speech

package
v0.0.0-...-e165f0f Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Sep 1, 2020 License: Apache-2.0 Imports: 13 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

View Source 
var RecognitionConfig_AudioEncoding_name = map[int32]string{
	0: "ENCODING_UNSPECIFIED",
	1: "LINEAR16",
	2: "FLAC",
	3: "MULAW",
	4: "AMR",
	5: "AMR_WB",
	6: "OGG_OPUS",
	7: "SPEEX_WITH_HEADER_BYTE",
	8: "MP3",
}
View Source 
var RecognitionConfig_AudioEncoding_value = map[string]int32{
	"ENCODING_UNSPECIFIED":   0,
	"LINEAR16":               1,
	"FLAC":                   2,
	"MULAW":                  3,
	"AMR":                    4,
	"AMR_WB":                 5,
	"OGG_OPUS":               6,
	"SPEEX_WITH_HEADER_BYTE": 7,
	"MP3":                    8,
}
View Source 
var RecognitionMetadata_InteractionType_name = map[int32]string{
	0: "INTERACTION_TYPE_UNSPECIFIED",
	1: "DISCUSSION",
	2: "PRESENTATION",
	3: "PHONE_CALL",
	4: "VOICEMAIL",
	5: "PROFESSIONALLY_PRODUCED",
	6: "VOICE_SEARCH",
	7: "VOICE_COMMAND",
	8: "DICTATION",
}
View Source 
var RecognitionMetadata_InteractionType_value = map[string]int32{
	"INTERACTION_TYPE_UNSPECIFIED": 0,
	"DISCUSSION":                   1,
	"PRESENTATION":                 2,
	"PHONE_CALL":                   3,
	"VOICEMAIL":                    4,
	"PROFESSIONALLY_PRODUCED":      5,
	"VOICE_SEARCH":                 6,
	"VOICE_COMMAND":                7,
	"DICTATION":                    8,
}
View Source 
var RecognitionMetadata_MicrophoneDistance_name = map[int32]string{
	0: "MICROPHONE_DISTANCE_UNSPECIFIED",
	1: "NEARFIELD",
	2: "MIDFIELD",
	3: "FARFIELD",
}
View Source 
var RecognitionMetadata_MicrophoneDistance_value = map[string]int32{
	"MICROPHONE_DISTANCE_UNSPECIFIED": 0,
	"NEARFIELD":                       1,
	"MIDFIELD":                        2,
	"FARFIELD":                        3,
}
View Source 
var RecognitionMetadata_OriginalMediaType_name = map[int32]string{
	0: "ORIGINAL_MEDIA_TYPE_UNSPECIFIED",
	1: "AUDIO",
	2: "VIDEO",
}
View Source 
var RecognitionMetadata_OriginalMediaType_value = map[string]int32{
	"ORIGINAL_MEDIA_TYPE_UNSPECIFIED": 0,
	"AUDIO":                           1,
	"VIDEO":                           2,
}
View Source 
var RecognitionMetadata_RecordingDeviceType_name = map[int32]string{
	0: "RECORDING_DEVICE_TYPE_UNSPECIFIED",
	1: "SMARTPHONE",
	2: "PC",
	3: "PHONE_LINE",
	4: "VEHICLE",
	5: "OTHER_OUTDOOR_DEVICE",
	6: "OTHER_INDOOR_DEVICE",
}
View Source 
var RecognitionMetadata_RecordingDeviceType_value = map[string]int32{
	"RECORDING_DEVICE_TYPE_UNSPECIFIED": 0,
	"SMARTPHONE":                        1,
	"PC":                                2,
	"PHONE_LINE":                        3,
	"VEHICLE":                           4,
	"OTHER_OUTDOOR_DEVICE":              5,
	"OTHER_INDOOR_DEVICE":               6,
}
View Source 
var StreamingRecognizeResponse_SpeechEventType_name = map[int32]string{
	0: "SPEECH_EVENT_UNSPECIFIED",
	1: "END_OF_SINGLE_UTTERANCE",
}
View Source 
var StreamingRecognizeResponse_SpeechEventType_value = map[string]int32{
	"SPEECH_EVENT_UNSPECIFIED": 0,
	"END_OF_SINGLE_UTTERANCE":  1,
}

Functions

func RegisterSpeechServer 

func RegisterSpeechServer(s *grpc.Server, srv SpeechServer)

Types

type CustomClass 

type CustomClass struct {
	// The resource name of the custom class.
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	// If this custom class is a resource, the custom_class_id is the resource id
	// of the CustomClass.
	CustomClassId string `protobuf:"bytes,2,opt,name=custom_class_id,json=customClassId,proto3" json:"custom_class_id,omitempty"`
	// A collection of class items.
	Items                []*CustomClass_ClassItem `protobuf:"bytes,3,rep,name=items,proto3" json:"items,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                 `json:"-"`
	XXX_unrecognized     []byte                   `json:"-"`
	XXX_sizecache        int32                    `json:"-"`
}

A set of words or phrases that represents a common concept likely to appear in your audio, for example a list of passenger ship names. CustomClass items can be substituted into placeholders that you set in PhraseSet phrases.

func (*CustomClass) Descriptor 

func (*CustomClass) Descriptor() ([]byte, []int)

func (*CustomClass) GetCustomClassId 

func (m *CustomClass) GetCustomClassId() string

func (*CustomClass) GetItems 

func (m *CustomClass) GetItems() []*CustomClass_ClassItem

func (*CustomClass) GetName 

func (m *CustomClass) GetName() string

func (*CustomClass) ProtoMessage 

func (*CustomClass) ProtoMessage()

func (*CustomClass) Reset 

func (m *CustomClass) Reset()

func (*CustomClass) String 

func (m *CustomClass) String() string

func (*CustomClass) XXX_DiscardUnknown 

func (m *CustomClass) XXX_DiscardUnknown()

func (*CustomClass) XXX_Marshal 

func (m *CustomClass) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*CustomClass) XXX_Merge 

func (m *CustomClass) XXX_Merge(src proto.Message)

func (*CustomClass) XXX_Size 

func (m *CustomClass) XXX_Size() int

func (*CustomClass) XXX_Unmarshal 

func (m *CustomClass) XXX_Unmarshal(b []byte) error

type CustomClass_ClassItem 

type CustomClass_ClassItem struct {
	// The class item's value.
	Value                string   `protobuf:"bytes,1,opt,name=value,proto3" json:"value,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

An item of the class.

func (*CustomClass_ClassItem) Descriptor 

func (*CustomClass_ClassItem) Descriptor() ([]byte, []int)

func (*CustomClass_ClassItem) GetValue 

func (m *CustomClass_ClassItem) GetValue() string

func (*CustomClass_ClassItem) ProtoMessage 

func (*CustomClass_ClassItem) ProtoMessage()

func (*CustomClass_ClassItem) Reset 

func (m *CustomClass_ClassItem) Reset()

func (*CustomClass_ClassItem) String 

func (m *CustomClass_ClassItem) String() string

func (*CustomClass_ClassItem) XXX_DiscardUnknown 

func (m *CustomClass_ClassItem) XXX_DiscardUnknown()

func (*CustomClass_ClassItem) XXX_Marshal 

func (m *CustomClass_ClassItem) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*CustomClass_ClassItem) XXX_Merge 

func (m *CustomClass_ClassItem) XXX_Merge(src proto.Message)

func (*CustomClass_ClassItem) XXX_Size 

func (m *CustomClass_ClassItem) XXX_Size() int

func (*CustomClass_ClassItem) XXX_Unmarshal 

func (m *CustomClass_ClassItem) XXX_Unmarshal(b []byte) error

type LongRunningRecognizeMetadata 

type LongRunningRecognizeMetadata struct {
	// Approximate percentage of audio processed thus far. Guaranteed to be 100
	// when the audio is fully processed and the results are available.
	ProgressPercent int32 `protobuf:"varint,1,opt,name=progress_percent,json=progressPercent,proto3" json:"progress_percent,omitempty"`
	// Time when the request was received.
	StartTime *timestamp.Timestamp `protobuf:"bytes,2,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// Time of the most recent processing update.
	LastUpdateTime *timestamp.Timestamp `protobuf:"bytes,3,opt,name=last_update_time,json=lastUpdateTime,proto3" json:"last_update_time,omitempty"`
	// The URI of the audio file being transcribed. Empty if the audio was sent
	// as byte content.
	Uri                  string   `protobuf:"bytes,4,opt,name=uri,proto3" json:"uri,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

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.

