speech

package
Version: v0.0.0-...-b7c3a96 Latest Latest
Warning

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

Go to latest
Published: Oct 20, 2021 License: Apache-2.0 Imports: 15 Imported by: 128

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",
	}
	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,
	}
)

Enum value maps for RecognitionConfig_AudioEncoding.

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",
	}
	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,
	}
)

Enum value maps for RecognitionMetadata_InteractionType.

View Source
var (
	RecognitionMetadata_MicrophoneDistance_name = map[int32]string{
		0: "MICROPHONE_DISTANCE_UNSPECIFIED",
		1: "NEARFIELD",
		2: "MIDFIELD",
		3: "FARFIELD",
	}
	RecognitionMetadata_MicrophoneDistance_value = map[string]int32{
		"MICROPHONE_DISTANCE_UNSPECIFIED": 0,
		"NEARFIELD":                       1,
		"MIDFIELD":                        2,
		"FARFIELD":                        3,
	}
)

Enum value maps for RecognitionMetadata_MicrophoneDistance.

View Source
var (
	RecognitionMetadata_OriginalMediaType_name = map[int32]string{
		0: "ORIGINAL_MEDIA_TYPE_UNSPECIFIED",
		1: "AUDIO",
		2: "VIDEO",
	}
	RecognitionMetadata_OriginalMediaType_value = map[string]int32{
		"ORIGINAL_MEDIA_TYPE_UNSPECIFIED": 0,
		"AUDIO":                           1,
		"VIDEO":                           2,
	}
)

Enum value maps for RecognitionMetadata_OriginalMediaType.

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",
	}
	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,
	}
)

Enum value maps for RecognitionMetadata_RecordingDeviceType.

View Source
var (
	StreamingRecognizeResponse_SpeechEventType_name = map[int32]string{
		0: "SPEECH_EVENT_UNSPECIFIED",
		1: "END_OF_SINGLE_UTTERANCE",
	}
	StreamingRecognizeResponse_SpeechEventType_value = map[string]int32{
		"SPEECH_EVENT_UNSPECIFIED": 0,
		"END_OF_SINGLE_UTTERANCE":  1,
	}
)

Enum value maps for StreamingRecognizeResponse_SpeechEventType.

View Source
var File_google_cloud_speech_v1_cloud_speech_proto protoreflect.FileDescriptor

Functions

func RegisterSpeechServer

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

Types

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 *timestamppb.Timestamp `protobuf:"bytes,2,opt,name=start_time,json=startTime,proto3" json:"start_time,omitempty"`
	// Time of the most recent processing update.
	LastUpdateTime *timestamppb.Timestamp `protobuf:"bytes,3,opt,name=last_update_time,json=lastUpdateTime,proto3" json:"last_update_time,omitempty"`
	// Output only. 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"`
	// contains filtered or unexported fields
}

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 deprecated

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

Deprecated: Use LongRunningRecognizeMetadata.ProtoReflect.Descriptor instead.

func (*LongRunningRecognizeMetadata) GetLastUpdateTime

func (x *LongRunningRecognizeMetadata) GetLastUpdateTime() *timestamppb.Timestamp

func (*LongRunningRecognizeMetadata) GetProgressPercent

func (x *LongRunningRecognizeMetadata) GetProgressPercent() int32

func (*LongRunningRecognizeMetadata) GetStartTime

func (*LongRunningRecognizeMetadata) GetUri

func (*LongRunningRecognizeMetadata) ProtoMessage

func (*LongRunningRecognizeMetadata) ProtoMessage()

func (*LongRunningRecognizeMetadata) ProtoReflect

func (*LongRunningRecognizeMetadata) Reset

func (x *LongRunningRecognizeMetadata) Reset()

func (*LongRunningRecognizeMetadata) String

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"`
	// Optional. Specifies an optional destination for the recognition results.
	OutputConfig *TranscriptOutputConfig `protobuf:"bytes,4,opt,name=output_config,json=outputConfig,proto3" json:"output_config,omitempty"`
	// contains filtered or unexported fields
}

