Class SpeechToTextConfig (4.61.0)

public final class SpeechToTextConfig extends GeneratedMessageV3 implements SpeechToTextConfigOrBuilder

Configures speech transcription for ConversationProfile.

Protobuf type google.cloud.dialogflow.v2.SpeechToTextConfig

Static Fields

AUDIO_ENCODING_FIELD_NUMBER

public static final int AUDIO_ENCODING_FIELD_NUMBER
Field Value
Type Description
int

ENABLE_WORD_INFO_FIELD_NUMBER

public static final int ENABLE_WORD_INFO_FIELD_NUMBER
Field Value
Type Description
int

LANGUAGE_CODE_FIELD_NUMBER

public static final int LANGUAGE_CODE_FIELD_NUMBER
Field Value
Type Description
int

MODEL_FIELD_NUMBER

public static final int MODEL_FIELD_NUMBER
Field Value
Type Description
int

PHRASE_SETS_FIELD_NUMBER

public static final int PHRASE_SETS_FIELD_NUMBER
Field Value
Type Description
int

SAMPLE_RATE_HERTZ_FIELD_NUMBER

public static final int SAMPLE_RATE_HERTZ_FIELD_NUMBER
Field Value
Type Description
int

SPEECH_MODEL_VARIANT_FIELD_NUMBER

public static final int SPEECH_MODEL_VARIANT_FIELD_NUMBER
Field Value
Type Description
int

USE_TIMEOUT_BASED_ENDPOINTING_FIELD_NUMBER

public static final int USE_TIMEOUT_BASED_ENDPOINTING_FIELD_NUMBER
Field Value
Type Description
int

Static Methods

getDefaultInstance()

public static SpeechToTextConfig getDefaultInstance()
Returns
Type Description
SpeechToTextConfig

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

newBuilder()

public static SpeechToTextConfig.Builder newBuilder()
Returns
Type Description
SpeechToTextConfig.Builder

newBuilder(SpeechToTextConfig prototype)

public static SpeechToTextConfig.Builder newBuilder(SpeechToTextConfig prototype)
Parameter
Name Description
prototype SpeechToTextConfig
Returns
Type Description
SpeechToTextConfig.Builder

parseDelimitedFrom(InputStream input)

public static SpeechToTextConfig parseDelimitedFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static SpeechToTextConfig parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
IOException

parseFrom(byte[] data)

public static SpeechToTextConfig parseFrom(byte[] data)
Parameter
Name Description
data byte[]
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static SpeechToTextConfig parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data byte[]
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data)

public static SpeechToTextConfig parseFrom(ByteString data)
Parameter
Name Description
data ByteString
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static SpeechToTextConfig parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteString
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static SpeechToTextConfig parseFrom(CodedInputStream input)
Parameter
Name Description
input CodedInputStream
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static SpeechToTextConfig parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
IOException

parseFrom(InputStream input)

public static SpeechToTextConfig parseFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static SpeechToTextConfig parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
IOException

parseFrom(ByteBuffer data)

public static SpeechToTextConfig parseFrom(ByteBuffer data)
Parameter
Name Description
data ByteBuffer
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static SpeechToTextConfig parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteBuffer
extensionRegistry ExtensionRegistryLite
Returns
Type Description
SpeechToTextConfig
Exceptions
Type Description
InvalidProtocolBufferException

parser()

public static Parser<SpeechToTextConfig> parser()
Returns
Type Description
Parser<SpeechToTextConfig>

Methods

equals(Object obj)

public boolean equals(Object obj)
Parameter
Name Description
obj Object
Returns
Type Description
boolean
Overrides

getAudioEncoding()

public AudioEncoding getAudioEncoding()

Audio encoding of the audio content to process.

.google.cloud.dialogflow.v2.AudioEncoding audio_encoding = 6;

Returns
Type Description
AudioEncoding

The audioEncoding.

getAudioEncodingValue()

public int getAudioEncodingValue()

Audio encoding of the audio content to process.

.google.cloud.dialogflow.v2.AudioEncoding audio_encoding = 6;

Returns
Type Description
int

The enum numeric value on the wire for audioEncoding.

getDefaultInstanceForType()

public SpeechToTextConfig getDefaultInstanceForType()
Returns
Type Description
SpeechToTextConfig

getEnableWordInfo()

public boolean getEnableWordInfo()

If true, Dialogflow returns SpeechWordInfo in StreamingRecognitionResult with information about the recognized speech words, e.g. start and end time offsets. If false or unspecified, Speech doesn't return any word-level information.

bool enable_word_info = 9;

Returns
Type Description
boolean

The enableWordInfo.

getLanguageCode()

public String getLanguageCode()

The language of the supplied audio. Dialogflow does not do translations. See Language Support for a list of the currently supported language codes. Note that queries in the same session do not necessarily need to specify the same language.

string language_code = 8;

Returns
Type Description
String

The languageCode.

getLanguageCodeBytes()

public ByteString getLanguageCodeBytes()

The language of the supplied audio. Dialogflow does not do translations. See Language Support for a list of the currently supported language codes. Note that queries in the same session do not necessarily need to specify the same language.

string language_code = 8;

Returns
Type Description
ByteString

The bytes for languageCode.

getModel()

public String getModel()