func (*LongRunningRecognizeMetadata) Descriptor 

func (*LongRunningRecognizeMetadata) Descriptor() ([]byte, []int)

func (*LongRunningRecognizeMetadata) GetLastUpdateTime 

func (m *LongRunningRecognizeMetadata) GetLastUpdateTime() *timestamp.Timestamp

func (*LongRunningRecognizeMetadata) GetProgressPercent 

func (m *LongRunningRecognizeMetadata) GetProgressPercent() int32

func (*LongRunningRecognizeMetadata) GetStartTime 

func (m *LongRunningRecognizeMetadata) GetStartTime() *timestamp.Timestamp

func (*LongRunningRecognizeMetadata) GetUri 

func (m *LongRunningRecognizeMetadata) GetUri() string

func (*LongRunningRecognizeMetadata) ProtoMessage 

func (*LongRunningRecognizeMetadata) ProtoMessage()

func (*LongRunningRecognizeMetadata) Reset 

func (m *LongRunningRecognizeMetadata) Reset()

func (*LongRunningRecognizeMetadata) String 

func (m *LongRunningRecognizeMetadata) String() string

func (*LongRunningRecognizeMetadata) XXX_DiscardUnknown 

func (m *LongRunningRecognizeMetadata) XXX_DiscardUnknown()

func (*LongRunningRecognizeMetadata) XXX_Marshal 

func (m *LongRunningRecognizeMetadata) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*LongRunningRecognizeMetadata) XXX_Merge 

func (m *LongRunningRecognizeMetadata) XXX_Merge(src proto.Message)

func (*LongRunningRecognizeMetadata) XXX_Size 

func (m *LongRunningRecognizeMetadata) XXX_Size() int

func (*LongRunningRecognizeMetadata) XXX_Unmarshal 

func (m *LongRunningRecognizeMetadata) XXX_Unmarshal(b []byte) error

type LongRunningRecognizeRequest 

type LongRunningRecognizeRequest struct {
	// Required. Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
	// Required. The audio data to be recognized.
	Audio                *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3" json:"audio,omitempty"`
	XXX_NoUnkeyedLiteral struct{}          `json:"-"`
	XXX_unrecognized     []byte            `json:"-"`
	XXX_sizecache        int32             `json:"-"`
}

The top-level message sent by the client for the `LongRunningRecognize` method.

func (*LongRunningRecognizeRequest) Descriptor 

func (*LongRunningRecognizeRequest) Descriptor() ([]byte, []int)

func (*LongRunningRecognizeRequest) GetAudio 

func (m *LongRunningRecognizeRequest) GetAudio() *RecognitionAudio

func (*LongRunningRecognizeRequest) GetConfig 

func (m *LongRunningRecognizeRequest) GetConfig() *RecognitionConfig

func (*LongRunningRecognizeRequest) ProtoMessage 

func (*LongRunningRecognizeRequest) ProtoMessage()

func (*LongRunningRecognizeRequest) Reset 

func (m *LongRunningRecognizeRequest) Reset()

func (*LongRunningRecognizeRequest) String 

func (m *LongRunningRecognizeRequest) String() string

func (*LongRunningRecognizeRequest) XXX_DiscardUnknown 

func (m *LongRunningRecognizeRequest) XXX_DiscardUnknown()

func (*LongRunningRecognizeRequest) XXX_Marshal 

func (m *LongRunningRecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*LongRunningRecognizeRequest) XXX_Merge 

func (m *LongRunningRecognizeRequest) XXX_Merge(src proto.Message)

func (*LongRunningRecognizeRequest) XXX_Size 

func (m *LongRunningRecognizeRequest) XXX_Size() int

func (*LongRunningRecognizeRequest) XXX_Unmarshal 

func (m *LongRunningRecognizeRequest) XXX_Unmarshal(b []byte) error

type LongRunningRecognizeResponse 

type LongRunningRecognizeResponse struct {
	// Sequential list of transcription results corresponding to
	// sequential portions of audio.
	Results              []*SpeechRecognitionResult `protobuf:"bytes,2,rep,name=results,proto3" json:"results,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                   `json:"-"`
	XXX_unrecognized     []byte                     `json:"-"`
	XXX_sizecache        int32                      `json:"-"`
}

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.

func (*LongRunningRecognizeResponse) Descriptor 

func (*LongRunningRecognizeResponse) Descriptor() ([]byte, []int)

func (*LongRunningRecognizeResponse) GetResults 

func (m *LongRunningRecognizeResponse) GetResults() []*SpeechRecognitionResult

func (*LongRunningRecognizeResponse) ProtoMessage 

func (*LongRunningRecognizeResponse) ProtoMessage()

func (*LongRunningRecognizeResponse) Reset 

func (m *LongRunningRecognizeResponse) Reset()

func (*LongRunningRecognizeResponse) String 

func (m *LongRunningRecognizeResponse) String() string

func (*LongRunningRecognizeResponse) XXX_DiscardUnknown 

func (m *LongRunningRecognizeResponse) XXX_DiscardUnknown()

func (*LongRunningRecognizeResponse) XXX_Marshal 

func (m *LongRunningRecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*LongRunningRecognizeResponse) XXX_Merge 

func (m *LongRunningRecognizeResponse) XXX_Merge(src proto.Message)

func (*LongRunningRecognizeResponse) XXX_Size 

func (m *LongRunningRecognizeResponse) XXX_Size() int

func (*LongRunningRecognizeResponse) XXX_Unmarshal 

func (m *LongRunningRecognizeResponse) XXX_Unmarshal(b []byte) error

type PhraseSet 

type PhraseSet struct {
	// The resource name of the phrase set.
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	// A list of word and phrases.
	Phrases []*PhraseSet_Phrase `protobuf:"bytes,2,rep,name=phrases,proto3" json:"phrases,omitempty"`
	// 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 (exclusive) and 20. We recommend using a binary search
	// approach to finding the optimal value for your use case. Speech recognition
	// will skip PhraseSets with a boost value of 0.
	Boost                float32  `protobuf:"fixed32,4,opt,name=boost,proto3" json:"boost,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

Provides "hints" to the speech recognizer to favor specific words and phrases in the results.

func (*PhraseSet) Descriptor 

func (*PhraseSet) Descriptor() ([]byte, []int)

func (*PhraseSet) GetBoost 

func (m *PhraseSet) GetBoost() float32

func (*PhraseSet) GetName 

func (m *PhraseSet) GetName() string

func (*PhraseSet) GetPhrases 

func (m *PhraseSet) GetPhrases() []*PhraseSet_Phrase

func (*PhraseSet) ProtoMessage 

func (*PhraseSet) ProtoMessage()

func (*PhraseSet) Reset 

func (m *PhraseSet) Reset()

func (*PhraseSet) String 

func (m *PhraseSet) String() string

func (*PhraseSet) XXX_DiscardUnknown 

func (m *PhraseSet) XXX_DiscardUnknown()

func (*PhraseSet) XXX_Marshal 

func (m *PhraseSet) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*PhraseSet) XXX_Merge 

func (m *PhraseSet) XXX_Merge(src proto.Message)

func (*PhraseSet) XXX_Size 

func (m *PhraseSet) XXX_Size() int

func (*PhraseSet) XXX_Unmarshal 

func (m *PhraseSet) XXX_Unmarshal(b []byte) error

type PhraseSet_Phrase 

type PhraseSet_Phrase struct {
	// The phrase itself.
	Value string `protobuf:"bytes,1,opt,name=value,proto3" json:"value,omitempty"`
	// Hint Boost. Overrides the boost set at the phrase set level.
	// 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. Speech recognition
	// will skip PhraseSets with a boost value of 0.
	Boost                float32  `protobuf:"fixed32,2,opt,name=boost,proto3" json:"boost,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

A phrases containing words and phrase "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 include pre-built or custom classes containing groups of words that represent common concepts that occur in natural language. For example, rather than providing a phrase hint for every month of the year (e.g. "i was born in january", "i was born in febuary", ...), use the pre-built `$MONTH` class improves the likelihood of correctly transcribing audio that includes months (e.g. "i was born in $month"). To refer to pre-built classes, use the class' symbol prepended with `$` e.g. `$MONTH`. To refer to custom classes that were defined inline in the request, set the class's `custom_class_id` to a string unique to all class resources and inline classes. Then use the class' id wrapped in $`{...}` e.g. "${my-months}". To refer to custom classes resources, use the class' id wrapped in `${}` (e.g. `${my-months}`).

