OMGeeky/google-apis-rs
1
0
Fork 0
mirror of https://github.com/OMGeeky/google-apis-rs.git synced 2026-02-23 15:49:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

update all json files

Browse Source
This commit is contained in:
Sebastian Thiel
2020-04-12 18:55:37 +08:00
parent ea3b428364
commit aacc30f08d
260 changed files with 138411 additions and 26293 deletions
Download Patch File Download Diff File Expand all files Collapse all files

99
etc/api/speech/v1/speech-api.json
View File

@@ -22,6 +22,7 @@
},
"id": "speech:v1",
"kind": "discovery#restDescription",
"mtlsRootUrl": "https://speech.mtls.googleapis.com/",
"name": "speech",
"ownerDomain": "google.com",
"ownerName": "Google",
@@ -118,7 +119,7 @@
"name": {
"description": "The name of the operation resource.",
"location": "path",
"pattern": "^.+$",
"pattern": "^.*$",
"required": true,
"type": "string"
}
@@ -289,7 +290,7 @@
}
}
},
"revision": "20190627",
"revision": "20200406",
"rootUrl": "https://speech.googleapis.com/",
"schemas": {
"ListOperationsResponse": {
@@ -328,6 +329,10 @@
"description": "Time when the request was received.",
"format": "google-datetime",
"type": "string"
},
"uri": {
"description": "The URI of the audio file being transcribed. Empty if the audio was sent\nas byte content. ",
"type": "string"
}
},
"type": "object"
@@ -338,11 +343,11 @@
"properties": {
"audio": {
"$ref": "RecognitionAudio",
"description": "*Required* The audio data to be recognized."
"description": "Required. The audio data to be recognized."
},
"config": {
"$ref": "RecognitionConfig",
"description": "*Required* Provides information to the recognizer that specifies how to\nprocess the request."
"description": "Required. Provides information to the recognizer that specifies how to\nprocess the request."
}
},
"type": "object"
@@ -352,7 +357,7 @@
"id": "LongRunningRecognizeResponse",
"properties": {
"results": {
"description": "Output only. Sequential list of transcription results corresponding to\nsequential portions of audio.",
"description": "Sequential list of transcription results corresponding to\nsequential portions of audio.",
"items": {
"$ref": "SpeechRecognitionResult"
},
@@ -397,7 +402,7 @@
"type": "object"
},
"RecognitionAudio": {
"description": "Contains audio data in the encoding specified in the `RecognitionConfig`.\nEither `content` or `uri` must be supplied. Supplying both or neither\nreturns google.rpc.Code.INVALID_ARGUMENT. See\n[content limits](/speech-to-text/quotas#content).",
"description": "Contains audio data in the encoding specified in the `RecognitionConfig`.\nEither `content` or `uri` must be supplied. Supplying both or neither\nreturns google.rpc.Code.INVALID_ARGUMENT. See\n[content limits](https://cloud.google.com/speech-to-text/quotas#content).",
"id": "RecognitionAudio",
"properties": {
"content": {
@@ -417,12 +422,16 @@
"id": "RecognitionConfig",
"properties": {
"audioChannelCount": {
"description": "*Optional* The number of channels in the input audio data.\nONLY set this for MULTI-CHANNEL recognition.\nValid values for LINEAR16 and FLAC are `1`-`8`.\nValid values for OGG_OPUS are '1'-'254'.\nValid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.\nIf `0` or omitted, defaults to one channel (mono).\nNote: We only recognize the first channel by default.\nTo perform independent recognition on each channel set\n`enable_separate_recognition_per_channel` to 'true'.",
"description": "The number of channels in the input audio data.\nONLY set this for MULTI-CHANNEL recognition.\nValid values for LINEAR16 and FLAC are `1`-`8`.\nValid values for OGG_OPUS are '1'-'254'.\nValid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.\nIf `0` or omitted, defaults to one channel (mono).\nNote: We only recognize the first channel by default.\nTo perform independent recognition on each channel set\n`enable_separate_recognition_per_channel` to 'true'.",
"format": "int32",
"type": "integer"
},
"diarizationConfig": {
"$ref": "SpeakerDiarizationConfig",
"description": "Config to enable speaker diarization and set additional\nparameters to make diarization better suited for your application.\nNote: When this is enabled, we send all the words from the beginning of the\naudio for the top alternative in every consecutive STREAMING responses.\nThis is done in order to improve our speaker tags as our models learn to\nidentify the speakers in the conversation over time.\nFor non-streaming requests, the diarization results will be provided only\nin the top alternative of the FINAL SpeechRecognitionResult."
},
"enableAutomaticPunctuation": {
"description": "*Optional* If 'true', adds punctuation to recognition result hypotheses.\nThis feature is only available in select languages. Setting this for\nrequests in other languages has no effect at all.\nThe default 'false' value does not add punctuation to result hypotheses.\nNote: This is currently offered as an experimental service, complimentary\nto all users. In the future this may be exclusively available as a\npremium feature.",
"description": "If 'true', adds punctuation to recognition result hypotheses.\nThis feature is only available in select languages. Setting this for\nrequests in other languages has no effect at all.\nThe default 'false' value does not add punctuation to result hypotheses.",
"type": "boolean"
},
"enableSeparateRecognitionPerChannel": {
@@ -430,7 +439,7 @@
"type": "boolean"
},
"enableWordTimeOffsets": {
"description": "*Optional* If `true`, the top result includes a list of words and\nthe start and end time offsets (timestamps) for those words. If\n`false`, no word-level time offset information is returned. The default is\n`false`.",
"description": "If `true`, the top result includes a list of words and\nthe start and end time offsets (timestamps) for those words. If\n`false`, no word-level time offset information is returned. The default is\n`false`.",
"type": "boolean"
},
"encoding": {
@@ -458,24 +467,24 @@
"type": "string"
},
"languageCode": {
"description": "*Required* The language of the supplied audio as a\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.\nExample: \"en-US\".\nSee [Language Support](/speech-to-text/docs/languages)\nfor a list of the currently supported language codes.",
"description": "Required. The language of the supplied audio as a\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.\nExample: \"en-US\".\nSee [Language\nSupport](https://cloud.google.com/speech-to-text/docs/languages) for a list\nof the currently supported language codes.",
"type": "string"
},
"maxAlternatives": {
"description": "*Optional* Maximum number of recognition hypotheses to be returned.\nSpecifically, the maximum number of `SpeechRecognitionAlternative` messages\nwithin each `SpeechRecognitionResult`.\nThe server may return fewer than `max_alternatives`.\nValid values are `0`-`30`. A value of `0` or `1` will return a maximum of\none. If omitted, will return a maximum of one.",
"description": "Maximum number of recognition hypotheses to be returned.\nSpecifically, the maximum number of `SpeechRecognitionAlternative` messages\nwithin each `SpeechRecognitionResult`.\nThe server may return fewer than `max_alternatives`.\nValid values are `0`-`30`. A value of `0` or `1` will return a maximum of\none. If omitted, will return a maximum of one.",
"format": "int32",
"type": "integer"
},
"metadata": {
"$ref": "RecognitionMetadata",
"description": "*Optional* Metadata regarding this request."