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

func (*LongRunningRecognizeRequest) Descriptor deprecated

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

Deprecated: Use LongRunningRecognizeRequest.ProtoReflect.Descriptor instead.

func (*LongRunningRecognizeRequest) GetAudio

func (*LongRunningRecognizeRequest) GetConfig

func (*LongRunningRecognizeRequest) GetOutputConfig

func (*LongRunningRecognizeRequest) ProtoMessage

func (*LongRunningRecognizeRequest) ProtoMessage()

func (*LongRunningRecognizeRequest) ProtoReflect

func (*LongRunningRecognizeRequest) Reset

func (x *LongRunningRecognizeRequest) Reset()

func (*LongRunningRecognizeRequest) String

func (x *LongRunningRecognizeRequest) String() string

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"`
	// When available, billed audio seconds for the corresponding request.
	TotalBilledTime *durationpb.Duration `protobuf:"bytes,3,opt,name=total_billed_time,json=totalBilledTime,proto3" json:"total_billed_time,omitempty"`
	// contains filtered or unexported fields
}

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 deprecated

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

Deprecated: Use LongRunningRecognizeResponse.ProtoReflect.Descriptor instead.

func (*LongRunningRecognizeResponse) GetResults

func (*LongRunningRecognizeResponse) GetTotalBilledTime

func (x *LongRunningRecognizeResponse) GetTotalBilledTime() *durationpb.Duration

func (*LongRunningRecognizeResponse) ProtoMessage

func (*LongRunningRecognizeResponse) ProtoMessage()

func (*LongRunningRecognizeResponse) ProtoReflect

func (*LongRunningRecognizeResponse) Reset

func (x *LongRunningRecognizeResponse) Reset()

func (*LongRunningRecognizeResponse) String

type RecognitionAudio

type RecognitionAudio struct {

	// The audio source, which is either inline content or a Google Cloud
	// Storage uri.
	//
	// Types that are assignable to AudioSource:
	//	*RecognitionAudio_Content
	//	*RecognitionAudio_Uri
	AudioSource isRecognitionAudio_AudioSource `protobuf_oneof:"audio_source"`
	// contains filtered or unexported fields
}

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 deprecated

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

Deprecated: Use RecognitionAudio.ProtoReflect.Descriptor instead.

func (*RecognitionAudio) GetAudioSource

func (m *RecognitionAudio) GetAudioSource() isRecognitionAudio_AudioSource

func (*RecognitionAudio) GetContent

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

func (*RecognitionAudio) GetUri

func (x *RecognitionAudio) GetUri() string

func (*RecognitionAudio) ProtoMessage

func (*RecognitionAudio) ProtoMessage()

func (*RecognitionAudio) ProtoReflect

func (x *RecognitionAudio) ProtoReflect() protoreflect.Message

func (*RecognitionAudio) Reset

func (x *RecognitionAudio) Reset()

func (*RecognitionAudio) String

func (x *RecognitionAudio) String() string

type RecognitionAudio_Content

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

type RecognitionAudio_Uri

type RecognitionAudio_Uri struct {
	// 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).
	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.v1.RecognitionConfig.AudioEncoding].
	Encoding RecognitionConfig_AudioEncoding `` /* 130-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.v1.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"`
	// 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"`
	// Array of [SpeechContext][google.cloud.speech.v1.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).
	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', 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 */
	// 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 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"`
	// contains filtered or unexported fields
}

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

func (*RecognitionConfig) Descriptor deprecated

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

Deprecated: Use RecognitionConfig.ProtoReflect.Descriptor instead.