func (*PhraseSet_Phrase) Descriptor 

func (*PhraseSet_Phrase) Descriptor() ([]byte, []int)

func (*PhraseSet_Phrase) GetBoost 

func (m *PhraseSet_Phrase) GetBoost() float32

func (*PhraseSet_Phrase) GetValue 

func (m *PhraseSet_Phrase) GetValue() string

func (*PhraseSet_Phrase) ProtoMessage 

func (*PhraseSet_Phrase) ProtoMessage()

func (*PhraseSet_Phrase) Reset 

func (m *PhraseSet_Phrase) Reset()

func (*PhraseSet_Phrase) String 

func (m *PhraseSet_Phrase) String() string

func (*PhraseSet_Phrase) XXX_DiscardUnknown 

func (m *PhraseSet_Phrase) XXX_DiscardUnknown()

func (*PhraseSet_Phrase) XXX_Marshal 

func (m *PhraseSet_Phrase) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*PhraseSet_Phrase) XXX_Merge 

func (m *PhraseSet_Phrase) XXX_Merge(src proto.Message)

func (*PhraseSet_Phrase) XXX_Size 

func (m *PhraseSet_Phrase) XXX_Size() int

func (*PhraseSet_Phrase) XXX_Unmarshal 

func (m *PhraseSet_Phrase) XXX_Unmarshal(b []byte) error

type RecognitionAudio 

type RecognitionAudio struct {
	// The audio source, which is either inline content or a Google Cloud
	// Storage uri.
	//
	// Types that are valid to be assigned to AudioSource:
	//	*RecognitionAudio_Content
	//	*RecognitionAudio_Uri
	AudioSource          isRecognitionAudio_AudioSource `protobuf_oneof:"audio_source"`
	XXX_NoUnkeyedLiteral struct{}                       `json:"-"`
	XXX_unrecognized     []byte                         `json:"-"`
	XXX_sizecache        int32                          `json:"-"`
}

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).

func (*RecognitionAudio) Descriptor 

func (*RecognitionAudio) Descriptor() ([]byte, []int)

func (*RecognitionAudio) GetAudioSource 

func (m *RecognitionAudio) GetAudioSource() isRecognitionAudio_AudioSource

func (*RecognitionAudio) GetContent 

func (m *RecognitionAudio) GetContent() []byte

func (*RecognitionAudio) GetUri 

func (m *RecognitionAudio) GetUri() string

func (*RecognitionAudio) ProtoMessage 

func (*RecognitionAudio) ProtoMessage()

func (*RecognitionAudio) Reset 

func (m *RecognitionAudio) Reset()

func (*RecognitionAudio) String 

func (m *RecognitionAudio) String() string

func (*RecognitionAudio) XXX_DiscardUnknown 

func (m *RecognitionAudio) XXX_DiscardUnknown()

func (*RecognitionAudio) XXX_Marshal 

func (m *RecognitionAudio) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*RecognitionAudio) XXX_Merge 

func (m *RecognitionAudio) XXX_Merge(src proto.Message)

func (*RecognitionAudio) XXX_OneofWrappers 

func (*RecognitionAudio) XXX_OneofWrappers() []interface{}

XXX_OneofWrappers is for the internal use of the proto package.

func (*RecognitionAudio) XXX_Size 

func (m *RecognitionAudio) XXX_Size() int

func (*RecognitionAudio) XXX_Unmarshal 

func (m *RecognitionAudio) XXX_Unmarshal(b []byte) error

type RecognitionAudio_Content 

type RecognitionAudio_Content struct {
	Content []byte `protobuf:"bytes,1,opt,name=content,proto3,oneof"`
}

type RecognitionAudio_Uri 

type RecognitionAudio_Uri struct {
	Uri string `protobuf:"bytes,2,opt,name=uri,proto3,oneof"`
}

type RecognitionConfig 

type RecognitionConfig struct {
	// 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].
	Encoding RecognitionConfig_AudioEncoding `` /* 137-byte string literal not displayed */
	// 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].
	SampleRateHertz int32 `protobuf:"varint,2,opt,name=sample_rate_hertz,json=sampleRateHertz,proto3" json:"sample_rate_hertz,omitempty"`
	// 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'.
	AudioChannelCount int32 `protobuf:"varint,7,opt,name=audio_channel_count,json=audioChannelCount,proto3" json:"audio_channel_count,omitempty"`
	// 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.
	EnableSeparateRecognitionPerChannel bool `` /* 174-byte string literal not displayed */
	// 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.
	LanguageCode string `protobuf:"bytes,3,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
	// 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).
	AlternativeLanguageCodes []string `` /* 136-byte string literal not displayed */
	// 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.
	MaxAlternatives int32 `protobuf:"varint,4,opt,name=max_alternatives,json=maxAlternatives,proto3" json:"max_alternatives,omitempty"`
	// 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.
	ProfanityFilter bool `protobuf:"varint,5,opt,name=profanity_filter,json=profanityFilter,proto3" json:"profanity_filter,omitempty"`
	// Speech adaptation configuration improves the accuracy of speech
	// recognition. When speech adaptation is set it supersedes the
	// `speech_contexts` field. For more information, see the [speech
	// adaptation](https://cloud.google.com/speech-to-text/docs/context-strength)
	// documentation.
	Adaptation *SpeechAdaptation `protobuf:"bytes,20,opt,name=adaptation,proto3" json:"adaptation,omitempty"`
	// 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/context-strength).
	SpeechContexts []*SpeechContext `protobuf:"bytes,6,rep,name=speech_contexts,json=speechContexts,proto3" json:"speech_contexts,omitempty"`
	// 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`.
	EnableWordTimeOffsets bool `` /* 129-byte string literal not displayed */
	// 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`.
	EnableWordConfidence bool `protobuf:"varint,15,opt,name=enable_word_confidence,json=enableWordConfidence,proto3" json:"enable_word_confidence,omitempty"`
	// 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.
	EnableAutomaticPunctuation bool `` /* 143-byte string literal not displayed */
	// 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.
	EnableSpeakerDiarization bool `` // Deprecated: Do not use.
	/* 137-byte string literal not displayed */
	// 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.
	DiarizationSpeakerCount int32 `` // Deprecated: Do not use.
	/* 134-byte string literal not displayed */
	// 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.
	DiarizationConfig *SpeakerDiarizationConfig `protobuf:"bytes,19,opt,name=diarization_config,json=diarizationConfig,proto3" json:"diarization_config,omitempty"`
	// Metadata regarding this request.
	Metadata *RecognitionMetadata `protobuf:"bytes,9,opt,name=metadata,proto3" json:"metadata,omitempty"`
	// 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>
	Model string `protobuf:"bytes,13,opt,name=model,proto3" json:"model,omitempty"`
	// 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.
	UseEnhanced          bool     `protobuf:"varint,14,opt,name=use_enhanced,json=useEnhanced,proto3" json:"use_enhanced,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

Provides information to the recognizer that specifies how to process the request.

func (*RecognitionConfig) Descriptor 

func (*RecognitionConfig) Descriptor() ([]byte, []int)

func (*RecognitionConfig) GetAdaptation 

func (m *RecognitionConfig) GetAdaptation() *SpeechAdaptation

func (*RecognitionConfig) GetAlternativeLanguageCodes 

func (m *RecognitionConfig) GetAlternativeLanguageCodes() []string

func (*RecognitionConfig) GetAudioChannelCount 

func (m *RecognitionConfig) GetAudioChannelCount() int32

func (*RecognitionConfig) GetDiarizationConfig 

func (m *RecognitionConfig) GetDiarizationConfig() *SpeakerDiarizationConfig

func (*RecognitionConfig) GetDiarizationSpeakerCount deprecated 

func (m *RecognitionConfig) GetDiarizationSpeakerCount() int32

Deprecated: Do not use.

func (*RecognitionConfig) GetEnableAutomaticPunctuation 

func (m *RecognitionConfig) GetEnableAutomaticPunctuation() bool

func (*RecognitionConfig) GetEnableSeparateRecognitionPerChannel 

func (m *RecognitionConfig) GetEnableSeparateRecognitionPerChannel() bool

func (*RecognitionConfig) GetEnableSpeakerDiarization deprecated 

func (m *RecognitionConfig) GetEnableSpeakerDiarization() bool

Deprecated: Do not use.