"description": "Metadata regarding this request."
},
"model": {
"description": "*Optional* Which model to select for the given request. Select the model\nbest suited to your domain to get best results. If a model is not\nexplicitly specified, then we auto-select a model based on the parameters\nin the RecognitionConfig.\n<table>\n <tr>\n <td><b>Model</b></td>\n <td><b>Description</b></td>\n </tr>\n <tr>\n <td><code>command_and_search</code></td>\n <td>Best for short queries such as voice commands or voice search.</td>\n </tr>\n <tr>\n <td><code>phone_call</code></td>\n <td>Best for audio that originated from a phone call (typically\n recorded at an 8khz sampling rate).</td>\n </tr>\n <tr>\n <td><code>video</code></td>\n <td>Best for audio that originated from from video or includes multiple\n speakers. Ideally the audio is recorded at a 16khz or greater\n sampling rate. This is a premium model that costs more than the\n standard rate.</td>\n </tr>\n <tr>\n <td><code>default</code></td>\n <td>Best for audio that is not one of the specific audio models.\n For example, long-form audio. Ideally the audio is high-fidelity,\n recorded at a 16khz or greater sampling rate.</td>\n </tr>\n</table>",
"description": "Which model to select for the given request. Select the model\nbest suited to your domain to get best results. If a model is not\nexplicitly specified, then we auto-select a model based on the parameters\nin the RecognitionConfig.\n<table>\n <tr>\n <td><b>Model</b></td>\n <td><b>Description</b></td>\n </tr>\n <tr>\n <td><code>command_and_search</code></td>\n <td>Best for short queries such as voice commands or voice search.</td>\n </tr>\n <tr>\n <td><code>phone_call</code></td>\n <td>Best for audio that originated from a phone call (typically\n recorded at an 8khz sampling rate).</td>\n </tr>\n <tr>\n <td><code>video</code></td>\n <td>Best for audio that originated from from video or includes multiple\n speakers. Ideally the audio is recorded at a 16khz or greater\n sampling rate. This is a premium model that costs more than the\n standard rate.</td>\n </tr>\n <tr>\n <td><code>default</code></td>\n <td>Best for audio that is not one of the specific audio models.\n For example, long-form audio. Ideally the audio is high-fidelity,\n recorded at a 16khz or greater sampling rate.</td>\n </tr>\n</table>",
"type": "string"
},
"profanityFilter": {
"description": "*Optional* If set to `true`, the server will attempt to filter out\nprofanities, replacing all but the initial character in each filtered word\nwith asterisks, e.g. \"f***\". If set to `false` or omitted, profanities\nwon't be filtered out.",
"description": "If set to `true`, the server will attempt to filter out\nprofanities, replacing all but the initial character in each filtered word\nwith asterisks, e.g. \"f***\". If set to `false` or omitted, profanities\nwon't be filtered out.",
"type": "boolean"
},
"sampleRateHertz": {
@@ -484,14 +493,14 @@
"type": "integer"
},
"speechContexts": {
"description": "*Optional* array of SpeechContext.\nA means to provide context to assist the speech recognition. For more\ninformation, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).",
"description": "Array of SpeechContext.\nA means to provide context to assist the speech recognition. For more\ninformation, see\n[speech\nadaptation](https://cloud.google.com/speech-to-text/docs/context-strength).",
"items": {
"$ref": "SpeechContext"
},
"type": "array"
},
"useEnhanced": {
"description": "*Optional* Set to true to use an enhanced model for speech recognition.\nIf `use_enhanced` is set to true and the `model` field is not set, then\nan appropriate enhanced model is chosen if an enhanced model exists for\nthe audio.\n\nIf `use_enhanced` is true and an enhanced version of the specified model\ndoes not exist, then the speech is recognized using the standard version\nof the specified model.",
"description": "Set to true to use an enhanced model for speech recognition.\nIf `use_enhanced` is set to true and the `model` field is not set, then\nan appropriate enhanced model is chosen if an enhanced model exists for\nthe audio.\n\nIf `use_enhanced` is true and an enhanced version of the specified model\ndoes not exist, then the speech is recognized using the standard version\nof the specified model.",
"type": "boolean"
}
},
@@ -552,11 +561,6 @@
],
"type": "string"
},
"obfuscatedId": {
"description": "Obfuscated (privacy-protected) ID of the user, to identify number of\nunique users using the service.",
"format": "int64",
"type": "string"
},
"originalMediaType": {
"description": "The original media the speech was recorded on.",
"enum": [
@@ -610,11 +614,11 @@
"properties": {
"audio": {
"$ref": "RecognitionAudio",
"description": "*Required* The audio data to be recognized."
"description": "Required. The audio data to be recognized."
},
"config": {
"$ref": "RecognitionConfig",
"description": "*Required* Provides information to the recognizer that specifies how to\nprocess the request."
"description": "Required. Provides information to the recognizer that specifies how to\nprocess the request."
