longrunningrecognize(body=None, x__xgafv=None)
Performs asynchronous speech recognition: receive results via the
recognize(body=None, x__xgafv=None)
Performs synchronous speech recognition: receive results after all audio
longrunningrecognize(body=None, x__xgafv=None)
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).
Args:
body: object, The request body.
The object takes the form of:
{ # 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).
"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).
},
"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.
"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.
"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.
"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.
"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`.
"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.
"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.
"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.
"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.
"model": "A String", # Which model to select for the given request. Select the model
# best suited to your domain to get best results. If a model is not
# explicitly specified, then we auto-select a model based on the parameters
# in the RecognitionConfig.
# <table>
# <tr>
# <td><b>Model</b></td>
# <td><b>Description</b></td>
# </tr>
# <tr>
# <td><code>command_and_search</code></td>
# <td>Best for short queries such as voice commands or voice search.</td>
# </tr>
# <tr>
# <td><code>phone_call</code></td>
# <td>Best for audio that originated from a phone call (typically
# recorded at an 8khz sampling rate).</td>
# </tr>
# <tr>
# <td><code>video</code></td>
# <td>Best for audio that originated from from video or includes multiple
# speakers. Ideally the audio is recorded at a 16khz or greater
# sampling rate. This is a premium model that costs more than the
# standard rate.</td>
# </tr>
# <tr>
# <td><code>default</code></td>
# <td>Best for audio that is not one of the specific audio models.
# For example, long-form audio. Ideally the audio is high-fidelity,
# recorded at a 16khz or greater sampling rate.</td>
# </tr>
# </table>
"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.
"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.
"speakerTag": 42, # Output only. Unused.
},
"speechContexts": [ # Array of SpeechContext.
# A means to provide context to assist the speech recognition. For more
# information, see
# [speech
# adaptation](https://cloud.google.com/speech-to-text/docs/context-strength).
{ # Provides "hints" to the speech recognizer to favor specific words and phrases
# in the results.
"phrases": [ # 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.
"A String",
],
},
],
"metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
"recordingDeviceType": "A String", # The type of device the speech was recorded with.
"originalMediaType": "A String", # The original media the speech was recorded on.
"microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
"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/.
"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
"interactionType": "A String", # The use case most closely describing the audio content to be recognized.
},
},
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a
# network API call.
"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
# three pieces of data: error code, error message, and error details.
#
# 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.
},
],
},
"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.
"response": { # The normal response of the operation in case of success. If the original
# method returns no data on success, such as `Delete`, the response is
# `google.protobuf.Empty`. If the original method is standard
# `Get`/`Create`/`Update`, the response should be the resource. For other
# methods, the response should have the type `XxxResponse`, where `Xxx`
# is the original method name. For example, if the original method name
# is `TakeSnapshot()`, the inferred response type is
# `TakeSnapshotResponse`.
"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}`.
"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.
},
}
recognize(body=None, x__xgafv=None)
Performs synchronous speech recognition: receive results after all audio
has been sent and processed.
Args:
body: object, The request body.
The object takes the form of:
{ # The top-level message sent by the client for the `Recognize` 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).
"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).
},
"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.
"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.
"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.
"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.
"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`.
"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.
"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.
"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.
"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.
"model": "A String", # Which model to select for the given request. Select the model
# best suited to your domain to get best results. If a model is not
# explicitly specified, then we auto-select a model based on the parameters
# in the RecognitionConfig.
# <table>
# <tr>
# <td><b>Model</b></td>
# <td><b>Description</b></td>
# </tr>
# <tr>
# <td><code>command_and_search</code></td>
# <td>Best for short queries such as voice commands or voice search.</td>
# </tr>
# <tr>
# <td><code>phone_call</code></td>
# <td>Best for audio that originated from a phone call (typically
# recorded at an 8khz sampling rate).</td>
# </tr>
# <tr>
# <td><code>video</code></td>
# <td>Best for audio that originated from from video or includes multiple
# speakers. Ideally the audio is recorded at a 16khz or greater
# sampling rate. This is a premium model that costs more than the
# standard rate.</td>
# </tr>
# <tr>
# <td><code>default</code></td>
# <td>Best for audio that is not one of the specific audio models.
# For example, long-form audio. Ideally the audio is high-fidelity,
# recorded at a 16khz or greater sampling rate.</td>
# </tr>
# </table>
"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.
"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.
"speakerTag": 42, # Output only. Unused.
},
"speechContexts": [ # Array of SpeechContext.
# A means to provide context to assist the speech recognition. For more
# information, see
# [speech
# adaptation](https://cloud.google.com/speech-to-text/docs/context-strength).
{ # Provides "hints" to the speech recognizer to favor specific words and phrases
# in the results.
"phrases": [ # 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.
"A String",
],
},
],
"metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
"recordingDeviceType": "A String", # The type of device the speech was recorded with.
"originalMediaType": "A String", # The original media the speech was recorded on.
"microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
"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/.
"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
"interactionType": "A String", # The use case most closely describing the audio content to be recognized.
},
},
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # The only message returned to the client by the `Recognize` method. It
# contains the result as zero or more sequential `SpeechRecognitionResult`
# messages.
"results": [ # Sequential list of transcription results corresponding to
# sequential portions of audio.
{ # A speech recognition result corresponding to a portion of the audio.
"channelTag": 42, # 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'.
"alternatives": [ # 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.
{ # Alternative hypotheses (a.k.a. n-best list).
"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
# 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.
"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.
"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
# in the top hypothesis.
# 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.
"startTime": "A String", # 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.
"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.
},
],
},
],
},
],
}