func (*RecognitionConfig) GetAudioChannelCount

func (x *RecognitionConfig) GetAudioChannelCount() int32

func (*RecognitionConfig) GetDiarizationConfig

func (x *RecognitionConfig) GetDiarizationConfig() *SpeakerDiarizationConfig

func (*RecognitionConfig) GetEnableAutomaticPunctuation

func (x *RecognitionConfig) GetEnableAutomaticPunctuation() bool

func (*RecognitionConfig) GetEnableSeparateRecognitionPerChannel

func (x *RecognitionConfig) GetEnableSeparateRecognitionPerChannel() bool

func (*RecognitionConfig) GetEnableWordTimeOffsets

func (x *RecognitionConfig) GetEnableWordTimeOffsets() bool

func (*RecognitionConfig) GetEncoding

func (*RecognitionConfig) GetLanguageCode

func (x *RecognitionConfig) GetLanguageCode() string

func (*RecognitionConfig) GetMaxAlternatives

func (x *RecognitionConfig) GetMaxAlternatives() int32

func (*RecognitionConfig) GetMetadata

func (x *RecognitionConfig) GetMetadata() *RecognitionMetadata

func (*RecognitionConfig) GetModel

func (x *RecognitionConfig) GetModel() string

func (*RecognitionConfig) GetProfanityFilter

func (x *RecognitionConfig) GetProfanityFilter() bool

func (*RecognitionConfig) GetSampleRateHertz

func (x *RecognitionConfig) GetSampleRateHertz() int32

func (*RecognitionConfig) GetSpeechContexts

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

func (*RecognitionConfig) GetUseEnhanced

func (x *RecognitionConfig) GetUseEnhanced() bool

func (*RecognitionConfig) ProtoMessage

func (*RecognitionConfig) ProtoMessage()

func (*RecognitionConfig) ProtoReflect

func (x *RecognitionConfig) ProtoReflect() protoreflect.Message

func (*RecognitionConfig) Reset

func (x *RecognitionConfig) Reset()

func (*RecognitionConfig) String

func (x *RecognitionConfig) String() string

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`, `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
)

func (RecognitionConfig_AudioEncoding) Descriptor

func (RecognitionConfig_AudioEncoding) Enum

func (RecognitionConfig_AudioEncoding) EnumDescriptor deprecated

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

Deprecated: Use RecognitionConfig_AudioEncoding.Descriptor instead.

func (RecognitionConfig_AudioEncoding) Number

func (RecognitionConfig_AudioEncoding) String

func (RecognitionConfig_AudioEncoding) Type

type RecognitionMetadata

type RecognitionMetadata struct {

	// The use case most closely describing the audio content to be recognized.
	InteractionType RecognitionMetadata_InteractionType `` /* 171-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 `` /* 183-byte string literal not displayed */
	// The original media the speech was recorded on.
	OriginalMediaType RecognitionMetadata_OriginalMediaType `` /* 181-byte string literal not displayed */
	// The type of device the speech was recorded with.
	RecordingDeviceType RecognitionMetadata_RecordingDeviceType `` /* 189-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"`
	// 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"`
	// contains filtered or unexported fields
}

Description of audio data to be recognized.

func (*RecognitionMetadata) Descriptor deprecated

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

Deprecated: Use RecognitionMetadata.ProtoReflect.Descriptor instead.

func (*RecognitionMetadata) GetAudioTopic

func (x *RecognitionMetadata) GetAudioTopic() string

func (*RecognitionMetadata) GetIndustryNaicsCodeOfAudio

func (x *RecognitionMetadata) GetIndustryNaicsCodeOfAudio() uint32

func (*RecognitionMetadata) GetInteractionType

func (*RecognitionMetadata) GetMicrophoneDistance

func (*RecognitionMetadata) GetOriginalMediaType

func (*RecognitionMetadata) GetOriginalMimeType

func (x *RecognitionMetadata) GetOriginalMimeType() string

func (*RecognitionMetadata) GetRecordingDeviceName

func (x *RecognitionMetadata) GetRecordingDeviceName() string

func (*RecognitionMetadata) GetRecordingDeviceType

func (*RecognitionMetadata) ProtoMessage

func (*RecognitionMetadata) ProtoMessage()

func (*RecognitionMetadata) ProtoReflect

func (x *RecognitionMetadata) ProtoReflect() protoreflect.Message

func (*RecognitionMetadata) Reset

func (x *RecognitionMetadata) Reset()

func (*RecognitionMetadata) String

func (x *RecognitionMetadata) String() string

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) Descriptor

func (RecognitionMetadata_InteractionType) Enum

func (RecognitionMetadata_InteractionType) EnumDescriptor deprecated

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

Deprecated: Use RecognitionMetadata_InteractionType.Descriptor instead.