}
},
"type": "object"
@@ -624,7 +628,7 @@
"id": "RecognizeResponse",
"properties": {
"results": {
"description": "Output only. Sequential list of transcription results corresponding to\nsequential portions of audio.",
"description": "Sequential list of transcription results corresponding to\nsequential portions of audio.",
"items": {
"$ref": "SpeechRecognitionResult"
},
@@ -633,12 +637,38 @@
},
"type": "object"
},
"SpeakerDiarizationConfig": {
"description": "Config to enable speaker diarization.",
"id": "SpeakerDiarizationConfig",
"properties": {
"enableSpeakerDiarization": {
"description": "If 'true', enables speaker detection for each recognized word in\nthe top alternative of the recognition result using a speaker_tag provided\nin the WordInfo.",
"type": "boolean"
},
"maxSpeakerCount": {
"description": "Maximum number of speakers in the conversation. This range gives you more\nflexibility by allowing the system to automatically determine the correct\nnumber of speakers. If not set, the default value is 6.",
"format": "int32",
"type": "integer"
},
"minSpeakerCount": {
"description": "Minimum number of speakers in the conversation. This range gives you more\nflexibility by allowing the system to automatically determine the correct\nnumber of speakers. If not set, the default value is 2.",
"format": "int32",
"type": "integer"
},
"speakerTag": {
"description": "Output only. Unused.",
"format": "int32",
"type": "integer"
}
},
"type": "object"
},
"SpeechContext": {
"description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases\nin the results.",
"id": "SpeechContext",
"properties": {
"phrases": {
"description": "*Optional* A list of strings containing words and phrases \"hints\" so that\nthe speech recognition is more likely to recognize them. This can be used\nto improve the accuracy for specific words and phrases, for example, if\nspecific commands are typically spoken by the user. This can also be used\nto add additional words to the vocabulary of the recognizer. See\n[usage limits](/speech-to-text/quotas#content).\n\nList items can also be set to classes for groups of words that represent\ncommon concepts that occur in natural language. For example, rather than\nproviding phrase hints for every month of the year, using the $MONTH class\nimproves the likelihood of correctly transcribing audio that includes\nmonths.",
"description": "A list of strings containing words and phrases \"hints\" so that\nthe speech recognition is more likely to recognize them. This can be used\nto improve the accuracy for specific words and phrases, for example, if\nspecific commands are typically spoken by the user. This can also be used\nto add additional words to the vocabulary of the recognizer. See\n[usage limits](https://cloud.google.com/speech-to-text/quotas#content).\n\nList items can also be set to classes for groups of words that represent\ncommon concepts that occur in natural language. For example, rather than\nproviding phrase hints for every month of the year, using the $MONTH class\nimproves the likelihood of correctly transcribing audio that includes\nmonths.",
"items": {
"type": "string"
},
@@ -652,16 +682,16 @@
"id": "SpeechRecognitionAlternative",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"description": "The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"transcript": {
"description": "Output only. Transcript text representing the words that the user spoke.",
"description": "Transcript text representing the words that the user spoke.",
"type": "string"
},
"words": {
"description": "Output only. A list of word-specific information for each recognized word.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"description": "A list of word-specific information for each recognized word.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"items": {
"$ref": "WordInfo"
},
@@ -675,7 +705,7 @@
"id": "SpeechRecognitionResult",
"properties": {
"alternatives": {
"description": "Output only. May contain one or more recognition hypotheses (up to the\nmaximum specified in `max_alternatives`).\nThese alternatives are ordered in terms of accuracy, with the top (first)\nalternative being the most probable, as ranked by the recognizer.",
"description": "May contain one or more recognition hypotheses (up to the\nmaximum specified in `max_alternatives`).\nThese alternatives are ordered in terms of accuracy, with the top (first)\nalternative being the most probable, as ranked by the recognizer.",
"items": {
"$ref": "SpeechRecognitionAlternative"
},
@@ -721,17 +751,22 @@
"id": "WordInfo",
"properties": {
"endTime": {
"description": "Output only. Time offset relative to the beginning of the audio,\nand corresponding to the end of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"description": "Time offset relative to the beginning of the audio,\nand corresponding to the end of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"format": "google-duration",
"type": "string"
},
"speakerTag": {
"description": "Output only. A distinct integer value is assigned for every speaker within\nthe audio. This field specifies which one of those speakers was detected to\nhave spoken this word. Value ranges from '1' to diarization_speaker_count.\nspeaker_tag is set if enable_speaker_diarization = 'true' and only in the\ntop alternative.",
"format": "int32",
"type": "integer"
},
"startTime": {
"description": "Output only. Time offset relative to the beginning of the audio,\nand corresponding to the start of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"description": "Time offset relative to the beginning of the audio,\nand corresponding to the start of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"format": "google-duration",
"type": "string"
},
"word": {
"description": "Output only. The word corresponding to this set of information.",
"description": "The word corresponding to this set of information.",
"type": "string"
}
},

91
etc/api/speech/v1p1beta1/speech-api.json
View File

@@ -22,6 +22,7 @@
},
"id": "speech:v1p1beta1",
"kind": "discovery#restDescription",
"mtlsRootUrl": "https://speech.mtls.googleapis.com/",
"name": "speech",
"ownerDomain": "google.com",
"ownerName": "Google",
@@ -118,7 +119,7 @@
"name": {
"description": "The name of the operation resource.",
"location": "path",
"pattern": "^.+$",
"pattern": "^.*$",
"required": true,
"type": "string"
}
@@ -289,7 +290,7 @@
}
}
},
"revision": "20190627",
"revision": "20200406",
"rootUrl": "https://speech.googleapis.com/",
"schemas": {
"ListOperationsResponse": {
@@ -328,6 +329,10 @@
"description": "Time when the request was received.",
"format": "google-datetime",
"type": "string"
},
"uri": {
"description": "The URI of the audio file being transcribed. Empty if the audio was sent\nas byte content. ",
"type": "string"
}
},
"type": "object"
@@ -338,11 +343,11 @@
"properties": {
"audio": {
"$ref": "RecognitionAudio",
"description": "*Required* The audio data to be recognized."
"description": "Required. The audio data to be recognized."
},
"config": {
"$ref": "RecognitionConfig",
"description": "*Required* Provides information to the recognizer that specifies how to\nprocess the request."
"description": "Required. Provides information to the recognizer that specifies how to\nprocess the request."