Which Speech model to select. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then Dialogflow auto-selects a model based on other parameters in the SpeechToTextConfig and Agent settings. If enhanced speech model is enabled for the agent and an enhanced version of the specified model for the language does not exist, then the speech is recognized using the standard version of the specified model. Refer to Cloud Speech API documentation for more details. If you specify a model, the following models typically have the best performance:

  • phone_call (best for Agent Assist and telephony)
  • latest_short (best for Dialogflow non-telephony)
  • command_and_search

    Leave this field unspecified to use Agent Speech settings for model selection.

string model = 2;

Returns
Type Description
String

The model.

getModelBytes()

public ByteString getModelBytes()

Which Speech model to select. Select the model best suited to your domain to get best results. If a model is not explicitly specified, then Dialogflow auto-selects a model based on other parameters in the SpeechToTextConfig and Agent settings. If enhanced speech model is enabled for the agent and an enhanced version of the specified model for the language does not exist, then the speech is recognized using the standard version of the specified model. Refer to Cloud Speech API documentation for more details. If you specify a model, the following models typically have the best performance:

  • phone_call (best for Agent Assist and telephony)
  • latest_short (best for Dialogflow non-telephony)
  • command_and_search

    Leave this field unspecified to use Agent Speech settings for model selection.

string model = 2;

Returns
Type Description
ByteString

The bytes for model.

getParserForType()

public Parser<SpeechToTextConfig> getParserForType()
Returns
Type Description
Parser<SpeechToTextConfig>
Overrides

getPhraseSets(int index)

public String getPhraseSets(int index)

List of names of Cloud Speech phrase sets that are used for transcription.

repeated string phrase_sets = 4 [(.google.api.resource_reference) = { ... }

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
String

The phraseSets at the given index.

getPhraseSetsBytes(int index)

public ByteString getPhraseSetsBytes(int index)

List of names of Cloud Speech phrase sets that are used for transcription.

repeated string phrase_sets = 4 [(.google.api.resource_reference) = { ... }

Parameter
Name Description
index int

The index of the value to return.

Returns
Type Description
ByteString

The bytes of the phraseSets at the given index.

getPhraseSetsCount()

public int getPhraseSetsCount()

List of names of Cloud Speech phrase sets that are used for transcription.

repeated string phrase_sets = 4 [(.google.api.resource_reference) = { ... }

Returns
Type Description
int

The count of phraseSets.

getPhraseSetsList()

public ProtocolStringList getPhraseSetsList()

List of names of Cloud Speech phrase sets that are used for transcription.

repeated string phrase_sets = 4 [(.google.api.resource_reference) = { ... }

Returns
Type Description
ProtocolStringList

A list containing the phraseSets.

getSampleRateHertz()

public int getSampleRateHertz()

Sample rate (in Hertz) of the audio content sent in the query. Refer to Cloud Speech API documentation for more details.

int32 sample_rate_hertz = 7;

Returns
Type Description
int

The sampleRateHertz.

getSerializedSize()

public int getSerializedSize()
Returns
Type Description
int
Overrides

getSpeechModelVariant()

public SpeechModelVariant getSpeechModelVariant()

The speech model used in speech to text. SPEECH_MODEL_VARIANT_UNSPECIFIED, USE_BEST_AVAILABLE will be treated as USE_ENHANCED. It can be overridden in AnalyzeContentRequest and StreamingAnalyzeContentRequest request. If enhanced model variant is specified and an enhanced version of the specified model for the language does not exist, then it would emit an error.

.google.cloud.dialogflow.v2.SpeechModelVariant speech_model_variant = 1;

Returns
Type Description
SpeechModelVariant

The speechModelVariant.

getSpeechModelVariantValue()

public int getSpeechModelVariantValue()

The speech model used in speech to text. SPEECH_MODEL_VARIANT_UNSPECIFIED, USE_BEST_AVAILABLE will be treated as USE_ENHANCED. It can be overridden in AnalyzeContentRequest and StreamingAnalyzeContentRequest request. If enhanced model variant is specified and an enhanced version of the specified model for the language does not exist, then it would emit an error.

.google.cloud.dialogflow.v2.SpeechModelVariant speech_model_variant = 1;

Returns
Type Description
int

The enum numeric value on the wire for speechModelVariant.

getUseTimeoutBasedEndpointing()

public boolean getUseTimeoutBasedEndpointing()

Use timeout based endpointing, interpreting endpointer sensitivy as seconds of timeout value.

bool use_timeout_based_endpointing = 11;

Returns
Type Description
boolean

The useTimeoutBasedEndpointing.

hashCode()

public int hashCode()
Returns
Type Description
int
Overrides

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

newBuilderForType()

public SpeechToTextConfig.Builder newBuilderForType()
Returns
Type Description
SpeechToTextConfig.Builder

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected SpeechToTextConfig.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Name Description
parent BuilderParent
Returns
Type Description
SpeechToTextConfig.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Name Description
unused UnusedPrivateParameter
Returns
Type Description
Object
Overrides

toBuilder()

public SpeechToTextConfig.Builder toBuilder()
Returns
Type Description
SpeechToTextConfig.Builder

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
Name Description
output CodedOutputStream
Overrides
Exceptions
Type Description
IOException