func (RecognitionMetadata_InteractionType) Number

func (RecognitionMetadata_InteractionType) String

func (RecognitionMetadata_InteractionType) Type

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) Descriptor

func (RecognitionMetadata_MicrophoneDistance) Enum

func (RecognitionMetadata_MicrophoneDistance) EnumDescriptor deprecated

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

Deprecated: Use RecognitionMetadata_MicrophoneDistance.Descriptor instead.

func (RecognitionMetadata_MicrophoneDistance) Number

func (RecognitionMetadata_MicrophoneDistance) String

func (RecognitionMetadata_MicrophoneDistance) Type

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) Descriptor

func (RecognitionMetadata_OriginalMediaType) Enum

func (RecognitionMetadata_OriginalMediaType) EnumDescriptor deprecated

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

Deprecated: Use RecognitionMetadata_OriginalMediaType.Descriptor instead.

func (RecognitionMetadata_OriginalMediaType) Number

func (RecognitionMetadata_OriginalMediaType) String

func (RecognitionMetadata_OriginalMediaType) Type

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) Descriptor

func (RecognitionMetadata_RecordingDeviceType) Enum

func (RecognitionMetadata_RecordingDeviceType) EnumDescriptor deprecated

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

Deprecated: Use RecognitionMetadata_RecordingDeviceType.Descriptor instead.

func (RecognitionMetadata_RecordingDeviceType) Number

func (RecognitionMetadata_RecordingDeviceType) String

func (RecognitionMetadata_RecordingDeviceType) Type

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"`
	// contains filtered or unexported fields
}

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

func (*RecognizeRequest) Descriptor deprecated

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

Deprecated: Use RecognizeRequest.ProtoReflect.Descriptor instead.

func (*RecognizeRequest) GetAudio

func (x *RecognizeRequest) GetAudio() *RecognitionAudio

func (*RecognizeRequest) GetConfig

func (x *RecognizeRequest) GetConfig() *RecognitionConfig

func (*RecognizeRequest) ProtoMessage

func (*RecognizeRequest) ProtoMessage()

func (*RecognizeRequest) ProtoReflect

func (x *RecognizeRequest) ProtoReflect() protoreflect.Message

func (*RecognizeRequest) Reset

func (x *RecognizeRequest) Reset()

func (*RecognizeRequest) String

func (x *RecognizeRequest) String() string

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"`
	// When available, billed audio seconds for the corresponding request.
	TotalBilledTime *durationpb.Duration `protobuf:"bytes,3,opt,name=total_billed_time,json=totalBilledTime,proto3" json:"total_billed_time,omitempty"`
	// contains filtered or unexported fields
}

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 deprecated

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

Deprecated: Use RecognizeResponse.ProtoReflect.Descriptor instead.

func (*RecognizeResponse) GetResults

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

func (*RecognizeResponse) GetTotalBilledTime

func (x *RecognizeResponse) GetTotalBilledTime() *durationpb.Duration

func (*RecognizeResponse) ProtoMessage

func (*RecognizeResponse) ProtoMessage()

func (*RecognizeResponse) ProtoReflect

func (x *RecognizeResponse) ProtoReflect() protoreflect.Message

func (*RecognizeResponse) Reset

func (x *RecognizeResponse) Reset()

func (*RecognizeResponse) String

func (x *RecognizeResponse) String() string

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.
	//
	// Deprecated: Do not use.
	SpeakerTag int32 `protobuf:"varint,5,opt,name=speaker_tag,json=speakerTag,proto3" json:"speaker_tag,omitempty"`
	// contains filtered or unexported fields
}

Config to enable speaker diarization.

func (*SpeakerDiarizationConfig) Descriptor deprecated

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

Deprecated: Use SpeakerDiarizationConfig.ProtoReflect.Descriptor instead.

