Blame - docs/dyn/speech_v1p1beta1.speech.html - platform/external/python/google-api-python-client

blob: 5fcdf3cb0a0bece7009fa46ab3c302c228e3429b [file] [log] [blame]

Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	1	<html><body>
				2	<style>
				3
				4	body, h1, h2, h3, div, span, p, pre, a {
				5	margin: 0;
				6	padding: 0;
				7	border: 0;
				8	font-weight: inherit;
				9	font-style: inherit;
				10	font-size: 100%;
				11	font-family: inherit;
				12	vertical-align: baseline;
				13	}
				14
				15	body {
				16	font-size: 13px;
				17	padding: 1em;
				18	}
				19
				20	h1 {
				21	font-size: 26px;
				22	margin-bottom: 1em;
				23	}
				24
				25	h2 {
				26	font-size: 24px;
				27	margin-bottom: 1em;
				28	}
				29
				30	h3 {
				31	font-size: 20px;
				32	margin-bottom: 1em;
				33	margin-top: 1em;
				34	}
				35
				36	pre, code {
				37	line-height: 1.5;
				38	font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
				39	}
				40
				41	pre {
				42	margin-top: 0.5em;
				43	}
				44
				45	h1, h2, h3, p {
				46	font-family: Arial, sans serif;
				47	}
				48
				49	h1, h2, h3 {
				50	border-bottom: solid #CCC 1px;
				51	}
				52
				53	.toc_element {
				54	margin-top: 0.5em;
				55	}
				56
				57	.firstline {
				58	margin-left: 2 em;
				59	}
				60
				61	.method {
				62	margin-top: 1em;
				63	border: solid 1px #CCC;
				64	padding: 1em;
				65	background: #EEE;
				66	}
				67
				68	.details {
				69	font-weight: bold;
				70	font-size: 14px;
				71	}
				72
				73	</style>
				74
				75	<h1><a href="speech_v1p1beta1.html">Cloud Speech-to-Text API</a> . <a href="speech_v1p1beta1.speech.html">speech</a></h1>
				76	<h2>Instance Methods</h2>
				77	<p class="toc_element">
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	78	<code><a href="#close">close()</a></code></p>
				79	<p class="firstline">Close httplib2 connections.</p>
				80	<p class="toc_element">
Dan O'Meara	dd49464	2020-05-01 07:42:23 -0700	[diff] [blame]	81	<code><a href="#longrunningrecognize">longrunningrecognize(body=None, x__xgafv=None)</a></code></p>
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	82	<p class="firstline">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).</p>
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	83	<p class="toc_element">
Dan O'Meara	dd49464	2020-05-01 07:42:23 -0700	[diff] [blame]	84	<code><a href="#recognize">recognize(body=None, x__xgafv=None)</a></code></p>
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	85	<p class="firstline">Performs synchronous speech recognition: receive results after all audio has been sent and processed.</p>
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	86	<h3>Method Details</h3>
				87	<div class="method">
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	88	<code class="details" id="close">close()</code>
				89	<pre>Close httplib2 connections.</pre>
				90	</div>
				91
				92	<div class="method">
Dan O'Meara	dd49464	2020-05-01 07:42:23 -0700	[diff] [blame]	93	<code class="details" id="longrunningrecognize">longrunningrecognize(body=None, x__xgafv=None)</code>
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	94	<pre>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).
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	95
				96	Args:
Dan O'Meara	dd49464	2020-05-01 07:42:23 -0700	[diff] [blame]	97	body: object, The request body.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	98	The object takes the form of:
				99
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	100	{ # The top-level message sent by the client for the `LongRunningRecognize` method.
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	101	"config": { # Provides information to the recognizer that specifies how to process the request. # Required. Provides information to the recognizer that specifies how to process the request.
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	102	"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).
				103	{ # Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
				104	"boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific phrase will be recognized over other similar sounding phrases. The higher the boost, the higher the chance of false positive recognition as well. Negative boost values would correspond to anti-biasing. Anti-biasing is not enabled, so negative boost will simply be ignored. Though `boost` can accept a wide range of positive values, most use cases are best served with values between 0 and 20. We recommend using a binary search approach to finding the optimal value for your use case.