func (*RecognitionConfig) GetEnableWordConfidence 

func (m *RecognitionConfig) GetEnableWordConfidence() bool

func (*RecognitionConfig) GetEnableWordTimeOffsets 

func (m *RecognitionConfig) GetEnableWordTimeOffsets() bool

func (*RecognitionConfig) GetEncoding 

func (m *RecognitionConfig) GetEncoding() RecognitionConfig_AudioEncoding

func (*RecognitionConfig) GetLanguageCode 

func (m *RecognitionConfig) GetLanguageCode() string

func (*RecognitionConfig) GetMaxAlternatives 

func (m *RecognitionConfig) GetMaxAlternatives() int32

func (*RecognitionConfig) GetMetadata 

func (m *RecognitionConfig) GetMetadata() *RecognitionMetadata

func (*RecognitionConfig) GetModel 

func (m *RecognitionConfig) GetModel() string

func (*RecognitionConfig) GetProfanityFilter 

func (m *RecognitionConfig) GetProfanityFilter() bool

func (*RecognitionConfig) GetSampleRateHertz 

func (m *RecognitionConfig) GetSampleRateHertz() int32

func (*RecognitionConfig) GetSpeechContexts 

func (m *RecognitionConfig) GetSpeechContexts() []*SpeechContext

func (*RecognitionConfig) GetUseEnhanced 

func (m *RecognitionConfig) GetUseEnhanced() bool

func (*RecognitionConfig) ProtoMessage 

func (*RecognitionConfig) ProtoMessage()

func (*RecognitionConfig) Reset 

func (m *RecognitionConfig) Reset()

func (*RecognitionConfig) String 

func (m *RecognitionConfig) String() string

func (*RecognitionConfig) XXX_DiscardUnknown 

func (m *RecognitionConfig) XXX_DiscardUnknown()

func (*RecognitionConfig) XXX_Marshal 

func (m *RecognitionConfig) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*RecognitionConfig) XXX_Merge 

func (m *RecognitionConfig) XXX_Merge(src proto.Message)

func (*RecognitionConfig) XXX_Size 

func (m *RecognitionConfig) XXX_Size() int

func (*RecognitionConfig) XXX_Unmarshal 

func (m *RecognitionConfig) XXX_Unmarshal(b []byte) error

type RecognitionConfig_AudioEncoding 

type RecognitionConfig_AudioEncoding int32

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`, and `MP3`.

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. 

const (
	// Not specified.
	RecognitionConfig_ENCODING_UNSPECIFIED RecognitionConfig_AudioEncoding = 0
	// Uncompressed 16-bit signed little-endian samples (Linear PCM).
	RecognitionConfig_LINEAR16 RecognitionConfig_AudioEncoding = 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.
	RecognitionConfig_FLAC RecognitionConfig_AudioEncoding = 2
	// 8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.
	RecognitionConfig_MULAW RecognitionConfig_AudioEncoding = 3
	// Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.
	RecognitionConfig_AMR RecognitionConfig_AudioEncoding = 4
	// Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.
	RecognitionConfig_AMR_WB RecognitionConfig_AudioEncoding = 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.
	RecognitionConfig_OGG_OPUS RecognitionConfig_AudioEncoding = 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.
	RecognitionConfig_SPEEX_WITH_HEADER_BYTE RecognitionConfig_AudioEncoding = 7
	// MP3 audio. 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.
	RecognitionConfig_MP3 RecognitionConfig_AudioEncoding = 8
)

func (RecognitionConfig_AudioEncoding) EnumDescriptor 

func (RecognitionConfig_AudioEncoding) EnumDescriptor() ([]byte, []int)

func (RecognitionConfig_AudioEncoding) String 

func (x RecognitionConfig_AudioEncoding) String() string

type RecognitionMetadata 

type RecognitionMetadata struct {
	// The use case most closely describing the audio content to be recognized.
	InteractionType RecognitionMetadata_InteractionType `` /* 178-byte string literal not displayed */
	// 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/.
	IndustryNaicsCodeOfAudio uint32 `` /* 140-byte string literal not displayed */
	// The audio type that most closely describes the audio being recognized.
	MicrophoneDistance RecognitionMetadata_MicrophoneDistance `` /* 190-byte string literal not displayed */
	// The original media the speech was recorded on.
	OriginalMediaType RecognitionMetadata_OriginalMediaType `` /* 188-byte string literal not displayed */
	// The type of device the speech was recorded with.
	RecordingDeviceType RecognitionMetadata_RecordingDeviceType `` /* 196-byte string literal not displayed */
	// The device used to make the recording.  Examples 'Nexus 5X' or
	// 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
	// 'Cardioid Microphone'.
	RecordingDeviceName string `protobuf:"bytes,7,opt,name=recording_device_name,json=recordingDeviceName,proto3" json:"recording_device_name,omitempty"`
	// 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
	OriginalMimeType string `protobuf:"bytes,8,opt,name=original_mime_type,json=originalMimeType,proto3" json:"original_mime_type,omitempty"`
	// Obfuscated (privacy-protected) ID of the user, to identify number of
	// unique users using the service.
	ObfuscatedId int64 `protobuf:"varint,9,opt,name=obfuscated_id,json=obfuscatedId,proto3" json:"obfuscated_id,omitempty"` // Deprecated: Do not use.
	// Description of the content. Eg. "Recordings of federal supreme court
	// hearings from 2012".
	AudioTopic           string   `protobuf:"bytes,10,opt,name=audio_topic,json=audioTopic,proto3" json:"audio_topic,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

Description of audio data to be recognized.

func (*RecognitionMetadata) Descriptor 

func (*RecognitionMetadata) Descriptor() ([]byte, []int)

func (*RecognitionMetadata) GetAudioTopic 

func (m *RecognitionMetadata) GetAudioTopic() string

func (*RecognitionMetadata) GetIndustryNaicsCodeOfAudio 

func (m *RecognitionMetadata) GetIndustryNaicsCodeOfAudio() uint32

func (*RecognitionMetadata) GetInteractionType 

func (m *RecognitionMetadata) GetInteractionType() RecognitionMetadata_InteractionType

func (*RecognitionMetadata) GetMicrophoneDistance 

func (m *RecognitionMetadata) GetMicrophoneDistance() RecognitionMetadata_MicrophoneDistance

func (*RecognitionMetadata) GetObfuscatedId deprecated 

func (m *RecognitionMetadata) GetObfuscatedId() int64

Deprecated: Do not use.

func (*RecognitionMetadata) GetOriginalMediaType 

func (m *RecognitionMetadata) GetOriginalMediaType() RecognitionMetadata_OriginalMediaType

func (*RecognitionMetadata) GetOriginalMimeType 

func (m *RecognitionMetadata) GetOriginalMimeType() string

func (*RecognitionMetadata) GetRecordingDeviceName 

func (m *RecognitionMetadata) GetRecordingDeviceName() string

func (*RecognitionMetadata) GetRecordingDeviceType 

func (m *RecognitionMetadata) GetRecordingDeviceType() RecognitionMetadata_RecordingDeviceType

func (*RecognitionMetadata) ProtoMessage 

func (*RecognitionMetadata) ProtoMessage()

func (*RecognitionMetadata) Reset 

func (m *RecognitionMetadata) Reset()

func (*RecognitionMetadata) String 

func (m *RecognitionMetadata) String() string

func (*RecognitionMetadata) XXX_DiscardUnknown 

func (m *RecognitionMetadata) XXX_DiscardUnknown()

func (*RecognitionMetadata) XXX_Marshal 

func (m *RecognitionMetadata) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*RecognitionMetadata) XXX_Merge 

func (m *RecognitionMetadata) XXX_Merge(src proto.Message)

func (*RecognitionMetadata) XXX_Size 

func (m *RecognitionMetadata) XXX_Size() int

func (*RecognitionMetadata) XXX_Unmarshal 

func (m *RecognitionMetadata) XXX_Unmarshal(b []byte) error

type RecognitionMetadata_InteractionType 

type RecognitionMetadata_InteractionType int32

Use case categories that the audio recognition request can be described by. 

const (
	// Use case is either unknown or is something other than one of the other
	// values below.
	RecognitionMetadata_INTERACTION_TYPE_UNSPECIFIED RecognitionMetadata_InteractionType = 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)
	RecognitionMetadata_DISCUSSION RecognitionMetadata_InteractionType = 1
	// One or more persons lecturing or presenting to others, mostly
	// uninterrupted.
	RecognitionMetadata_PRESENTATION RecognitionMetadata_InteractionType = 2
	// A phone-call or video-conference in which two or more people, who are
	// not in the same room, are actively participating.
	RecognitionMetadata_PHONE_CALL RecognitionMetadata_InteractionType = 3
	// A recorded message intended for another person to listen to.
	RecognitionMetadata_VOICEMAIL RecognitionMetadata_InteractionType = 4
	// Professionally produced audio (eg. TV Show, Podcast).
	RecognitionMetadata_PROFESSIONALLY_PRODUCED RecognitionMetadata_InteractionType = 5
	// Transcribe spoken questions and queries into text.
	RecognitionMetadata_VOICE_SEARCH RecognitionMetadata_InteractionType = 6
	// Transcribe voice commands, such as for controlling a device.
	RecognitionMetadata_VOICE_COMMAND RecognitionMetadata_InteractionType = 7
	// Transcribe speech to text to create a written document, such as a
	// text-message, email or report.
	RecognitionMetadata_DICTATION RecognitionMetadata_InteractionType = 8
)

func (RecognitionMetadata_InteractionType) EnumDescriptor 

func (RecognitionMetadata_InteractionType) EnumDescriptor() ([]byte, []int)

func (RecognitionMetadata_InteractionType) String 

func (x RecognitionMetadata_InteractionType) String() string

type RecognitionMetadata_MicrophoneDistance 

type RecognitionMetadata_MicrophoneDistance int32

Enumerates the types of capture settings describing an audio file. 

const (
	// Audio type is not known.
	RecognitionMetadata_MICROPHONE_DISTANCE_UNSPECIFIED RecognitionMetadata_MicrophoneDistance = 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.
	RecognitionMetadata_NEARFIELD RecognitionMetadata_MicrophoneDistance = 1
	// The speaker if within 3 meters of the microphone.
	RecognitionMetadata_MIDFIELD RecognitionMetadata_MicrophoneDistance = 2
	// The speaker is more than 3 meters away from the microphone.
	RecognitionMetadata_FARFIELD RecognitionMetadata_MicrophoneDistance = 3
)

func (RecognitionMetadata_MicrophoneDistance) EnumDescriptor 

func (RecognitionMetadata_MicrophoneDistance) EnumDescriptor() ([]byte, []int)

func (RecognitionMetadata_MicrophoneDistance) String 

func (x RecognitionMetadata_MicrophoneDistance) String() string

type RecognitionMetadata_OriginalMediaType 

type RecognitionMetadata_OriginalMediaType int32

The original media the speech was recorded on. 

const (
	// Unknown original media type.
	RecognitionMetadata_ORIGINAL_MEDIA_TYPE_UNSPECIFIED RecognitionMetadata_OriginalMediaType = 0
	// The speech data is an audio recording.
	RecognitionMetadata_AUDIO RecognitionMetadata_OriginalMediaType = 1
	// The speech data originally recorded on a video.
	RecognitionMetadata_VIDEO RecognitionMetadata_OriginalMediaType = 2
)

func (RecognitionMetadata_OriginalMediaType) EnumDescriptor 

func (RecognitionMetadata_OriginalMediaType) EnumDescriptor() ([]byte, []int)

func (RecognitionMetadata_OriginalMediaType) String 

func (x RecognitionMetadata_OriginalMediaType) String() string

type RecognitionMetadata_RecordingDeviceType 

type RecognitionMetadata_RecordingDeviceType int32

The type of device the speech was recorded with. 

const (
	// The recording device is unknown.
	RecognitionMetadata_RECORDING_DEVICE_TYPE_UNSPECIFIED RecognitionMetadata_RecordingDeviceType = 0
	// Speech was recorded on a smartphone.
	RecognitionMetadata_SMARTPHONE RecognitionMetadata_RecordingDeviceType = 1
	// Speech was recorded using a personal computer or tablet.
	RecognitionMetadata_PC RecognitionMetadata_RecordingDeviceType = 2
	// Speech was recorded over a phone line.
	RecognitionMetadata_PHONE_LINE RecognitionMetadata_RecordingDeviceType = 3
	// Speech was recorded in a vehicle.
	RecognitionMetadata_VEHICLE RecognitionMetadata_RecordingDeviceType = 4
	// Speech was recorded outdoors.
	RecognitionMetadata_OTHER_OUTDOOR_DEVICE RecognitionMetadata_RecordingDeviceType = 5
	// Speech was recorded indoors.
	RecognitionMetadata_OTHER_INDOOR_DEVICE RecognitionMetadata_RecordingDeviceType = 6
)

func (RecognitionMetadata_RecordingDeviceType) EnumDescriptor 

func (RecognitionMetadata_RecordingDeviceType) EnumDescriptor() ([]byte, []int)

func (RecognitionMetadata_RecordingDeviceType) String 

func (x RecognitionMetadata_RecordingDeviceType) String() string

type RecognizeRequest 

type RecognizeRequest struct {
	// Required. Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
	// Required. The audio data to be recognized.
	Audio                *RecognitionAudio `protobuf:"bytes,2,opt,name=audio,proto3" json:"audio,omitempty"`
	XXX_NoUnkeyedLiteral struct{}          `json:"-"`
	XXX_unrecognized     []byte            `json:"-"`
	XXX_sizecache        int32             `json:"-"`
}

The top-level message sent by the client for the `Recognize` method.

func (*RecognizeRequest) Descriptor 

func (*RecognizeRequest) Descriptor() ([]byte, []int)

func (*RecognizeRequest) GetAudio 

func (m *RecognizeRequest) GetAudio() *RecognitionAudio

func (*RecognizeRequest) GetConfig 

func (m *RecognizeRequest) GetConfig() *RecognitionConfig

func (*RecognizeRequest) ProtoMessage 

func (*RecognizeRequest) ProtoMessage()

func (*RecognizeRequest) Reset 

func (m *RecognizeRequest) Reset()

func (*RecognizeRequest) String 

func (m *RecognizeRequest) String() string

func (*RecognizeRequest) XXX_DiscardUnknown 

func (m *RecognizeRequest) XXX_DiscardUnknown()

func (*RecognizeRequest) XXX_Marshal 

func (m *RecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*RecognizeRequest) XXX_Merge 

func (m *RecognizeRequest) XXX_Merge(src proto.Message)

func (*RecognizeRequest) XXX_Size 

func (m *RecognizeRequest) XXX_Size() int

func (*RecognizeRequest) XXX_Unmarshal 

func (m *RecognizeRequest) XXX_Unmarshal(b []byte) error

type RecognizeResponse 

type RecognizeResponse struct {
	// Sequential list of transcription results corresponding to
	// sequential portions of audio.
	Results              []*SpeechRecognitionResult `protobuf:"bytes,2,rep,name=results,proto3" json:"results,omitempty"`
	XXX_NoUnkeyedLiteral struct{}                   `json:"-"`
	XXX_unrecognized     []byte                     `json:"-"`
	XXX_sizecache        int32                      `json:"-"`
}

The only message returned to the client by the `Recognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages.

func (*RecognizeResponse) Descriptor 

func (*RecognizeResponse) Descriptor() ([]byte, []int)

func (*RecognizeResponse) GetResults 

func (m *RecognizeResponse) GetResults() []*SpeechRecognitionResult

func (*RecognizeResponse) ProtoMessage 

func (*RecognizeResponse) ProtoMessage()

func (*RecognizeResponse) Reset 

func (m *RecognizeResponse) Reset()

func (*RecognizeResponse) String 

func (m *RecognizeResponse) String() string

func (*RecognizeResponse) XXX_DiscardUnknown 

func (m *RecognizeResponse) XXX_DiscardUnknown()

func (*RecognizeResponse) XXX_Marshal 

func (m *RecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*RecognizeResponse) XXX_Merge 

func (m *RecognizeResponse) XXX_Merge(src proto.Message)

func (*RecognizeResponse) XXX_Size 

func (m *RecognizeResponse) XXX_Size() int

func (*RecognizeResponse) XXX_Unmarshal 

func (m *RecognizeResponse) XXX_Unmarshal(b []byte) error

type SpeakerDiarizationConfig 

type SpeakerDiarizationConfig struct {
	// 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.
	EnableSpeakerDiarization bool `` /* 136-byte string literal not displayed */
	// 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.
	MinSpeakerCount int32 `protobuf:"varint,2,opt,name=min_speaker_count,json=minSpeakerCount,proto3" json:"min_speaker_count,omitempty"`
	// 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.
	MaxSpeakerCount int32 `protobuf:"varint,3,opt,name=max_speaker_count,json=maxSpeakerCount,proto3" json:"max_speaker_count,omitempty"`
	// Output only. Unused.
	SpeakerTag           int32    `protobuf:"varint,5,opt,name=speaker_tag,json=speakerTag,proto3" json:"speaker_tag,omitempty"` // Deprecated: Do not use.
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

Config to enable speaker diarization.

func (*SpeakerDiarizationConfig) Descriptor 

func (*SpeakerDiarizationConfig) Descriptor() ([]byte, []int)

func (*SpeakerDiarizationConfig) GetEnableSpeakerDiarization 

func (m *SpeakerDiarizationConfig) GetEnableSpeakerDiarization() bool

func (*SpeakerDiarizationConfig) GetMaxSpeakerCount 

func (m *SpeakerDiarizationConfig) GetMaxSpeakerCount() int32

func (*SpeakerDiarizationConfig) GetMinSpeakerCount 

func (m *SpeakerDiarizationConfig) GetMinSpeakerCount() int32

func (*SpeakerDiarizationConfig) GetSpeakerTag deprecated 

func (m *SpeakerDiarizationConfig) GetSpeakerTag() int32

Deprecated: Do not use.

