = OUTPUT_ONLY];
// Output only. A copy of the TranscriptOutputConfig if it was set in the
// request.
TranscriptOutputConfig output_config = 5
[(google.api.field_behavior) = OUTPUT_ONLY];
}
// `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 `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;
// This event indicates that the server has detected the beginning of human
// voice activity in the stream. This event can be returned multiple times
// if speech starts and stops repeatedly throughout the stream. This event
// is only sent if `voice_activity_events` is set to true.
SPEECH_ACTIVITY_BEGIN = 2;
// This event indicates that the server has detected the end of human voice
// activity in the stream. This event can be returned multiple times if
// speech starts and stops repeatedly throughout the stream. This event is
// only sent if `voice_activity_events` is set to true.
SPEECH_ACTIVITY_END = 3;
// This event indicates that the user-set timeout for speech activity begin
// or end has exceeded. Upon receiving this event, the client is expected to
// send a half close. Further audio will not be processed.
SPEECH_ACTIVITY_TIMEOUT = 4;
}
// If set, returns a [google.rpc.Status][google.rpc.Status] message that
// specifies the error for the operation.
google.rpc.Status error = 1;
// 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;
// Indicates the type of speech event.
SpeechEventType speech_event_type = 4;
// Time offset between the beginning of the audio and event emission.
google.protobuf.Duration speech_event_time = 8;
// When available, billed audio seconds for the stream.
// Set only if this is the last response in the stream.
google.protobuf.Duration total_billed_time = 5;
// Provides information on adaptation behavior in response
SpeechAdaptationInfo speech_adaptation_info = 9;
// The ID associated with the request. This is a unique ID specific only to
// the given request.
int64 request_id = 10;
}
// A streaming speech recognition result corresponding to a portion of the audio
// that is currently being processed.
message StreamingRecognitionResult {
// 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;
// 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;
// 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;
// Time offset of the end of this result relative to the
// beginning of the audio.
google.protobuf.Duration result_end_time = 4;
// 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;
// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
// language tag of the language in this result. This language code was
// detected to have the most likelihood of being spoken in the audio.
string language_code = 6 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// A speech recognition result corresponding to a portion of the audio.
message SpeechRecognitionResult {
// 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;
// Time offset of the end of this result relative to the
// beginning of the audio.
google.protobuf.Duration result_end_time = 4;
// Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
// language tag of the language in this result. This language code was
// detected to have the most likelihood of being spoken in the audio.
string language_code = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// Alternative hypotheses (a.k.a. n-best list).
message SpeechRecognitionAlternative {
// Transcript text representing the words that the user spoke.
// In languages that use spaces to separate words, the transcript might have a
// leading space if it isn't the first result. You can concatenate each result
// to obtain the full transcript without using a separator.
string transcript = 1;
// 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;
// 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 {
// 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;
// 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;
// The word corresponding to this set of information.
string word = 3;
// 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 = 4;
// Output only. A distinct integer value is assigned for every speaker within
// the audio. This field specifies which one of those speakers was detected to
// have spoken this word. Value ranges from '1' to diarization_speaker_count.
// speaker_tag is set if enable_speaker_diarization = 'true' and only in the
// top alternative.
int32 speaker_tag = 5 [(google.api.field_behavior) = OUTPUT_ONLY];
}
// Information on speech adaptation use in results
message SpeechAdaptationInfo {
// Whether there was a timeout when applying speech adaptation. If true,
// adaptation had no effect in the response transcript.
bool adaptation_timeout = 1;
// If set, returns a message specifying which part of the speech adaptation
// request timed out.
string timeout_message = 4;
}
