| { |
| "fullyEncodeReservedExpansion": true, |
| "parameters": { |
| "fields": { |
| "location": "query", |
| "type": "string", |
| "description": "Selector specifying which fields to include in a partial response." |
| }, |
| "callback": { |
| "description": "JSONP", |
| "location": "query", |
| "type": "string" |
| }, |
| "quotaUser": { |
| "location": "query", |
| "type": "string", |
| "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." |
| }, |
| "oauth_token": { |
| "type": "string", |
| "location": "query", |
| "description": "OAuth 2.0 token for the current user." |
| }, |
| "key": { |
| "location": "query", |
| "type": "string", |
| "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." |
| }, |
| "uploadType": { |
| "type": "string", |
| "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", |
| "location": "query" |
| }, |
| "prettyPrint": { |
| "default": "true", |
| "location": "query", |
| "description": "Returns response with indentations and line breaks.", |
| "type": "boolean" |
| }, |
| "$.xgafv": { |
| "type": "string", |
| "description": "V1 error format.", |
| "location": "query", |
| "enumDescriptions": [ |
| "v1 error format", |
| "v2 error format" |
| ], |
| "enum": [ |
| "1", |
| "2" |
| ] |
| }, |
| "access_token": { |
| "type": "string", |
| "description": "OAuth access token.", |
| "location": "query" |
| }, |
| "upload_protocol": { |
| "type": "string", |
| "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", |
| "location": "query" |
| }, |
| "alt": { |
| "description": "Data format for response.", |
| "type": "string", |
| "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" |
| ], |
| "default": "json", |
| "location": "query" |
| } |
| }, |
| "documentationLink": "https://cloud.google.com/speech-to-text/docs/quickstart-protocol", |
| "batchPath": "batch", |
| "servicePath": "", |
| "version_module": true, |
| "icons": { |
| "x16": "http://www.google.com/images/icons/product/search-16.gif", |
| "x32": "http://www.google.com/images/icons/product/search-32.gif" |
| }, |
| "version": "v1", |
| "ownerDomain": "google.com", |
| "basePath": "", |
| "title": "Cloud Speech-to-Text API", |
| "name": "speech", |
| "id": "speech:v1", |
| "auth": { |
| "oauth2": { |
| "scopes": { |
| "https://www.googleapis.com/auth/cloud-platform": { |
| "description": "View and manage your data across Google Cloud Platform services" |
| } |
| } |
| } |
| }, |
| "description": "Converts audio to text by applying powerful neural network models.", |
| "canonicalName": "Speech", |
| "rootUrl": "https://speech.googleapis.com/", |
| "mtlsRootUrl": "https://speech.mtls.googleapis.com/", |
| "revision": "20200824", |
| "ownerName": "Google", |
| "resources": { |
| "speech": { |
| "methods": { |
| "recognize": { |
| "httpMethod": "POST", |
| "request": { |
| "$ref": "RecognizeRequest" |
| }, |
| "description": "Performs synchronous speech recognition: receive results after all audio has been sent and processed.", |
| "path": "v1/speech:recognize", |
| "id": "speech.speech.recognize", |
| "flatPath": "v1/speech:recognize", |
| "parameterOrder": [], |
| "scopes": [ |
| "https://www.googleapis.com/auth/cloud-platform" |
| ], |
| "parameters": {}, |
| "response": { |
| "$ref": "RecognizeResponse" |
| } |
| }, |
| "longrunningrecognize": { |
| "flatPath": "v1/speech:longrunningrecognize", |
| "path": "v1/speech:longrunningrecognize", |
| "response": { |
| "$ref": "Operation" |
| }, |
| "description": "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).", |
| "parameterOrder": [], |
| "parameters": {}, |
| "httpMethod": "POST", |
| "id": "speech.speech.longrunningrecognize", |
| "scopes": [ |
| "https://www.googleapis.com/auth/cloud-platform" |
| ], |
| "request": { |
| "$ref": "LongRunningRecognizeRequest" |
| } |
| } |
| } |
| }, |
| "projects": { |
| "resources": { |
| "locations": { |
| "resources": { |
| "operations": { |
| "methods": { |
| "list": { |
| "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`. NOTE: the `name` binding allows API services to override the binding to use different resource name schemes, such as `users/*/operations`. To override the binding, API services can add a binding such as `\"/v1/{name=users/*}/operations\"` to their service configuration. For backwards compatibility, the default name includes the operations collection id, however overriding users must ensure the name binding is the parent resource, without the operations collection id.", |
| "parameters": { |
| "pageSize": { |
| "type": "integer", |
| "format": "int32", |
| "description": "The standard list page size.", |
| "location": "query" |
| }, |
| "filter": { |
| "location": "query", |
| "type": "string", |
| "description": "The standard list filter." |