func (*SpeakerDiarizationConfig) GetEnableSpeakerDiarization

func (x *SpeakerDiarizationConfig) GetEnableSpeakerDiarization() bool

func (*SpeakerDiarizationConfig) GetMaxSpeakerCount

func (x *SpeakerDiarizationConfig) GetMaxSpeakerCount() int32

func (*SpeakerDiarizationConfig) GetMinSpeakerCount

func (x *SpeakerDiarizationConfig) GetMinSpeakerCount() int32

func (*SpeakerDiarizationConfig) GetSpeakerTag deprecated

func (x *SpeakerDiarizationConfig) GetSpeakerTag() int32

Deprecated: Do not use.

func (*SpeakerDiarizationConfig) ProtoMessage

func (*SpeakerDiarizationConfig) ProtoMessage()

func (*SpeakerDiarizationConfig) ProtoReflect

func (x *SpeakerDiarizationConfig) ProtoReflect() protoreflect.Message

func (*SpeakerDiarizationConfig) Reset

func (x *SpeakerDiarizationConfig) Reset()

func (*SpeakerDiarizationConfig) String

func (x *SpeakerDiarizationConfig) String() string

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"`
	// contains filtered or unexported fields
}

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

func (*SpeechContext) Descriptor deprecated

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

Deprecated: Use SpeechContext.ProtoReflect.Descriptor instead.

func (*SpeechContext) GetPhrases

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

func (*SpeechContext) ProtoMessage

func (*SpeechContext) ProtoMessage()

func (*SpeechContext) ProtoReflect

func (x *SpeechContext) ProtoReflect() protoreflect.Message

func (*SpeechContext) Reset

func (x *SpeechContext) Reset()

func (*SpeechContext) String

func (x *SpeechContext) String() string

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"`
	// contains filtered or unexported fields
}

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

func (*SpeechRecognitionAlternative) Descriptor deprecated

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

Deprecated: Use SpeechRecognitionAlternative.ProtoReflect.Descriptor instead.

func (*SpeechRecognitionAlternative) GetConfidence

func (x *SpeechRecognitionAlternative) GetConfidence() float32

func (*SpeechRecognitionAlternative) GetTranscript

func (x *SpeechRecognitionAlternative) GetTranscript() string

func (*SpeechRecognitionAlternative) GetWords

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

func (*SpeechRecognitionAlternative) ProtoMessage

func (*SpeechRecognitionAlternative) ProtoMessage()

func (*SpeechRecognitionAlternative) ProtoReflect

func (*SpeechRecognitionAlternative) Reset

func (x *SpeechRecognitionAlternative) Reset()

func (*SpeechRecognitionAlternative) String

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"`
	// contains filtered or unexported fields
}

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

func (*SpeechRecognitionResult) Descriptor deprecated

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

Deprecated: Use SpeechRecognitionResult.ProtoReflect.Descriptor instead.

func (*SpeechRecognitionResult) GetAlternatives

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

func (*SpeechRecognitionResult) GetChannelTag

func (x *SpeechRecognitionResult) GetChannelTag() int32

func (*SpeechRecognitionResult) ProtoMessage

func (*SpeechRecognitionResult) ProtoMessage()

func (*SpeechRecognitionResult) ProtoReflect

func (x *SpeechRecognitionResult) ProtoReflect() protoreflect.Message

func (*SpeechRecognitionResult) Reset

func (x *SpeechRecognitionResult) Reset()

func (*SpeechRecognitionResult) String

func (x *SpeechRecognitionResult) String() string

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`.
	//
	// 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`.
	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"`
	// contains filtered or unexported fields
}

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

func (*StreamingRecognitionConfig) Descriptor deprecated

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

Deprecated: Use StreamingRecognitionConfig.ProtoReflect.Descriptor instead.