}
},
"type": "object"
@@ -352,7 +357,7 @@
"id": "LongRunningRecognizeResponse",
"properties": {
"results": {
"description": "Output only. Sequential list of transcription results corresponding to\nsequential portions of audio.",
"description": "Sequential list of transcription results corresponding to\nsequential portions of audio.",
"items": {
"$ref": "SpeechRecognitionResult"
},
@@ -397,7 +402,7 @@
"type": "object"
},
"RecognitionAudio": {
"description": "Contains audio data in the encoding specified in the `RecognitionConfig`.\nEither `content` or `uri` must be supplied. Supplying both or neither\nreturns google.rpc.Code.INVALID_ARGUMENT. See\n[content limits](/speech-to-text/quotas#content).",
"description": "Contains audio data in the encoding specified in the `RecognitionConfig`.\nEither `content` or `uri` must be supplied. Supplying both or neither\nreturns google.rpc.Code.INVALID_ARGUMENT. See\n[content limits](https://cloud.google.com/speech-to-text/quotas#content).",
"id": "RecognitionAudio",
"properties": {
"content": {
@@ -417,28 +422,28 @@
"id": "RecognitionConfig",
"properties": {
"alternativeLanguageCodes": {
"description": "*Optional* A list of up to 3 additional\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,\nlisting possible alternative languages of the supplied audio.\nSee [Language Support](/speech-to-text/docs/languages)\nfor a list of the currently supported language codes.\nIf alternative languages are listed, recognition result will contain\nrecognition in the most likely language detected including the main\nlanguage_code. The recognition result will include the language tag\nof the language detected in the audio.\nNote: This feature is only supported for Voice Command and Voice Search\nuse cases and performance may vary for other use cases (e.g., phone call\ntranscription).",
"description": "A list of up to 3 additional\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,\nlisting possible alternative languages of the supplied audio.\nSee [Language\nSupport](https://cloud.google.com/speech-to-text/docs/languages) for a list\nof the currently supported language codes. If alternative languages are\nlisted, recognition result will contain recognition in the most likely\nlanguage detected including the main language_code. The recognition result\nwill include the language tag of the language detected in the audio. Note:\nThis feature is only supported for Voice Command and Voice Search use cases\nand performance may vary for other use cases (e.g., phone call\ntranscription).",
"items": {
"type": "string"
},
"type": "array"
},
"audioChannelCount": {
"description": "*Optional* The number of channels in the input audio data.\nONLY set this for MULTI-CHANNEL recognition.\nValid values for LINEAR16 and FLAC are `1`-`8`.\nValid values for OGG_OPUS are '1'-'254'.\nValid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.\nIf `0` or omitted, defaults to one channel (mono).\nNote: We only recognize the first channel by default.\nTo perform independent recognition on each channel set\n`enable_separate_recognition_per_channel` to 'true'.",
"description": "The number of channels in the input audio data.\nONLY set this for MULTI-CHANNEL recognition.\nValid values for LINEAR16 and FLAC are `1`-`8`.\nValid values for OGG_OPUS are '1'-'254'.\nValid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.\nIf `0` or omitted, defaults to one channel (mono).\nNote: We only recognize the first channel by default.\nTo perform independent recognition on each channel set\n`enable_separate_recognition_per_channel` to 'true'.",
"format": "int32",
"type": "integer"
},
"diarizationConfig": {
"$ref": "SpeakerDiarizationConfig",
"description": "*Optional* Config to enable speaker diarization and set additional\nparameters to make diarization better suited for your application.\nNote: When this is enabled, we send all the words from the beginning of the\naudio for the top alternative in every consecutive STREAMING responses.\nThis is done in order to improve our speaker tags as our models learn to\nidentify the speakers in the conversation over time.\nFor non-streaming requests, the diarization results will be provided only\nin the top alternative of the FINAL SpeechRecognitionResult."
"description": "Config to enable speaker diarization and set additional\nparameters to make diarization better suited for your application.\nNote: When this is enabled, we send all the words from the beginning of the\naudio for the top alternative in every consecutive STREAMING responses.\nThis is done in order to improve our speaker tags as our models learn to\nidentify the speakers in the conversation over time.\nFor non-streaming requests, the diarization results will be provided only\nin the top alternative of the FINAL SpeechRecognitionResult."
},
"diarizationSpeakerCount": {
"description": "*Optional*\nIf set, specifies the estimated number of speakers in the conversation.\nIf not set, defaults to '2'.\nIgnored unless enable_speaker_diarization is set to true.\"\nNote: Use diarization_config instead. This field will be DEPRECATED soon.",
"description": "If set, specifies the estimated number of speakers in the conversation.\nDefaults to '2'. Ignored unless enable_speaker_diarization is set to true.\nNote: Use diarization_config instead.",
"format": "int32",
"type": "integer"
},
"enableAutomaticPunctuation": {
"description": "*Optional* If 'true', adds punctuation to recognition result hypotheses.\nThis feature is only available in select languages. Setting this for\nrequests in other languages has no effect at all.\nThe default 'false' value does not add punctuation to result hypotheses.\nNote: This is currently offered as an experimental service, complimentary\nto all users. In the future this may be exclusively available as a\npremium feature.",
"description": "If 'true', adds punctuation to recognition result hypotheses.\nThis feature is only available in select languages. Setting this for\nrequests in other languages has no effect at all.\nThe default 'false' value does not add punctuation to result hypotheses.",
"type": "boolean"
},
"enableSeparateRecognitionPerChannel": {
@@ -446,15 +451,15 @@
"type": "boolean"
},
"enableSpeakerDiarization": {
"description": "*Optional* If 'true', enables speaker detection for each recognized word in\nthe top alternative of the recognition result using a speaker_tag provided\nin the WordInfo.\nNote: Use diarization_config instead. This field will be DEPRECATED soon.",
"description": "If 'true', enables speaker detection for each recognized word in\nthe top alternative of the recognition result using a speaker_tag provided\nin the WordInfo.\nNote: Use diarization_config instead.",
"type": "boolean"
},
"enableWordConfidence": {
"description": "*Optional* If `true`, the top result includes a list of words and the\nconfidence for those words. If `false`, no word-level confidence\ninformation is returned. The default is `false`.",
"description": "If `true`, the top result includes a list of words and the\nconfidence for those words. If `false`, no word-level confidence\ninformation is returned. The default is `false`.",
"type": "boolean"
},
"enableWordTimeOffsets": {
"description": "*Optional* If `true`, the top result includes a list of words and\nthe start and end time offsets (timestamps) for those words. If\n`false`, no word-level time offset information is returned. The default is\n`false`.",
"description": "If `true`, the top result includes a list of words and\nthe start and end time offsets (timestamps) for those words. If\n`false`, no word-level time offset information is returned. The default is\n`false`.",
"type": "boolean"
},
"encoding": {
@@ -479,29 +484,29 @@
"Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.",
"Opus encoded audio frames in Ogg container\n([OggOpus](https://wiki.xiph.org/OggOpus)).\n`sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000.",
"Although the use of lossy encodings is not recommended, if a very low\nbitrate encoding is required, `OGG_OPUS` is highly preferred over\nSpeex encoding. The [Speex](https://speex.org/) encoding supported by\nCloud Speech API has a header byte in each block, as in MIME type\n`audio/x-speex-with-header-byte`.\nIt is a variant of the RTP Speex encoding defined in\n[RFC 5574](https://tools.ietf.org/html/rfc5574).\nThe stream is a sequence of blocks, one block per RTP packet. Each block\nstarts with a byte containing the length of the block, in bytes, followed\nby one or more frames of Speex data, padded to an integral number of\nbytes (octets) as specified in RFC 5574. In other words, each RTP header\nis replaced with a single byte containing the block length. Only Speex\nwideband is supported. `sample_rate_hertz` must be 16000.",
"MP3 audio. Support all standard MP3 bitrates (which range from 32-320\nkbps). When using this encoding, `sample_rate_hertz` can be optionally\nunset if not known."
"MP3 audio. Support all standard MP3 bitrates (which range from 32-320\nkbps). When using this encoding, `sample_rate_hertz` has to match the\nsample rate of the file being used."
],
"type": "string"
},
"languageCode": {
"description": "*Required* The language of the supplied audio as a\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.\nExample: \"en-US\".\nSee [Language Support](/speech-to-text/docs/languages)\nfor a list of the currently supported language codes.",
"description": "Required. The language of the supplied audio as a\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.\nExample: \"en-US\".\nSee [Language\nSupport](https://cloud.google.com/speech-to-text/docs/languages) for a list\nof the currently supported language codes.",
"type": "string"
},
"maxAlternatives": {
"description": "*Optional* Maximum number of recognition hypotheses to be returned.\nSpecifically, the maximum number of `SpeechRecognitionAlternative` messages\nwithin each `SpeechRecognitionResult`.\nThe server may return fewer than `max_alternatives`.\nValid values are `0`-`30`. A value of `0` or `1` will return a maximum of\none. If omitted, will return a maximum of one.",
"description": "Maximum number of recognition hypotheses to be returned.\nSpecifically, the maximum number of `SpeechRecognitionAlternative` messages\nwithin each `SpeechRecognitionResult`.\nThe server may return fewer than `max_alternatives`.\nValid values are `0`-`30`. A value of `0` or `1` will return a maximum of\none. If omitted, will return a maximum of one.",
"format": "int32",
"type": "integer"
},
"metadata": {
"$ref": "RecognitionMetadata",
"description": "*Optional* Metadata regarding this request."
"description": "Metadata regarding this request."
},
"model": {
"description": "*Optional* Which model to select for the given request. Select the model\nbest suited to your domain to get best results. If a model is not\nexplicitly specified, then we auto-select a model based on the parameters\nin the RecognitionConfig.\n<table>\n <tr>\n <td><b>Model</b></td>\n <td><b>Description</b></td>\n </tr>\n <tr>\n <td><code>command_and_search</code></td>\n <td>Best for short queries such as voice commands or voice search.</td>\n </tr>\n <tr>\n <td><code>phone_call</code></td>\n <td>Best for audio that originated from a phone call (typically\n recorded at an 8khz sampling rate).</td>\n </tr>\n <tr>\n <td><code>video</code></td>\n <td>Best for audio that originated from from video or includes multiple\n speakers. Ideally the audio is recorded at a 16khz or greater\n sampling rate. This is a premium model that costs more than the\n standard rate.</td>\n </tr>\n <tr>\n <td><code>default</code></td>\n <td>Best for audio that is not one of the specific audio models.\n For example, long-form audio. Ideally the audio is high-fidelity,\n recorded at a 16khz or greater sampling rate.</td>\n </tr>\n</table>",
"description": "Which model to select for the given request. Select the model\nbest suited to your domain to get best results. If a model is not\nexplicitly specified, then we auto-select a model based on the parameters\nin the RecognitionConfig.\n<table>\n <tr>\n <td><b>Model</b></td>\n <td><b>Description</b></td>\n </tr>\n <tr>\n <td><code>command_and_search</code></td>\n <td>Best for short queries such as voice commands or voice search.</td>\n </tr>\n <tr>\n <td><code>phone_call</code></td>\n <td>Best for audio that originated from a phone call (typically\n recorded at an 8khz sampling rate).</td>\n </tr>\n <tr>\n <td><code>video</code></td>\n <td>Best for audio that originated from from video or includes multiple\n speakers. Ideally the audio is recorded at a 16khz or greater\n sampling rate. This is a premium model that costs more than the\n standard rate.</td>\n </tr>\n <tr>\n <td><code>default</code></td>\n <td>Best for audio that is not one of the specific audio models.\n For example, long-form audio. Ideally the audio is high-fidelity,\n recorded at a 16khz or greater sampling rate.</td>\n </tr>\n</table>",
"type": "string"
},
"profanityFilter": {
"description": "*Optional* If set to `true`, the server will attempt to filter out\nprofanities, replacing all but the initial character in each filtered word\nwith asterisks, e.g. \"f***\". If set to `false` or omitted, profanities\nwon't be filtered out.",
"description": "If set to `true`, the server will attempt to filter out\nprofanities, replacing all but the initial character in each filtered word\nwith asterisks, e.g. \"f***\". If set to `false` or omitted, profanities\nwon't be filtered out.",
"type": "boolean"
},
"sampleRateHertz": {
@@ -510,14 +515,14 @@
"type": "integer"
},
"speechContexts": {
"description": "*Optional* array of SpeechContext.\nA means to provide context to assist the speech recognition. For more\ninformation, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).",
"description": "Array of SpeechContext.\nA means to provide context to assist the speech recognition. For more\ninformation, see\n[speech\nadaptation](https://cloud.google.com/speech-to-text/docs/context-strength).",
"items": {
"$ref": "SpeechContext"
},
"type": "array"
},
"useEnhanced": {
"description": "*Optional* Set to true to use an enhanced model for speech recognition.\nIf `use_enhanced` is set to true and the `model` field is not set, then\nan appropriate enhanced model is chosen if an enhanced model exists for\nthe audio.\n\nIf `use_enhanced` is true and an enhanced version of the specified model\ndoes not exist, then the speech is recognized using the standard version\nof the specified model.",
"description": "Set to true to use an enhanced model for speech recognition.\nIf `use_enhanced` is set to true and the `model` field is not set, then\nan appropriate enhanced model is chosen if an enhanced model exists for\nthe audio.\n\nIf `use_enhanced` is true and an enhanced version of the specified model\ndoes not exist, then the speech is recognized using the standard version\nof the specified model.",
"type": "boolean"
}
},
@@ -636,15 +641,11 @@
"properties": {
"audio": {
"$ref": "RecognitionAudio",
"description": "*Required* The audio data to be recognized."
"description": "Required. The audio data to be recognized."
},
"config": {
"$ref": "RecognitionConfig",
"description": "*Required* Provides information to the recognizer that specifies how to\nprocess the request."
},
"name": {
"description": "*Optional* The name of the model to use for recognition.",
"type": "string"
"description": "Required. Provides information to the recognizer that specifies how to\nprocess the request."
}
},
"type": "object"
@@ -654,7 +655,7 @@
"id": "RecognizeResponse",
"properties": {
"results": {
"description": "Output only. Sequential list of transcription results corresponding to\nsequential portions of audio.",
"description": "Sequential list of transcription results corresponding to\nsequential portions of audio.",
"items": {
"$ref": "SpeechRecognitionResult"
},
@@ -664,19 +665,25 @@
"type": "object"
},
"SpeakerDiarizationConfig": {
"description": "Config to enable speaker diarization.",
"id": "SpeakerDiarizationConfig",
"properties": {
"enableSpeakerDiarization": {
"description": "*Optional* If 'true', enables speaker detection for each recognized word in\nthe top alternative of the recognition result using a speaker_tag provided\nin the WordInfo.",
"description": "If 'true', enables speaker detection for each recognized word in\nthe top alternative of the recognition result using a speaker_tag provided\nin the WordInfo.",
"type": "boolean"
},
"maxSpeakerCount": {
"description": "*Optional* Only used if diarization_speaker_count is not set.\nMaximum number of speakers in the conversation. This range gives you more\nflexibility by allowing the system to automatically determine the correct\nnumber of speakers. If not set, the default value is 6.",
"description": "Maximum number of speakers in the conversation. This range gives you more\nflexibility by allowing the system to automatically determine the correct\nnumber of speakers. If not set, the default value is 6.",
"format": "int32",
"type": "integer"
},
"minSpeakerCount": {
"description": "*Optional* Only used if diarization_speaker_count is not set.\nMinimum number of speakers in the conversation. This range gives you more\nflexibility by allowing the system to automatically determine the correct\nnumber of speakers. If not set, the default value is 2.",
"description": "Minimum number of speakers in the conversation. This range gives you more\nflexibility by allowing the system to automatically determine the correct\nnumber of speakers. If not set, the default value is 2.",
"format": "int32",
"type": "integer"
},
"speakerTag": {
"description": "Output only. Unused.",
"format": "int32",
"type": "integer"
}
@@ -693,7 +700,7 @@
"type": "number"
},
"phrases": {
"description": "*Optional* A list of strings containing words and phrases \"hints\" so that\nthe speech recognition is more likely to recognize them. This can be used\nto improve the accuracy for specific words and phrases, for example, if\nspecific commands are typically spoken by the user. This can also be used\nto add additional words to the vocabulary of the recognizer. See\n[usage limits](/speech-to-text/quotas#content).\n\nList items can also be set to classes for groups of words that represent\ncommon concepts that occur in natural language. For example, rather than\nproviding phrase hints for every month of the year, using the $MONTH class\nimproves the likelihood of correctly transcribing audio that includes\nmonths.",
"description": "A list of strings containing words and phrases \"hints\" so that\nthe speech recognition is more likely to recognize them. This can be used\nto improve the accuracy for specific words and phrases, for example, if\nspecific commands are typically spoken by the user. This can also be used\nto add additional words to the vocabulary of the recognizer. See\n[usage limits](https://cloud.google.com/speech-to-text/quotas#content).\n\nList items can also be set to classes for groups of words that represent\ncommon concepts that occur in natural language. For example, rather than\nproviding phrase hints for every month of the year, using the $MONTH class\nimproves the likelihood of correctly transcribing audio that includes\nmonths.",
"items": {
"type": "string"
},
@@ -707,16 +714,16 @@
"id": "SpeechRecognitionAlternative",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"description": "The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"transcript": {
"description": "Output only. Transcript text representing the words that the user spoke.",
"description": "Transcript text representing the words that the user spoke.",
"type": "string"
},
"words": {
"description": "Output only. A list of word-specific information for each recognized word.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"description": "A list of word-specific information for each recognized word.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"items": {
"$ref": "WordInfo"
},
@@ -730,7 +737,7 @@
"id": "SpeechRecognitionResult",
"properties": {
"alternatives": {
"description": "Output only. May contain one or more recognition hypotheses (up to the\nmaximum specified in `max_alternatives`).\nThese alternatives are ordered in terms of accuracy, with the top (first)\nalternative being the most probable, as ranked by the recognizer.",
"description": "May contain one or more recognition hypotheses (up to the\nmaximum specified in `max_alternatives`).\nThese alternatives are ordered in terms of accuracy, with the top (first)\nalternative being the most probable, as ranked by the recognizer.",
"items": {
"$ref": "SpeechRecognitionAlternative"
},
@@ -742,7 +749,7 @@
"type": "integer"
},
"languageCode": {
"description": "Output only. The\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the\nlanguage in this result. This language code was detected to have the most\nlikelihood of being spoken in the audio.",
"description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag\nof the language in this result. This language code was detected to have\nthe most likelihood of being spoken in the audio.",
"type": "string"
}
},
@@ -780,12 +787,12 @@
"id": "WordInfo",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"description": "The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"endTime": {
"description": "Output only. Time offset relative to the beginning of the audio,\nand corresponding to the end of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"description": "Time offset relative to the beginning of the audio,\nand corresponding to the end of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"format": "google-duration",
"type": "string"
},
@@ -795,12 +802,12 @@
"type": "integer"
},
"startTime": {
"description": "Output only. Time offset relative to the beginning of the audio,\nand corresponding to the start of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"description": "Time offset relative to the beginning of the audio,\nand corresponding to the start of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"format": "google-duration",
"type": "string"
},
"word": {
"description": "Output only. The word corresponding to this set of information.",
"description": "The word corresponding to this set of information.",
"type": "string"
}
},

392
etc/api/speech/v2beta1/speech-api.json Normal file
View File

@@ -0,0 +1,392 @@
{
"auth": {
"oauth2": {
"scopes": {
"https://www.googleapis.com/auth/cloud-platform": {
"description": "View and manage your data across Google Cloud Platform services"
}
}
}
},
"basePath": "",
"baseUrl": "https://speech.googleapis.com/",
"batchPath": "batch",
"canonicalName": "Speech",
"description": "Converts audio to text by applying powerful neural network models.",
"discoveryVersion": "v1",
"documentationLink": "https://cloud.google.com/speech-to-text/docs/quickstart-protocol",
"fullyEncodeReservedExpansion": true,
"icons": {
"x16": "http://www.google.com/images/icons/product/search-16.gif",
"x32": "http://www.google.com/images/icons/product/search-32.gif"
},
"id": "speech:v2beta1",
"kind": "discovery#restDescription",
"mtlsRootUrl": "https://speech.mtls.googleapis.com/",
"name": "speech",
"ownerDomain": "google.com",
"ownerName": "Google",
"parameters": {
"$.xgafv": {
"description": "V1 error format.",
"enum": [
"1",
"2"
],
"enumDescriptions": [
"v1 error format",
"v2 error format"
],
"location": "query",
"type": "string"
},
"access_token": {
"description": "OAuth access token.",
"location": "query",
"type": "string"
},
"alt": {
"default": "json",
"description": "Data format for response.",
"enum": [
"json",
"media",
"proto"
],
"enumDescriptions": [
"Responses with Content-Type of application/json",
"Media download with context-dependent Content-Type",
"Responses with Content-Type of application/x-protobuf"
],
"location": "query",
"type": "string"
},
"callback": {
"description": "JSONP",
"location": "query",
"type": "string"
},
"fields": {
"description": "Selector specifying which fields to include in a partial response.",
"location": "query",
"type": "string"
},
"key": {
"description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.",
"location": "query",
"type": "string"
},
"oauth_token": {
"description": "OAuth 2.0 token for the current user.",
"location": "query",
"type": "string"
},
"prettyPrint": {
"default": "true",
"description": "Returns response with indentations and line breaks.",
"location": "query",
"type": "boolean"
},
"quotaUser": {
"description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.",
"location": "query",
"type": "string"
},
"uploadType": {
"description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
"location": "query",
"type": "string"
},
"upload_protocol": {
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
"location": "query",
"type": "string"
}
},
"protocol": "rest",
"resources": {
"projects": {
"resources": {
"locations": {
"resources": {
"operations": {
"methods": {
"get": {
"description": "Gets the latest state of a long-running operation. Clients can use this\nmethod to poll the operation result at intervals as recommended by the API\nservice.",
"flatPath": "v2beta1/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}",
"httpMethod": "GET",
"id": "speech.projects.locations.operations.get",
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$",
"required": true,
"type": "string"
}
},
"path": "v2beta1/{+name}",
"response": {
"$ref": "Operation"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
},
"list": {
"description": "Lists operations that match the specified filter in the request. If the\nserver doesn't support this method, it returns `UNIMPLEMENTED`.\n\nNOTE: the `name` binding allows API services to override the binding\nto use different resource name schemes, such as `users/*/operations`. To\noverride the binding, API services can add a binding such as\n`\"/v1/{name=users/*}/operations\"` to their service configuration.\nFor backwards compatibility, the default name includes the operations\ncollection id, however overriding users must ensure the name binding\nis the parent resource, without the operations collection id.",
"flatPath": "v2beta1/projects/{projectsId}/locations/{locationsId}/operations",
"httpMethod": "GET",
"id": "speech.projects.locations.operations.list",
"parameterOrder": [
"name"
],
"parameters": {
"filter": {
"description": "The standard list filter.",
"location": "query",
"type": "string"
},
"name": {
"description": "The name of the operation's parent resource.",
"location": "path",
"pattern": "^projects/[^/]+/locations/[^/]+$",
"required": true,
"type": "string"
},
"pageSize": {
"description": "The standard list page size.",
"format": "int32",
"location": "query",
"type": "integer"
},
"pageToken": {
"description": "The standard list page token.",
"location": "query",
"type": "string"
}
},
"path": "v2beta1/{+name}/operations",
"response": {
"$ref": "ListOperationsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
]
}
}
}
}
}
}
}
},
"revision": "20200406",
"rootUrl": "https://speech.googleapis.com/",
"schemas": {
"ListOperationsResponse": {
"description": "The response message for Operations.ListOperations.",
"id": "ListOperationsResponse",
"properties": {
"nextPageToken": {
"description": "The standard List next-page token.",
"type": "string"
},
"operations": {
"description": "A list of operations that matches the specified filter in the request.",
"items": {
"$ref": "Operation"
},
"type": "array"
}
},
"type": "object"
},
"LongRunningRecognizeMetadata": {
"description": "Describes the progress of a long-running `LongRunningRecognize` call. It is\nincluded in the `metadata` field of the `Operation` returned by the\n`GetOperation` call of the `google::longrunning::Operations` service.",
"id": "LongRunningRecognizeMetadata",
"properties": {
"lastUpdateTime": {
"description": "Output only. Time of the most recent processing update.",
"format": "google-datetime",
"type": "string"
},
"progressPercent": {
"description": "Output only. Approximate percentage of audio processed thus far. Guaranteed to be 100\nwhen the audio is fully processed and the results are available.",
"format": "int32",
"type": "integer"
},
"startTime": {
"description": "Output only. Time when the request was received.",
"format": "google-datetime",
"type": "string"
},
"uri": {
"description": "The URI of the audio file being transcribed. Empty if the audio was sent\nas byte content.",
"type": "string"
}
},
"type": "object"
},
"LongRunningRecognizeResponse": {
"description": "The only message returned to the client by the `LongRunningRecognize` method.\nIt contains the result as zero or more sequential SpeechRecognitionResult\nmessages. It is included in the `result.response` field of the `Operation`\nreturned by the `GetOperation` call of the `google::longrunning::Operations`\nservice.",
"id": "LongRunningRecognizeResponse",
"properties": {
"results": {
"description": "Output only. Sequential list of transcription results corresponding to\nsequential portions of audio.",
"items": {
"$ref": "SpeechRecognitionResult"
},
"type": "array"
}
},
"type": "object"
},
"Operation": {
"description": "This resource represents a long-running operation that is the result of a\nnetwork API call.",
"id": "Operation",
"properties": {
"done": {
"description": "If the value is `false`, it means the operation is still in progress.\nIf `true`, the operation is completed, and either `error` or `response` is\navailable.",
"type": "boolean"
},
"error": {
"$ref": "Status",
"description": "The error result of the operation in case of failure or cancellation."
},
"metadata": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"description": "Service-specific metadata associated with the operation. It typically\ncontains progress information and common metadata such as create time.\nSome services might not provide such metadata. Any method that returns a\nlong-running operation should document the metadata type, if any.",
"type": "object"
},
"name": {
"description": "The server-assigned name, which is only unique within the same service that\noriginally returns it. If you use the default HTTP mapping, the\n`name` should be a resource name ending with `operations/{unique_id}`.",
"type": "string"
},
"response": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"description": "The normal response of the operation in case of success. If the original\nmethod returns no data on success, such as `Delete`, the response is\n`google.protobuf.Empty`. If the original method is standard\n`Get`/`Create`/`Update`, the response should be the resource. For other\nmethods, the response should have the type `XxxResponse`, where `Xxx`\nis the original method name. For example, if the original method name\nis `TakeSnapshot()`, the inferred response type is\n`TakeSnapshotResponse`.",
"type": "object"
}
},
"type": "object"
},
"SpeechRecognitionAlternative": {
"description": "Alternative hypotheses (a.k.a. n-best list).",
"id": "SpeechRecognitionAlternative",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"transcript": {
"description": "Output only. Transcript text representing the words that the user spoke.",
"type": "string"
},
"words": {
"description": "Output only. A list of word-specific information for each recognized word.\nNote: When `enable_speaker_diarization` is true, you will see all the words\nfrom the beginning of the audio.",
"items": {
"$ref": "WordInfo"
},
"type": "array"
}
},
"type": "object"
},
"SpeechRecognitionResult": {
"description": "A speech recognition result corresponding to a portion of the audio.",
"id": "SpeechRecognitionResult",
"properties": {
"alternatives": {
"description": "Output only. May contain one or more recognition hypotheses (up to the\nmaximum specified in `max_alternatives`).\nThese alternatives are ordered in terms of accuracy, with the top (first)\nalternative being the most probable, as ranked by the recognizer.",
"items": {
"$ref": "SpeechRecognitionAlternative"
},
"type": "array"
},
"channelTag": {
"description": "Output only. For multi-channel audio, this is the channel number corresponding to the\nrecognized result for the audio from that channel.\nFor `audio_channel_count` = N, its output values can range from `1` to `N`.",
"format": "int32",
"type": "integer"
},
"languageCode": {
"description": "Output only. The\n[BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the\nlanguage in this result. This language code was detected to have the most\nlikelihood of being spoken in the audio.",
"type": "string"
}
},
"type": "object"
},
"Status": {
"description": "The `Status` type defines a logical error model that is suitable for\ndifferent programming environments, including REST APIs and RPC APIs. It is\nused by [gRPC](https://github.com/grpc). Each `Status` message contains\nthree pieces of data: error code, error message, and error details.\n\nYou can find out more about this error model and how to work with it in the\n[API Design Guide](https://cloud.google.com/apis/design/errors).",
"id": "Status",
"properties": {
"code": {
"description": "The status code, which should be an enum value of google.rpc.Code.",
"format": "int32",
"type": "integer"
},
"details": {
"description": "A list of messages that carry the error details. There is a common set of\nmessage types for APIs to use.",
"items": {
"additionalProperties": {
"description": "Properties of the object. Contains field @type with type URL.",
"type": "any"
},
"type": "object"
},
"type": "array"
},
"message": {
"description": "A developer-facing error message, which should be in English. Any\nuser-facing error message should be localized and sent in the\ngoogle.rpc.Status.details field, or localized by the client.",
"type": "string"
}
},
"type": "object"
},
"WordInfo": {
"description": "Word-specific information for recognized words.",
"id": "WordInfo",
"properties": {
"confidence": {
"description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"format": "float",
"type": "number"
},
"endOffset": {
"description": "Output only. Time offset relative to the beginning of the audio,\nand corresponding to the end of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"format": "google-duration",
"type": "string"
},
"speakerTag": {
"description": "Output only. A distinct integer value is assigned for every speaker within\nthe audio. This field specifies which one of those speakers was detected to\nhave spoken this word. Value ranges from `1` to\n`diarization_config.max_speaker_count` . `speaker_tag` is set if\n`diarization_config.enable_speaker_diarization` = `true` and only in the\ntop alternative.",
"format": "int32",
"type": "integer"
},
"startOffset": {
"description": "Output only. Time offset relative to the beginning of the audio,\nand corresponding to the start of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.",
"format": "google-duration",
"type": "string"
},
"word": {
"description": "Output only. The word corresponding to this set of information.",
"type": "string"
}
},
"type": "object"
}
},
"servicePath": "",
"title": "Cloud Speech-to-Text API",
"version": "v2beta1",
"version_module": true
}