				105	"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.
Bu Sun Kim	d059ad8	2020-07-22 17:02:09 -0700	[diff] [blame]	106	"A String",
				107	],
				108	},
				109	],
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	110	"adaptation": { # Speech adaptation configuration. # Speech adaptation configuration improves the accuracy of speech recognition. When speech adaptation is set it supersedes the `speech_contexts` field. For more information, see the [speech adaptation](https://cloud.google.com/speech-to-text/docs/context-strength) documentation.
				111	"phraseSets": [ # A collection of phrase sets. To specify the hints inline, leave the phrase set's `name` blank and fill in the rest of its fields. Any phrase set can use any custom class.
				112	{ # Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	113	"boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific phrase will be recognized over other similar sounding phrases. The higher the boost, the higher the chance of false positive recognition as well. Negative boost values would correspond to anti-biasing. Anti-biasing is not enabled, so negative boost will simply be ignored. Though `boost` can accept a wide range of positive values, most use cases are best served with values between 0 (exclusive) and 20. We recommend using a binary search approach to finding the optimal value for your use case. Speech recognition will skip PhraseSets with a boost value of 0.
				114	"phrases": [ # A list of word and phrases.
				115	{ # A phrases containing words and phrase "hints" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech-to-text/quotas#content). List items can also include pre-built or custom classes containing groups of words that represent common concepts that occur in natural language. For example, rather than providing a phrase hint for every month of the year (e.g. "i was born in january", "i was born in febuary", ...), use the pre-built `$MONTH` class improves the likelihood of correctly transcribing audio that includes months (e.g. "i was born in $month"). To refer to pre-built classes, use the class' symbol prepended with `$` e.g. `$MONTH`. To refer to custom classes that were defined inline in the request, set the class's `custom_class_id` to a string unique to all class resources and inline classes. Then use the class' id wrapped in $`{...}` e.g. "${my-months}". To refer to custom classes resources, use the class' id wrapped in `${}` (e.g. `${my-months}`).
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	116	"boost": 3.14, # Hint Boost. Overrides the boost set at the phrase set level. Positive value will increase the probability that a specific phrase will be recognized over other similar sounding phrases. The higher the boost, the higher the chance of false positive recognition as well. Negative boost values would correspond to anti-biasing. Anti-biasing is not enabled, so negative boost will simply be ignored. Though `boost` can accept a wide range of positive values, most use cases are best served with values between 0 and 20. We recommend using a binary search approach to finding the optimal value for your use case. Speech recognition will skip PhraseSets with a boost value of 0.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	117	"value": "A String", # The phrase itself.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	118	},
				119	],
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	120	"name": "A String", # The resource name of the phrase set.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	121	},
				122	],
				123	"customClasses": [ # A collection of custom classes. To specify the classes inline, leave the class' `name` blank and fill in the rest of its fields, giving it a unique `custom_class_id`. Refer to the inline defined class in phrase hints by its `custom_class_id`.
				124	{ # A set of words or phrases that represents a common concept likely to appear in your audio, for example a list of passenger ship names. CustomClass items can be substituted into placeholders that you set in PhraseSet phrases.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	125	"items": [ # A collection of class items.
				126	{ # An item of the class.
				127	"value": "A String", # The class item's value.
				128	},
				129	],
				130	"customClassId": "A String", # If this custom class is a resource, the custom_class_id is the resource id of the CustomClass. Case sensitive.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	131	"name": "A String", # The resource name of the custom class.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	132	},
				133	],
				134	},
Yoshi Automation Bot	c2228be	2020-11-24 15:48:03 -0800	[diff] [blame]	135	"metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	136	"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'.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	137	"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
				138	"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/.
				139	"obfuscatedId": "A String", # Obfuscated (privacy-protected) ID of the user, to identify number of unique users using the service.
				140	"recordingDeviceType": "A String", # The type of device the speech was recorded with.
				141	"microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
				142	"originalMediaType": "A String", # The original media the speech was recorded on.
				143	"interactionType": "A String", # The use case most closely describing the audio content to be recognized.