func (*StreamingRecognitionConfig) GetConfig

func (*StreamingRecognitionConfig) GetInterimResults

func (x *StreamingRecognitionConfig) GetInterimResults() bool

func (*StreamingRecognitionConfig) GetSingleUtterance

func (x *StreamingRecognitionConfig) GetSingleUtterance() bool

func (*StreamingRecognitionConfig) ProtoMessage

func (*StreamingRecognitionConfig) ProtoMessage()

func (*StreamingRecognitionConfig) ProtoReflect

func (*StreamingRecognitionConfig) Reset

func (x *StreamingRecognitionConfig) Reset()

func (*StreamingRecognitionConfig) String

func (x *StreamingRecognitionConfig) String() string

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 *durationpb.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"`
	// 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"`
	// contains filtered or unexported fields
}

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

func (*StreamingRecognitionResult) Descriptor deprecated

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

Deprecated: Use StreamingRecognitionResult.ProtoReflect.Descriptor instead.

func (*StreamingRecognitionResult) GetAlternatives

func (*StreamingRecognitionResult) GetChannelTag

func (x *StreamingRecognitionResult) GetChannelTag() int32

func (*StreamingRecognitionResult) GetIsFinal

func (x *StreamingRecognitionResult) GetIsFinal() bool

func (*StreamingRecognitionResult) GetLanguageCode

func (x *StreamingRecognitionResult) GetLanguageCode() string

func (*StreamingRecognitionResult) GetResultEndTime

func (x *StreamingRecognitionResult) GetResultEndTime() *durationpb.Duration

func (*StreamingRecognitionResult) GetStability

func (x *StreamingRecognitionResult) GetStability() float32

func (*StreamingRecognitionResult) ProtoMessage

func (*StreamingRecognitionResult) ProtoMessage()

func (*StreamingRecognitionResult) ProtoReflect

func (*StreamingRecognitionResult) Reset

func (x *StreamingRecognitionResult) Reset()

func (*StreamingRecognitionResult) String

func (x *StreamingRecognitionResult) String() string

type StreamingRecognizeRequest

type StreamingRecognizeRequest struct {

	// The streaming request, which is either a streaming config or audio content.
	//
	// Types that are assignable to StreamingRequest:
	//	*StreamingRecognizeRequest_StreamingConfig
	//	*StreamingRecognizeRequest_AudioContent
	StreamingRequest isStreamingRecognizeRequest_StreamingRequest `protobuf_oneof:"streaming_request"`
	// contains filtered or unexported fields
}

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 deprecated

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

Deprecated: Use StreamingRecognizeRequest.ProtoReflect.Descriptor instead.

func (*StreamingRecognizeRequest) GetAudioContent

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

func (*StreamingRecognizeRequest) GetStreamingConfig

func (x *StreamingRecognizeRequest) GetStreamingConfig() *StreamingRecognitionConfig

func (*StreamingRecognizeRequest) GetStreamingRequest

func (m *StreamingRecognizeRequest) GetStreamingRequest() isStreamingRecognizeRequest_StreamingRequest

func (*StreamingRecognizeRequest) ProtoMessage

func (*StreamingRecognizeRequest) ProtoMessage()

func (*StreamingRecognizeRequest) ProtoReflect

func (*StreamingRecognizeRequest) Reset

func (x *StreamingRecognizeRequest) Reset()

func (*StreamingRecognizeRequest) String

func (x *StreamingRecognizeRequest) String() string

type StreamingRecognizeRequest_AudioContent

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

type StreamingRecognizeRequest_StreamingConfig

type StreamingRecognizeRequest_StreamingConfig struct {
	// Provides information to the recognizer that specifies how to process the
	// request. The first `StreamingRecognizeRequest` message must contain a
	// `streaming_config`  message.
	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 `` /* 180-byte string literal not displayed */
	// When available, billed audio seconds for the stream.
	// Set only if this is the last response in the stream.
	TotalBilledTime *durationpb.Duration `protobuf:"bytes,5,opt,name=total_billed_time,json=totalBilledTime,proto3" json:"total_billed_time,omitempty"`
	// contains filtered or unexported fields
}

`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`.

func (*StreamingRecognizeResponse) Descriptor deprecated

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

Deprecated: Use StreamingRecognizeResponse.ProtoReflect.Descriptor instead.