func (*SpeakerDiarizationConfig) ProtoMessage 

func (*SpeakerDiarizationConfig) ProtoMessage()

func (*SpeakerDiarizationConfig) Reset 

func (m *SpeakerDiarizationConfig) Reset()

func (*SpeakerDiarizationConfig) String 

func (m *SpeakerDiarizationConfig) String() string

func (*SpeakerDiarizationConfig) XXX_DiscardUnknown 

func (m *SpeakerDiarizationConfig) XXX_DiscardUnknown()

func (*SpeakerDiarizationConfig) XXX_Marshal 

func (m *SpeakerDiarizationConfig) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*SpeakerDiarizationConfig) XXX_Merge 

func (m *SpeakerDiarizationConfig) XXX_Merge(src proto.Message)

func (*SpeakerDiarizationConfig) XXX_Size 

func (m *SpeakerDiarizationConfig) XXX_Size() int

func (*SpeakerDiarizationConfig) XXX_Unmarshal 

func (m *SpeakerDiarizationConfig) XXX_Unmarshal(b []byte) error

type SpeechAdaptation 

type SpeechAdaptation struct {
	// A collection of phrase sets. To specify the hints inline, leave the
	// phrase set's `name` blank and fill in the rest of its fields. Any
	// phrase set can use any custom class.
	PhraseSets []*PhraseSet `protobuf:"bytes,1,rep,name=phrase_sets,json=phraseSets,proto3" json:"phrase_sets,omitempty"`
	// A collection of custom classes. To specify the classes inline, leave the
	// class' `name` blank and fill in the rest of its fields, giving it a unique
	// `custom_class_id`. Refer to the inline defined class in phrase hints by its
	// `custom_class_id`.
	CustomClasses        []*CustomClass `protobuf:"bytes,2,rep,name=custom_classes,json=customClasses,proto3" json:"custom_classes,omitempty"`
	XXX_NoUnkeyedLiteral struct{}       `json:"-"`
	XXX_unrecognized     []byte         `json:"-"`
	XXX_sizecache        int32          `json:"-"`
}

Speech adaptation configuration.

func (*SpeechAdaptation) Descriptor 

func (*SpeechAdaptation) Descriptor() ([]byte, []int)

func (*SpeechAdaptation) GetCustomClasses 

func (m *SpeechAdaptation) GetCustomClasses() []*CustomClass

func (*SpeechAdaptation) GetPhraseSets 

func (m *SpeechAdaptation) GetPhraseSets() []*PhraseSet

func (*SpeechAdaptation) ProtoMessage 

func (*SpeechAdaptation) ProtoMessage()

func (*SpeechAdaptation) Reset 

func (m *SpeechAdaptation) Reset()

func (*SpeechAdaptation) String 

func (m *SpeechAdaptation) String() string

func (*SpeechAdaptation) XXX_DiscardUnknown 

func (m *SpeechAdaptation) XXX_DiscardUnknown()

func (*SpeechAdaptation) XXX_Marshal 

func (m *SpeechAdaptation) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*SpeechAdaptation) XXX_Merge 

func (m *SpeechAdaptation) XXX_Merge(src proto.Message)

func (*SpeechAdaptation) XXX_Size 

func (m *SpeechAdaptation) XXX_Size() int

func (*SpeechAdaptation) XXX_Unmarshal 

func (m *SpeechAdaptation) XXX_Unmarshal(b []byte) error

type SpeechClient 

type SpeechClient interface {
	// Performs synchronous speech recognition: receive results after all audio
	// has been sent and processed.
	Recognize(ctx context.Context, in *RecognizeRequest, opts ...grpc.CallOption) (*RecognizeResponse, error)
	// 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).
	LongRunningRecognize(ctx context.Context, in *LongRunningRecognizeRequest, opts ...grpc.CallOption) (*longrunning.Operation, error)
	// Performs bidirectional streaming speech recognition: receive results while
	// sending audio. This method is only available via the gRPC API (not REST).
	StreamingRecognize(ctx context.Context, opts ...grpc.CallOption) (Speech_StreamingRecognizeClient, error)
}

SpeechClient is the client API for Speech service.

For semantics around ctx use and closing/ending streaming RPCs, please refer to https://godoc.org/google.golang.org/grpc#ClientConn.NewStream.

func NewSpeechClient 

func NewSpeechClient(cc grpc.ClientConnInterface) SpeechClient

type SpeechContext 

type SpeechContext struct {
	// 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.
	Phrases []string `protobuf:"bytes,1,rep,name=phrases,proto3" json:"phrases,omitempty"`
	// 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.
	Boost                float32  `protobuf:"fixed32,4,opt,name=boost,proto3" json:"boost,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

Provides "hints" to the speech recognizer to favor specific words and phrases in the results.

func (*SpeechContext) Descriptor 

func (*SpeechContext) Descriptor() ([]byte, []int)

func (*SpeechContext) GetBoost 

func (m *SpeechContext) GetBoost() float32

func (*SpeechContext) GetPhrases 

func (m *SpeechContext) GetPhrases() []string

func (*SpeechContext) ProtoMessage 

func (*SpeechContext) ProtoMessage()

func (*SpeechContext) Reset 

func (m *SpeechContext) Reset()

func (*SpeechContext) String 

func (m *SpeechContext) String() string

func (*SpeechContext) XXX_DiscardUnknown 

func (m *SpeechContext) XXX_DiscardUnknown()

func (*SpeechContext) XXX_Marshal 

func (m *SpeechContext) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*SpeechContext) XXX_Merge 

func (m *SpeechContext) XXX_Merge(src proto.Message)

func (*SpeechContext) XXX_Size 

func (m *SpeechContext) XXX_Size() int

func (*SpeechContext) XXX_Unmarshal 

func (m *SpeechContext) XXX_Unmarshal(b []byte) error

type SpeechRecognitionAlternative 

type SpeechRecognitionAlternative struct {
	// Transcript text representing the words that the user spoke.
	Transcript string `protobuf:"bytes,1,opt,name=transcript,proto3" json:"transcript,omitempty"`
	// 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.
	Confidence float32 `protobuf:"fixed32,2,opt,name=confidence,proto3" json:"confidence,omitempty"`
	// 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.
	Words                []*WordInfo `protobuf:"bytes,3,rep,name=words,proto3" json:"words,omitempty"`
	XXX_NoUnkeyedLiteral struct{}    `json:"-"`
	XXX_unrecognized     []byte      `json:"-"`
	XXX_sizecache        int32       `json:"-"`
}

Alternative hypotheses (a.k.a. n-best list).

func (*SpeechRecognitionAlternative) Descriptor 

func (*SpeechRecognitionAlternative) Descriptor() ([]byte, []int)

func (*SpeechRecognitionAlternative) GetConfidence 

func (m *SpeechRecognitionAlternative) GetConfidence() float32

func (*SpeechRecognitionAlternative) GetTranscript 

func (m *SpeechRecognitionAlternative) GetTranscript() string

func (*SpeechRecognitionAlternative) GetWords 

func (m *SpeechRecognitionAlternative) GetWords() []*WordInfo

func (*SpeechRecognitionAlternative) ProtoMessage 

func (*SpeechRecognitionAlternative) ProtoMessage()

func (*SpeechRecognitionAlternative) Reset 

func (m *SpeechRecognitionAlternative) Reset()

func (*SpeechRecognitionAlternative) String 

func (m *SpeechRecognitionAlternative) String() string

func (*SpeechRecognitionAlternative) XXX_DiscardUnknown 

func (m *SpeechRecognitionAlternative) XXX_DiscardUnknown()

func (*SpeechRecognitionAlternative) XXX_Marshal 

func (m *SpeechRecognitionAlternative) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*SpeechRecognitionAlternative) XXX_Merge 

func (m *SpeechRecognitionAlternative) XXX_Merge(src proto.Message)

func (*SpeechRecognitionAlternative) XXX_Size 

func (m *SpeechRecognitionAlternative) XXX_Size() int

func (*SpeechRecognitionAlternative) XXX_Unmarshal 

func (m *SpeechRecognitionAlternative) XXX_Unmarshal(b []byte) error

type SpeechRecognitionResult 

type SpeechRecognitionResult struct {
	// 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.
	Alternatives []*SpeechRecognitionAlternative `protobuf:"bytes,1,rep,name=alternatives,proto3" json:"alternatives,omitempty"`
	// 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'.
	ChannelTag int32 `protobuf:"varint,2,opt,name=channel_tag,json=channelTag,proto3" json:"channel_tag,omitempty"`
	// 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.
	LanguageCode         string   `protobuf:"bytes,5,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

A speech recognition result corresponding to a portion of the audio.

func (*SpeechRecognitionResult) Descriptor 

func (*SpeechRecognitionResult) Descriptor() ([]byte, []int)

func (*SpeechRecognitionResult) GetAlternatives 

func (m *SpeechRecognitionResult) GetAlternatives() []*SpeechRecognitionAlternative

func (*SpeechRecognitionResult) GetChannelTag 

func (m *SpeechRecognitionResult) GetChannelTag() int32

func (*SpeechRecognitionResult) GetLanguageCode 

func (m *SpeechRecognitionResult) GetLanguageCode() string

func (*SpeechRecognitionResult) ProtoMessage 

func (*SpeechRecognitionResult) ProtoMessage()

func (*SpeechRecognitionResult) Reset 

func (m *SpeechRecognitionResult) Reset()

func (*SpeechRecognitionResult) String 

func (m *SpeechRecognitionResult) String() string

func (*SpeechRecognitionResult) XXX_DiscardUnknown 

func (m *SpeechRecognitionResult) XXX_DiscardUnknown()

func (*SpeechRecognitionResult) XXX_Marshal 

func (m *SpeechRecognitionResult) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*SpeechRecognitionResult) XXX_Merge 

func (m *SpeechRecognitionResult) XXX_Merge(src proto.Message)

func (*SpeechRecognitionResult) XXX_Size 

func (m *SpeechRecognitionResult) XXX_Size() int

func (*SpeechRecognitionResult) XXX_Unmarshal 

func (m *SpeechRecognitionResult) XXX_Unmarshal(b []byte) error

type SpeechServer 

type SpeechServer interface {
	// Performs synchronous speech recognition: receive results after all audio
	// has been sent and processed.
	Recognize(context.Context, *RecognizeRequest) (*RecognizeResponse, error)
	// 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).
	LongRunningRecognize(context.Context, *LongRunningRecognizeRequest) (*longrunning.Operation, error)
	// Performs bidirectional streaming speech recognition: receive results while
	// sending audio. This method is only available via the gRPC API (not REST).
	StreamingRecognize(Speech_StreamingRecognizeServer) error
}

SpeechServer is the server API for Speech service.

type Speech_StreamingRecognizeClient 

type Speech_StreamingRecognizeClient interface {
	Send(*StreamingRecognizeRequest) error
	Recv() (*StreamingRecognizeResponse, error)
	grpc.ClientStream
}

type Speech_StreamingRecognizeServer 

type Speech_StreamingRecognizeServer interface {
	Send(*StreamingRecognizeResponse) error
	Recv() (*StreamingRecognizeRequest, error)
	grpc.ServerStream
}

type StreamingRecognitionConfig 

type StreamingRecognitionConfig struct {
	// Required. Provides information to the recognizer that specifies how to
	// process the request.
	Config *RecognitionConfig `protobuf:"bytes,1,opt,name=config,proto3" json:"config,omitempty"`
	// 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`.
	SingleUtterance bool `protobuf:"varint,2,opt,name=single_utterance,json=singleUtterance,proto3" json:"single_utterance,omitempty"`
	// 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.
	InterimResults       bool     `protobuf:"varint,3,opt,name=interim_results,json=interimResults,proto3" json:"interim_results,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

Provides information to the recognizer that specifies how to process the request.

func (*StreamingRecognitionConfig) Descriptor 

func (*StreamingRecognitionConfig) Descriptor() ([]byte, []int)

func (*StreamingRecognitionConfig) GetConfig 

func (m *StreamingRecognitionConfig) GetConfig() *RecognitionConfig

func (*StreamingRecognitionConfig) GetInterimResults 

func (m *StreamingRecognitionConfig) GetInterimResults() bool

func (*StreamingRecognitionConfig) GetSingleUtterance 

func (m *StreamingRecognitionConfig) GetSingleUtterance() bool

func (*StreamingRecognitionConfig) ProtoMessage 

func (*StreamingRecognitionConfig) ProtoMessage()

func (*StreamingRecognitionConfig) Reset 

func (m *StreamingRecognitionConfig) Reset()

func (*StreamingRecognitionConfig) String 

func (m *StreamingRecognitionConfig) String() string

func (*StreamingRecognitionConfig) XXX_DiscardUnknown 

func (m *StreamingRecognitionConfig) XXX_DiscardUnknown()

func (*StreamingRecognitionConfig) XXX_Marshal 

func (m *StreamingRecognitionConfig) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*StreamingRecognitionConfig) XXX_Merge 

func (m *StreamingRecognitionConfig) XXX_Merge(src proto.Message)

func (*StreamingRecognitionConfig) XXX_Size 

func (m *StreamingRecognitionConfig) XXX_Size() int

func (*StreamingRecognitionConfig) XXX_Unmarshal 

func (m *StreamingRecognitionConfig) XXX_Unmarshal(b []byte) error

type StreamingRecognitionResult 

type StreamingRecognitionResult struct {
	// 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.
	Alternatives []*SpeechRecognitionAlternative `protobuf:"bytes,1,rep,name=alternatives,proto3" json:"alternatives,omitempty"`
	// 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.
	IsFinal bool `protobuf:"varint,2,opt,name=is_final,json=isFinal,proto3" json:"is_final,omitempty"`
	// 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.
	Stability float32 `protobuf:"fixed32,3,opt,name=stability,proto3" json:"stability,omitempty"`
	// Time offset of the end of this result relative to the
	// beginning of the audio.
	ResultEndTime *duration.Duration `protobuf:"bytes,4,opt,name=result_end_time,json=resultEndTime,proto3" json:"result_end_time,omitempty"`
	// 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'.
	ChannelTag int32 `protobuf:"varint,5,opt,name=channel_tag,json=channelTag,proto3" json:"channel_tag,omitempty"`
	// 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.
	LanguageCode         string   `protobuf:"bytes,6,opt,name=language_code,json=languageCode,proto3" json:"language_code,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

A streaming speech recognition result corresponding to a portion of the audio that is currently being processed.

func (*StreamingRecognitionResult) Descriptor 

func (*StreamingRecognitionResult) Descriptor() ([]byte, []int)

func (*StreamingRecognitionResult) GetAlternatives 

func (m *StreamingRecognitionResult) GetAlternatives() []*SpeechRecognitionAlternative

func (*StreamingRecognitionResult) GetChannelTag 

func (m *StreamingRecognitionResult) GetChannelTag() int32

func (*StreamingRecognitionResult) GetIsFinal 

func (m *StreamingRecognitionResult) GetIsFinal() bool

func (*StreamingRecognitionResult) GetLanguageCode 

func (m *StreamingRecognitionResult) GetLanguageCode() string

func (*StreamingRecognitionResult) GetResultEndTime 

func (m *StreamingRecognitionResult) GetResultEndTime() *duration.Duration

func (*StreamingRecognitionResult) GetStability 

func (m *StreamingRecognitionResult) GetStability() float32

func (*StreamingRecognitionResult) ProtoMessage 

func (*StreamingRecognitionResult) ProtoMessage()

func (*StreamingRecognitionResult) Reset 

func (m *StreamingRecognitionResult) Reset()

func (*StreamingRecognitionResult) String 

func (m *StreamingRecognitionResult) String() string

func (*StreamingRecognitionResult) XXX_DiscardUnknown 

func (m *StreamingRecognitionResult) XXX_DiscardUnknown()

func (*StreamingRecognitionResult) XXX_Marshal 

func (m *StreamingRecognitionResult) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*StreamingRecognitionResult) XXX_Merge 

func (m *StreamingRecognitionResult) XXX_Merge(src proto.Message)

func (*StreamingRecognitionResult) XXX_Size 

func (m *StreamingRecognitionResult) XXX_Size() int

func (*StreamingRecognitionResult) XXX_Unmarshal 

func (m *StreamingRecognitionResult) XXX_Unmarshal(b []byte) error

type StreamingRecognizeRequest 

type StreamingRecognizeRequest struct {
	// The streaming request, which is either a streaming config or audio content.
	//
	// Types that are valid to be assigned to StreamingRequest:
	//	*StreamingRecognizeRequest_StreamingConfig
	//	*StreamingRecognizeRequest_AudioContent
	StreamingRequest     isStreamingRecognizeRequest_StreamingRequest `protobuf_oneof:"streaming_request"`
	XXX_NoUnkeyedLiteral struct{}                                     `json:"-"`
	XXX_unrecognized     []byte                                       `json:"-"`
	XXX_sizecache        int32                                        `json:"-"`
}

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.

func (*StreamingRecognizeRequest) Descriptor 

func (*StreamingRecognizeRequest) Descriptor() ([]byte, []int)

func (*StreamingRecognizeRequest) GetAudioContent 

func (m *StreamingRecognizeRequest) GetAudioContent() []byte

func (*StreamingRecognizeRequest) GetStreamingConfig 

func (m *StreamingRecognizeRequest) GetStreamingConfig() *StreamingRecognitionConfig

func (*StreamingRecognizeRequest) GetStreamingRequest 

func (m *StreamingRecognizeRequest) GetStreamingRequest() isStreamingRecognizeRequest_StreamingRequest

func (*StreamingRecognizeRequest) ProtoMessage 

func (*StreamingRecognizeRequest) ProtoMessage()

func (*StreamingRecognizeRequest) Reset 

func (m *StreamingRecognizeRequest) Reset()

func (*StreamingRecognizeRequest) String 

func (m *StreamingRecognizeRequest) String() string

func (*StreamingRecognizeRequest) XXX_DiscardUnknown 

func (m *StreamingRecognizeRequest) XXX_DiscardUnknown()

func (*StreamingRecognizeRequest) XXX_Marshal 

func (m *StreamingRecognizeRequest) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*StreamingRecognizeRequest) XXX_Merge 

func (m *StreamingRecognizeRequest) XXX_Merge(src proto.Message)

func (*StreamingRecognizeRequest) XXX_OneofWrappers 

func (*StreamingRecognizeRequest) XXX_OneofWrappers() []interface{}

XXX_OneofWrappers is for the internal use of the proto package.

func (*StreamingRecognizeRequest) XXX_Size 

func (m *StreamingRecognizeRequest) XXX_Size() int

func (*StreamingRecognizeRequest) XXX_Unmarshal 

func (m *StreamingRecognizeRequest) XXX_Unmarshal(b []byte) error

type StreamingRecognizeRequest_AudioContent 

type StreamingRecognizeRequest_AudioContent struct {
	AudioContent []byte `protobuf:"bytes,2,opt,name=audio_content,json=audioContent,proto3,oneof"`
}

type StreamingRecognizeRequest_StreamingConfig 

type StreamingRecognizeRequest_StreamingConfig struct {
	StreamingConfig *StreamingRecognitionConfig `protobuf:"bytes,1,opt,name=streaming_config,json=streamingConfig,proto3,oneof"`
}

type StreamingRecognizeResponse 

type StreamingRecognizeResponse struct {
	// If set, returns a [google.rpc.Status][google.rpc.Status] message that
	// specifies the error for the operation.
	Error *status.Status `protobuf:"bytes,1,opt,name=error,proto3" json:"error,omitempty"`
	// 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).
	Results []*StreamingRecognitionResult `protobuf:"bytes,2,rep,name=results,proto3" json:"results,omitempty"`
	// Indicates the type of speech event.
	SpeechEventType      StreamingRecognizeResponse_SpeechEventType `` /* 187-byte string literal not displayed */
	XXX_NoUnkeyedLiteral struct{}                                   `json:"-"`
	XXX_unrecognized     []byte                                     `json:"-"`
	XXX_sizecache        int32                                      `json:"-"`
}

`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 }

  1. results { alternatives { transcript: "to be" } stability: 0.9 } results { alternatives { transcript: " or not to be" } stability: 0.01 }
  1. 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 }

  1. results { alternatives { transcript: " that is" } stability: 0.9 } results { alternatives { transcript: " the question" } stability: 0.01 }
  1. 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`.

func (*StreamingRecognizeResponse) Descriptor 

func (*StreamingRecognizeResponse) Descriptor() ([]byte, []int)

func (*StreamingRecognizeResponse) GetError 

func (m *StreamingRecognizeResponse) GetError() *status.Status

func (*StreamingRecognizeResponse) GetResults 

func (m *StreamingRecognizeResponse) GetResults() []*StreamingRecognitionResult

func (*StreamingRecognizeResponse) GetSpeechEventType 

func (m *StreamingRecognizeResponse) GetSpeechEventType() StreamingRecognizeResponse_SpeechEventType

func (*StreamingRecognizeResponse) ProtoMessage 

func (*StreamingRecognizeResponse) ProtoMessage()

func (*StreamingRecognizeResponse) Reset 

func (m *StreamingRecognizeResponse) Reset()

func (*StreamingRecognizeResponse) String 

func (m *StreamingRecognizeResponse) String() string

func (*StreamingRecognizeResponse) XXX_DiscardUnknown 

func (m *StreamingRecognizeResponse) XXX_DiscardUnknown()

func (*StreamingRecognizeResponse) XXX_Marshal 

func (m *StreamingRecognizeResponse) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*StreamingRecognizeResponse) XXX_Merge 

func (m *StreamingRecognizeResponse) XXX_Merge(src proto.Message)

func (*StreamingRecognizeResponse) XXX_Size 

func (m *StreamingRecognizeResponse) XXX_Size() int

func (*StreamingRecognizeResponse) XXX_Unmarshal 

func (m *StreamingRecognizeResponse) XXX_Unmarshal(b []byte) error

type StreamingRecognizeResponse_SpeechEventType 

type StreamingRecognizeResponse_SpeechEventType int32

Indicates the type of speech event. 

const (
	// No speech event specified.
	StreamingRecognizeResponse_SPEECH_EVENT_UNSPECIFIED StreamingRecognizeResponse_SpeechEventType = 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.
	StreamingRecognizeResponse_END_OF_SINGLE_UTTERANCE StreamingRecognizeResponse_SpeechEventType = 1
)

func (StreamingRecognizeResponse_SpeechEventType) EnumDescriptor 

func (StreamingRecognizeResponse_SpeechEventType) EnumDescriptor() ([]byte, []int)

func (StreamingRecognizeResponse_SpeechEventType) String 

func (x StreamingRecognizeResponse_SpeechEventType) String() string

type UnimplementedSpeechServer 

type UnimplementedSpeechServer struct {
}

UnimplementedSpeechServer can be embedded to have forward compatible implementations.

func (*UnimplementedSpeechServer) LongRunningRecognize 

func (*UnimplementedSpeechServer) LongRunningRecognize(ctx context.Context, req *LongRunningRecognizeRequest) (*longrunning.Operation, error)

func (*UnimplementedSpeechServer) Recognize 

func (*UnimplementedSpeechServer) Recognize(ctx context.Context, req *RecognizeRequest) (*RecognizeResponse, error)

func (*UnimplementedSpeechServer) StreamingRecognize 

func (*UnimplementedSpeechServer) StreamingRecognize(srv Speech_StreamingRecognizeServer) error

type WordInfo 

type WordInfo struct {
	// 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.
	StartTime *duration.Duration `protobuf:"bytes,1,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// 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.
	EndTime *duration.Duration `protobuf:"bytes,2,opt,name=end_time,json=endTime,proto3" json:"end_time,omitempty"`
	// The word corresponding to this set of information.
	Word string `protobuf:"bytes,3,opt,name=word,proto3" json:"word,omitempty"`
	// 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.
	Confidence float32 `protobuf:"fixed32,4,opt,name=confidence,proto3" json:"confidence,omitempty"`
	// 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.
	SpeakerTag           int32    `protobuf:"varint,5,opt,name=speaker_tag,json=speakerTag,proto3" json:"speaker_tag,omitempty"`
	XXX_NoUnkeyedLiteral struct{} `json:"-"`
	XXX_unrecognized     []byte   `json:"-"`
	XXX_sizecache        int32    `json:"-"`
}

Word-specific information for recognized words.

func (*WordInfo) Descriptor 

func (*WordInfo) Descriptor() ([]byte, []int)

func (*WordInfo) GetConfidence 

func (m *WordInfo) GetConfidence() float32

func (*WordInfo) GetEndTime 

func (m *WordInfo) GetEndTime() *duration.Duration

func (*WordInfo) GetSpeakerTag 

func (m *WordInfo) GetSpeakerTag() int32

func (*WordInfo) GetStartTime 

func (m *WordInfo) GetStartTime() *duration.Duration

func (*WordInfo) GetWord 

func (m *WordInfo) GetWord() string

func (*WordInfo) ProtoMessage 

func (*WordInfo) ProtoMessage()

func (*WordInfo) Reset 

func (m *WordInfo) Reset()

func (*WordInfo) String 

func (m *WordInfo) String() string

func (*WordInfo) XXX_DiscardUnknown 

func (m *WordInfo) XXX_DiscardUnknown()

func (*WordInfo) XXX_Marshal 

func (m *WordInfo) XXX_Marshal(b []byte, deterministic bool) ([]byte, error)

func (*WordInfo) XXX_Merge 

func (m *WordInfo) XXX_Merge(src proto.Message)

func (*WordInfo) XXX_Size 

func (m *WordInfo) XXX_Size() int

func (*WordInfo) XXX_Unmarshal 

func (m *WordInfo) XXX_Unmarshal(b []byte) error

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.