				144	"audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court hearings from 2012".
Yoshi Automation Bot	c2228be	2020-11-24 15:48:03 -0800	[diff] [blame]	145	},
Bu Sun Kim	673ec5c	2020-11-16 11:05:03 -0700	[diff] [blame]	146	"alternativeLanguageCodes": [ # A list of up to 3 additional [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags, listing possible alternative languages of the supplied audio. See [Language Support](https://cloud.google.com/speech-to-text/docs/languages) for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).
				147	"A String",
				148	],
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	149	"diarizationSpeakerCount": 42, # If set, specifies the estimated number of speakers in the conversation. Defaults to '2'. Ignored unless enable_speaker_diarization is set to true. Note: Use diarization_config instead.
				150	"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.
				151	"enableSpokenEmojis": True or False, # The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.
				152	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	153	"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.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	154	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	155	"speakerTag": 42, # Output only. Unused.
				156	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	157	"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.
				158	},
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	159	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	160	"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. Model Description command_and_search Best for short queries such as voice commands or voice search. phone_call Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate). video 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. default 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.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	161	"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'.
				162	"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.
				163	"enableSpokenPunctuation": True or False, # The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, "how are you question mark" becomes "how are you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.
Yoshi Automation Bot	c2228be	2020-11-24 15:48:03 -0800	[diff] [blame]	164	"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.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	165	"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`.
				166	"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. Note: Use diarization_config instead.
				167	"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.
				168	"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.
				169	"enableWordConfidence": True or False, # If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.
				170	"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.
				171	},
				172	"audio": { # 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. See [content limits](https://cloud.google.com/speech-to-text/quotas#content). # Required. The audio data to be recognized.
				173	"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).
				174	"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.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	175	},
				176	}
				177
				178	x__xgafv: string, V1 error format.
				179	Allowed values
				180	1 - v1 error format
				181	2 - v2 error format
				182
				183	Returns:
				184	An object of the form:
				185
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	186	{ # This resource represents a long-running operation that is the result of a network API call.
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	187	"error": { # The `Status` type defines a logical error model that is suitable for 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). # The error result of the operation in case of failure or cancellation.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	188	"code": 42, # The status code, which should be an enum value of google.rpc.Code.
				189	"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.
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	190	"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	191	{
Bu Sun Kim	6502091	2020-05-20 12:08:20 -0700	[diff] [blame]	192	"a_key": "", # Properties of the object. Contains field @type with type URL.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	193	},
				194	],
				195	},
Bu Sun Kim	673ec5c	2020-11-16 11:05:03 -0700	[diff] [blame]	196	"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`.
Bu Sun Kim	6502091	2020-05-20 12:08:20 -0700	[diff] [blame]	197	"a_key": "", # Properties of the object. Contains field @type with type URL.
				198	},
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	199	"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}`.
				200	"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.
				201	"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.
				202	"a_key": "", # Properties of the object. Contains field @type with type URL.
				203	},
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	204	}</pre>
				205	</div>
				206
				207	<div class="method">
Dan O'Meara	dd49464	2020-05-01 07:42:23 -0700	[diff] [blame]	208	<code class="details" id="recognize">recognize(body=None, x__xgafv=None)</code>
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	209	<pre>Performs synchronous speech recognition: receive results after all audio has been sent and processed.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	210
				211	Args:
Dan O'Meara	dd49464	2020-05-01 07:42:23 -0700	[diff] [blame]	212	body: object, The request body.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	213	The object takes the form of:
				214
				215	{ # The top-level message sent by the client for the `Recognize` method.
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	216	"config": { # Provides information to the recognizer that specifies how to process the request. # Required. Provides information to the recognizer that specifies how to process the request.
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	217	"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).
				218	{ # Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
				219	"boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific phrase will be recognized over other similar sounding phrases. The higher the boost, the higher the chance of false positive recognition as well. Negative boost values would correspond to anti-biasing. Anti-biasing is not enabled, so negative boost will simply be ignored. Though `boost` can accept a wide range of positive values, most use cases are best served with values between 0 and 20. We recommend using a binary search approach to finding the optimal value for your use case.
				220	"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.
Bu Sun Kim	d059ad8	2020-07-22 17:02:09 -0700	[diff] [blame]	221	"A String",
				222	],
				223	},
				224	],
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	225	"adaptation": { # Speech adaptation configuration. # Speech adaptation configuration improves the accuracy of speech recognition. When speech adaptation is set it supersedes the `speech_contexts` field. For more information, see the [speech adaptation](https://cloud.google.com/speech-to-text/docs/context-strength) documentation.
				226	"phraseSets": [ # A collection of phrase sets. To specify the hints inline, leave the phrase set's `name` blank and fill in the rest of its fields. Any phrase set can use any custom class.
				227	{ # Provides "hints" to the speech recognizer to favor specific words and phrases in the results.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	228	"boost": 3.14, # Hint Boost. Positive value will increase the probability that a specific phrase will be recognized over other similar sounding phrases. The higher the boost, the higher the chance of false positive recognition as well. Negative boost values would correspond to anti-biasing. Anti-biasing is not enabled, so negative boost will simply be ignored. Though `boost` can accept a wide range of positive values, most use cases are best served with values between 0 (exclusive) and 20. We recommend using a binary search approach to finding the optimal value for your use case. Speech recognition will skip PhraseSets with a boost value of 0.
				229	"phrases": [ # A list of word and phrases.
				230	{ # A phrases containing words and phrase "hints" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech-to-text/quotas#content). List items can also include pre-built or custom classes containing groups of words that represent common concepts that occur in natural language. For example, rather than providing a phrase hint for every month of the year (e.g. "i was born in january", "i was born in febuary", ...), use the pre-built `$MONTH` class improves the likelihood of correctly transcribing audio that includes months (e.g. "i was born in $month"). To refer to pre-built classes, use the class' symbol prepended with `$` e.g. `$MONTH`. To refer to custom classes that were defined inline in the request, set the class's `custom_class_id` to a string unique to all class resources and inline classes. Then use the class' id wrapped in $`{...}` e.g. "${my-months}". To refer to custom classes resources, use the class' id wrapped in `${}` (e.g. `${my-months}`).
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	231	"boost": 3.14, # Hint Boost. Overrides the boost set at the phrase set level. Positive value will increase the probability that a specific phrase will be recognized over other similar sounding phrases. The higher the boost, the higher the chance of false positive recognition as well. Negative boost values would correspond to anti-biasing. Anti-biasing is not enabled, so negative boost will simply be ignored. Though `boost` can accept a wide range of positive values, most use cases are best served with values between 0 and 20. We recommend using a binary search approach to finding the optimal value for your use case. Speech recognition will skip PhraseSets with a boost value of 0.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	232	"value": "A String", # The phrase itself.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	233	},
				234	],
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	235	"name": "A String", # The resource name of the phrase set.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	236	},
				237	],
				238	"customClasses": [ # A collection of custom classes. To specify the classes inline, leave the class' `name` blank and fill in the rest of its fields, giving it a unique `custom_class_id`. Refer to the inline defined class in phrase hints by its `custom_class_id`.
				239	{ # A set of words or phrases that represents a common concept likely to appear in your audio, for example a list of passenger ship names. CustomClass items can be substituted into placeholders that you set in PhraseSet phrases.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	240	"items": [ # A collection of class items.
				241	{ # An item of the class.
				242	"value": "A String", # The class item's value.
				243	},
				244	],
				245	"customClassId": "A String", # If this custom class is a resource, the custom_class_id is the resource id of the CustomClass. Case sensitive.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	246	"name": "A String", # The resource name of the custom class.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	247	},
				248	],
				249	},
Yoshi Automation Bot	c2228be	2020-11-24 15:48:03 -0800	[diff] [blame]	250	"metadata": { # Description of audio data to be recognized. # Metadata regarding this request.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	251	"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'.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	252	"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
				253	"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/.
				254	"obfuscatedId": "A String", # Obfuscated (privacy-protected) ID of the user, to identify number of unique users using the service.
				255	"recordingDeviceType": "A String", # The type of device the speech was recorded with.
				256	"microphoneDistance": "A String", # The audio type that most closely describes the audio being recognized.
				257	"originalMediaType": "A String", # The original media the speech was recorded on.
				258	"interactionType": "A String", # The use case most closely describing the audio content to be recognized.
				259	"audioTopic": "A String", # Description of the content. Eg. "Recordings of federal supreme court hearings from 2012".
Yoshi Automation Bot	c2228be	2020-11-24 15:48:03 -0800	[diff] [blame]	260	},
Bu Sun Kim	673ec5c	2020-11-16 11:05:03 -0700	[diff] [blame]	261	"alternativeLanguageCodes": [ # A list of up to 3 additional [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags, listing possible alternative languages of the supplied audio. See [Language Support](https://cloud.google.com/speech-to-text/docs/languages) for a list of the currently supported language codes. If alternative languages are listed, recognition result will contain recognition in the most likely language detected including the main language_code. The recognition result will include the language tag of the language detected in the audio. Note: This feature is only supported for Voice Command and Voice Search use cases and performance may vary for other use cases (e.g., phone call transcription).
				262	"A String",
				263	],
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	264	"diarizationSpeakerCount": 42, # If set, specifies the estimated number of speakers in the conversation. Defaults to '2'. Ignored unless enable_speaker_diarization is set to true. Note: Use diarization_config instead.
				265	"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.
				266	"enableSpokenEmojis": True or False, # The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.
				267	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	268	"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.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	269	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	270	"speakerTag": 42, # Output only. Unused.
				271	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	272	"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.
				273	},
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	274	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	275	"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. Model Description command_and_search Best for short queries such as voice commands or voice search. phone_call Best for audio that originated from a phone call (typically recorded at an 8khz sampling rate). video 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. default 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.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	276	"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'.
				277	"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.
				278	"enableSpokenPunctuation": True or False, # The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, "how are you question mark" becomes "how are you?". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.
Yoshi Automation Bot	c2228be	2020-11-24 15:48:03 -0800	[diff] [blame]	279	"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.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	280	"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`.
				281	"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. Note: Use diarization_config instead.
				282	"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.
				283	"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.
				284	"enableWordConfidence": True or False, # If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.
				285	"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.
Yoshi Automation Bot	c2228be	2020-11-24 15:48:03 -0800	[diff] [blame]	286	},
				287	"audio": { # 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. See [content limits](https://cloud.google.com/speech-to-text/quotas#content). # Required. The audio data to be recognized.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	288	"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).
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	289	"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.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	290	},
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	291	}
				292
				293	x__xgafv: string, V1 error format.
				294	Allowed values
				295	1 - v1 error format
				296	2 - v2 error format
				297
				298	Returns:
				299	An object of the form:
				300
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	301	{ # The only message returned to the client by the `Recognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages.
				302	"results": [ # Sequential list of transcription results corresponding to sequential portions of audio.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	303	{ # A speech recognition result corresponding to a portion of the audio.
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	304	"languageCode": "A String", # Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	305	"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'.
Dmitry Frenkel	3e17f89	2020-10-06 16:46:05 -0700	[diff] [blame]	306	"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.
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	307	{ # Alternative hypotheses (a.k.a. n-best list).
Yoshi Automation Bot	c2228be	2020-11-24 15:48:03 -0800	[diff] [blame]	308	"transcript": "A String", # Transcript text representing the words that the user spoke.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	309	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	310	"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.
				311	{ # Word-specific information for recognized words.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	312	"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.
Yoshi Automation Bot	b6971b0	2020-11-26 17:16:03 -0800	[diff] [blame^]	313	"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.
				314	"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.
				315	"word": "A String", # The word corresponding to this set of information.
				316	"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.
Yoshi Automation Bot	0d561ef	2020-11-25 07:50:41 -0800	[diff] [blame]	317	},
				318	],
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	319	},
				320	],
Bu Sun Kim	715bd7f	2019-06-14 16:50:42 -0700	[diff] [blame]	321	},
				322	],
				323	}</pre>
				324	</div>
				325
				326	</body></html>