func (*StreamingRecognizeResponse) GetError

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

func (*StreamingRecognizeResponse) GetResults

func (*StreamingRecognizeResponse) GetSpeechEventType

func (*StreamingRecognizeResponse) GetTotalBilledTime

func (x *StreamingRecognizeResponse) GetTotalBilledTime() *durationpb.Duration

func (*StreamingRecognizeResponse) ProtoMessage

func (*StreamingRecognizeResponse) ProtoMessage()

func (*StreamingRecognizeResponse) ProtoReflect

func (*StreamingRecognizeResponse) Reset

func (x *StreamingRecognizeResponse) Reset()

func (*StreamingRecognizeResponse) String

func (x *StreamingRecognizeResponse) String() string

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) Descriptor

func (StreamingRecognizeResponse_SpeechEventType) Enum

func (StreamingRecognizeResponse_SpeechEventType) EnumDescriptor deprecated

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

Deprecated: Use StreamingRecognizeResponse_SpeechEventType.Descriptor instead.

func (StreamingRecognizeResponse_SpeechEventType) Number

func (StreamingRecognizeResponse_SpeechEventType) String

func (StreamingRecognizeResponse_SpeechEventType) Type

type TranscriptOutputConfig

type TranscriptOutputConfig struct {

	// Types that are assignable to OutputType:
	//	*TranscriptOutputConfig_GcsUri
	OutputType isTranscriptOutputConfig_OutputType `protobuf_oneof:"output_type"`
	// contains filtered or unexported fields
}

Specifies an optional destination for the recognition results.

func (*TranscriptOutputConfig) Descriptor deprecated

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

Deprecated: Use TranscriptOutputConfig.ProtoReflect.Descriptor instead.

func (*TranscriptOutputConfig) GetGcsUri

func (x *TranscriptOutputConfig) GetGcsUri() string

func (*TranscriptOutputConfig) GetOutputType

func (m *TranscriptOutputConfig) GetOutputType() isTranscriptOutputConfig_OutputType

func (*TranscriptOutputConfig) ProtoMessage

func (*TranscriptOutputConfig) ProtoMessage()

func (*TranscriptOutputConfig) ProtoReflect

func (x *TranscriptOutputConfig) ProtoReflect() protoreflect.Message

func (*TranscriptOutputConfig) Reset

func (x *TranscriptOutputConfig) Reset()

func (*TranscriptOutputConfig) String

func (x *TranscriptOutputConfig) String() string

type TranscriptOutputConfig_GcsUri

type TranscriptOutputConfig_GcsUri struct {
	// 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.
	GcsUri string `protobuf:"bytes,1,opt,name=gcs_uri,json=gcsUri,proto3,oneof"`
}

type UnimplementedSpeechServer

type UnimplementedSpeechServer struct {
}

UnimplementedSpeechServer can be embedded to have forward compatible implementations.

func (*UnimplementedSpeechServer) LongRunningRecognize

func (*UnimplementedSpeechServer) Recognize

func (*UnimplementedSpeechServer) StreamingRecognize

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 *durationpb.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 *durationpb.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"`
	// 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"`
	// contains filtered or unexported fields
}

Word-specific information for recognized words.

func (*WordInfo) Descriptor deprecated

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

Deprecated: Use WordInfo.ProtoReflect.Descriptor instead.

func (*WordInfo) GetEndTime

func (x *WordInfo) GetEndTime() *durationpb.Duration

func (*WordInfo) GetSpeakerTag

func (x *WordInfo) GetSpeakerTag() int32

func (*WordInfo) GetStartTime

func (x *WordInfo) GetStartTime() *durationpb.Duration

func (*WordInfo) GetWord

func (x *WordInfo) GetWord() string

func (*WordInfo) ProtoMessage

func (*WordInfo) ProtoMessage()

func (*WordInfo) ProtoReflect

func (x *WordInfo) ProtoReflect() protoreflect.Message

func (*WordInfo) Reset

func (x *WordInfo) Reset()

func (*WordInfo) String

func (x *WordInfo) String() string

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL