docs: update generated docs (#981)
diff --git a/docs/dyn/speech_v1.speech.html b/docs/dyn/speech_v1.speech.html
index fd71ac9..fe57cce 100644
--- a/docs/dyn/speech_v1.speech.html
+++ b/docs/dyn/speech_v1.speech.html
@@ -96,92 +96,24 @@
{ # The top-level message sent by the client for the `LongRunningRecognize`
# method.
+ "audio": { # Contains audio data in the encoding specified in the `RecognitionConfig`. # Required. The audio data to be recognized.
+ # Either `content` or `uri` must be supplied. Supplying both or neither
+ # returns google.rpc.Code.INVALID_ARGUMENT. See
+ # [content limits](https://cloud.google.com/speech-to-text/quotas#content).
+ "uri": "A String", # 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). For more information, see
+ # [Request URIs](https://cloud.google.com/storage/docs/reference-uris).
+ "content": "A String", # 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.
+ },
"config": { # Provides information to the recognizer that specifies how to process the # Required. Provides information to the recognizer that specifies how to
# process the request.
# request.
- "enableWordTimeOffsets": True or False, # 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`.
- "diarizationConfig": { # Config to enable speaker diarization. # 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.
- "minSpeakerCount": 42, # 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.
- "maxSpeakerCount": 42, # 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.
- "speakerTag": 42, # Output only. Unused.
- "enableSpeakerDiarization": True or False, # 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.
- },
- "languageCode": "A String", # 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.
- "profanityFilter": True or False, # 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.
- "useEnhanced": True or False, # 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.
- "metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
- "originalMediaType": "A String", # The original media the speech was recorded on.
- "recordingDeviceType": "A String", # The type of device the speech was recorded with.
- "interactionType": "A String", # The use case most closely describing the audio content to be recognized.
- "audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court
- # hearings from 2012".
- "originalMimeType": "A String", # 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
- "recordingDeviceName": "A String", # The device used to make the recording. Examples 'Nexus 5X' or
- # 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
- # 'Cardioid Microphone'.
- "industryNaicsCodeOfAudio": 42, # 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/.
- "microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
- },
- "sampleRateHertz": 42, # 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.
- "enableSeparateRecognitionPerChannel": True or False, # 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.
- "enableAutomaticPunctuation": True or False, # 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.
- "maxAlternatives": 42, # 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.
"speechContexts": [ # Array of SpeechContext.
# A means to provide context to assist the speech recognition. For more
# information, see
@@ -205,6 +137,98 @@
],
},
],
+ "languageCode": "A String", # 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.
+ "useEnhanced": True or False, # 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.
+ "enableWordTimeOffsets": True or False, # 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`.
+ "diarizationConfig": { # Config to enable speaker diarization. # 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.
+ "speakerTag": 42, # Output only. Unused.
+ "minSpeakerCount": 42, # 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.
+ "enableSpeakerDiarization": True or False, # 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.
+ "maxSpeakerCount": 42, # 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.
+ },
+ "profanityFilter": True or False, # 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.
+ "enableAutomaticPunctuation": True or False, # 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.
+ "enableSeparateRecognitionPerChannel": True or False, # 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.
+ "sampleRateHertz": 42, # 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.
+ "metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
+ "originalMediaType": "A String", # The original media the speech was recorded on.
+ "recordingDeviceName": "A String", # The device used to make the recording. Examples 'Nexus 5X' or
+ # 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
+ # 'Cardioid Microphone'.
+ "industryNaicsCodeOfAudio": 42, # 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/.
+ "originalMimeType": "A String", # 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
+ "audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court
+ # hearings from 2012".
+ "recordingDeviceType": "A String", # The type of device the speech was recorded with.
+ "microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
+ "interactionType": "A String", # The use case most closely describing the audio content to be recognized.
+ },
+ "maxAlternatives": 42, # 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.
+ "audioChannelCount": 42, # 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'.
"encoding": "A String", # 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.
@@ -240,30 +264,6 @@
# recorded at a 16khz or greater sampling rate.</td>
# </tr>
# </table>
- "audioChannelCount": 42, # 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'.
- },
- "audio": { # Contains audio data in the encoding specified in the `RecognitionConfig`. # Required. The audio data to be recognized.
- # Either `content` or `uri` must be supplied. Supplying both or neither
- # returns google.rpc.Code.INVALID_ARGUMENT. See
- # [content limits](https://cloud.google.com/speech-to-text/quotas#content).
- "content": "A String", # 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.
- "uri": "A String", # 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). For more information, see
- # [Request URIs](https://cloud.google.com/storage/docs/reference-uris).
},
}
@@ -287,9 +287,18 @@
# `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
+ "metadata": { # Service-specific metadata associated with the operation. It typically
+ # contains progress information and common metadata such as create time.
+ # Some services might not provide such metadata. Any method that returns a
+ # long-running operation should document the metadata type, if any.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
"name": "A String", # The server-assigned name, which is only unique within the same service that
# originally returns it. If you use the default HTTP mapping, the
# `name` should be a resource name ending with `operations/{unique_id}`.
+ "done": True or False, # If the value is `false`, it means the operation is still in progress.
+ # If `true`, the operation is completed, and either `error` or `response` is
+ # available.
"error": { # The `Status` type defines a logical error model that is suitable for # The error result of the operation in case of failure or cancellation.
# different programming environments, including REST APIs and RPC APIs. It is
# used by [gRPC](https://github.com/grpc). Each `Status` message contains
@@ -297,26 +306,17 @@
#
# You can find out more about this error model and how to work with it in the
# [API Design Guide](https://cloud.google.com/apis/design/errors).
+ "message": "A String", # A developer-facing error message, which should be in English. Any
+ # user-facing error message should be localized and sent in the
+ # google.rpc.Status.details field, or localized by the client.
+ "code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of
# message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
- "code": 42, # The status code, which should be an enum value of google.rpc.Code.
- "message": "A String", # A developer-facing error message, which should be in English. Any
- # user-facing error message should be localized and sent in the
- # google.rpc.Status.details field, or localized by the client.
},
- "metadata": { # Service-specific metadata associated with the operation. It typically
- # contains progress information and common metadata such as create time.
- # Some services might not provide such metadata. Any method that returns a
- # long-running operation should document the metadata type, if any.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "done": True or False, # If the value is `false`, it means the operation is still in progress.
- # If `true`, the operation is completed, and either `error` or `response` is
- # available.
}</pre>
</div>
@@ -333,89 +333,6 @@
"config": { # Provides information to the recognizer that specifies how to process the # Required. Provides information to the recognizer that specifies how to
# process the request.
# request.
- "enableWordTimeOffsets": True or False, # 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`.
- "diarizationConfig": { # Config to enable speaker diarization. # 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.
- "minSpeakerCount": 42, # 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.
- "maxSpeakerCount": 42, # 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.
- "speakerTag": 42, # Output only. Unused.
- "enableSpeakerDiarization": True or False, # 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.
- },
- "languageCode": "A String", # 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.
- "profanityFilter": True or False, # 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.
- "useEnhanced": True or False, # 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.
- "metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
- "originalMediaType": "A String", # The original media the speech was recorded on.
- "recordingDeviceType": "A String", # The type of device the speech was recorded with.
- "interactionType": "A String", # The use case most closely describing the audio content to be recognized.
- "audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court
- # hearings from 2012".
- "originalMimeType": "A String", # 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
- "recordingDeviceName": "A String", # The device used to make the recording. Examples 'Nexus 5X' or
- # 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
- # 'Cardioid Microphone'.
- "industryNaicsCodeOfAudio": 42, # 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/.
- "microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
- },
- "sampleRateHertz": 42, # 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.
- "enableSeparateRecognitionPerChannel": True or False, # 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.
- "enableAutomaticPunctuation": True or False, # 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.
- "maxAlternatives": 42, # 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.
"speechContexts": [ # Array of SpeechContext.
# A means to provide context to assist the speech recognition. For more
# information, see
@@ -439,6 +356,98 @@
],
},
],
+ "languageCode": "A String", # 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.
+ "useEnhanced": True or False, # 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.
+ "enableWordTimeOffsets": True or False, # 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`.
+ "diarizationConfig": { # Config to enable speaker diarization. # 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.
+ "speakerTag": 42, # Output only. Unused.
+ "minSpeakerCount": 42, # 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.
+ "enableSpeakerDiarization": True or False, # 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.
+ "maxSpeakerCount": 42, # 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.
+ },
+ "profanityFilter": True or False, # 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.
+ "enableAutomaticPunctuation": True or False, # 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.
+ "enableSeparateRecognitionPerChannel": True or False, # 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.
+ "sampleRateHertz": 42, # 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.
+ "metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
+ "originalMediaType": "A String", # The original media the speech was recorded on.
+ "recordingDeviceName": "A String", # The device used to make the recording. Examples 'Nexus 5X' or
+ # 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or
+ # 'Cardioid Microphone'.
+ "industryNaicsCodeOfAudio": 42, # 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/.
+ "originalMimeType": "A String", # 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
+ "audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court
+ # hearings from 2012".
+ "recordingDeviceType": "A String", # The type of device the speech was recorded with.
+ "microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
+ "interactionType": "A String", # The use case most closely describing the audio content to be recognized.
+ },
+ "maxAlternatives": 42, # 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.
+ "audioChannelCount": 42, # 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'.
"encoding": "A String", # 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.
@@ -474,23 +483,11 @@
# recorded at a 16khz or greater sampling rate.</td>
# </tr>
# </table>
- "audioChannelCount": 42, # 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'.
},
"audio": { # Contains audio data in the encoding specified in the `RecognitionConfig`. # Required. The audio data to be recognized.
# Either `content` or `uri` must be supplied. Supplying both or neither
# returns google.rpc.Code.INVALID_ARGUMENT. See
# [content limits](https://cloud.google.com/speech-to-text/quotas#content).
- "content": "A String", # 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.
"uri": "A String", # 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
@@ -498,6 +495,9 @@
# `gs://bucket_name/object_name` (other URI formats return
# google.rpc.Code.INVALID_ARGUMENT). For more information, see
# [Request URIs](https://cloud.google.com/storage/docs/reference-uris).
+ "content": "A String", # 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.
},
}
@@ -523,6 +523,7 @@
# These alternatives are ordered in terms of accuracy, with the top (first)
# alternative being the most probable, as ranked by the recognizer.
{ # Alternative hypotheses (a.k.a. n-best list).
+ "transcript": "A String", # Transcript text representing the words that the user spoke.
"confidence": 3.14, # 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
@@ -530,11 +531,15 @@
# 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.
- "transcript": "A String", # Transcript text representing the words that the user spoke.
"words": [ # 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.
{ # Word-specific information for recognized words.
+ "speakerTag": 42, # 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.
"endTime": "A String", # 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
@@ -548,11 +553,6 @@
# This is an experimental feature and the accuracy of the time offset can
# vary.
"word": "A String", # The word corresponding to this set of information.
- "speakerTag": 42, # 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.
},
],
},