| }, |
| "pageToken": { |
| "location": "query", |
| "type": "string", |
| "description": "The standard list page token." |
| }, |
| "name": { |
| "required": true, |
| "description": "The name of the operation's parent resource.", |
| "pattern": "^projects/[^/]+/locations/[^/]+$", |
| "location": "path", |
| "type": "string" |
| } |
| }, |
| "parameterOrder": [ |
| "name" |
| ], |
| "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations", |
| "scopes": [ |
| "https://www.googleapis.com/auth/cloud-platform" |
| ], |
| "path": "v1/{+name}/operations", |
| "response": { |
| "$ref": "ListOperationsResponse" |
| }, |
| "httpMethod": "GET", |
| "id": "speech.projects.locations.operations.list" |
| }, |
| "get": { |
| "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/operations/{operationsId}", |
| "scopes": [ |
| "https://www.googleapis.com/auth/cloud-platform" |
| ], |
| "description": "Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.", |
| "httpMethod": "GET", |
| "path": "v1/{+name}", |
| "parameters": { |
| "name": { |
| "location": "path", |
| "pattern": "^projects/[^/]+/locations/[^/]+/operations/[^/]+$", |
| "type": "string", |
| "required": true, |
| "description": "The name of the operation resource." |
| } |
| }, |
| "response": { |
| "$ref": "Operation" |
| }, |
| "id": "speech.projects.locations.operations.get", |
| "parameterOrder": [ |
| "name" |
| ] |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "operations": { |
| "methods": { |
| "get": { |
| "httpMethod": "GET", |
| "parameters": { |
| "name": { |
| "description": "The name of the operation resource.", |
| "location": "path", |
| "required": true, |
| "type": "string", |
| "pattern": "^.*$" |
| } |
| }, |
| "parameterOrder": [ |
| "name" |
| ], |
| "scopes": [ |
| "https://www.googleapis.com/auth/cloud-platform" |
| ], |
| "flatPath": "v1/operations/{operationsId}", |
| "description": "Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.", |
| "path": "v1/operations/{+name}", |
| "id": "speech.operations.get", |
| "response": { |
| "$ref": "Operation" |
| } |
| }, |
| "list": { |
| "response": { |
| "$ref": "ListOperationsResponse" |
| }, |
| "path": "v1/operations", |
| "httpMethod": "GET", |
| "description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`. NOTE: the `name` binding allows API services to override the binding to use different resource name schemes, such as `users/*/operations`. To override the binding, API services can add a binding such as `\"/v1/{name=users/*}/operations\"` to their service configuration. For backwards compatibility, the default name includes the operations collection id, however overriding users must ensure the name binding is the parent resource, without the operations collection id.", |
| "flatPath": "v1/operations", |
| "id": "speech.operations.list", |
| "parameterOrder": [], |
| "scopes": [ |
| "https://www.googleapis.com/auth/cloud-platform" |
| ], |
| "parameters": { |
| "filter": { |
| "type": "string", |
| "description": "The standard list filter.", |
| "location": "query" |
| }, |
| "pageSize": { |
| "type": "integer", |
| "format": "int32", |
| "description": "The standard list page size.", |
| "location": "query" |
| }, |
| "pageToken": { |
| "type": "string", |
| "description": "The standard list page token.", |
| "location": "query" |
| }, |
| "name": { |
| "description": "The name of the operation's parent resource.", |
| "type": "string", |
| "location": "query" |
| } |
| } |
| } |
| } |
| } |
| }, |
| "kind": "discovery#restDescription", |
| "baseUrl": "https://speech.googleapis.com/", |
| "protocol": "rest", |
| "schemas": { |
| "LongRunningRecognizeResponse": { |
| "properties": { |
| "results": { |
| "type": "array", |
| "items": { |
| "$ref": "SpeechRecognitionResult" |
| }, |
| "description": "Sequential list of transcription results corresponding to sequential portions of audio." |
| } |
| }, |
| "description": "The only message returned to the client by the `LongRunningRecognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages. It is included in the `result.response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.", |
| "type": "object", |
| "id": "LongRunningRecognizeResponse" |
| }, |
| "LongRunningRecognizeMetadata": { |
| "id": "LongRunningRecognizeMetadata", |
| "properties": { |
| "lastUpdateTime": { |
| "description": "Time of the most recent processing update.", |
| "format": "google-datetime", |
| "type": "string" |
| }, |
| "progressPercent": { |
| "description": "Approximate percentage of audio processed thus far. Guaranteed to be 100 when the audio is fully processed and the results are available.", |
| "format": "int32", |
| "type": "integer" |
| }, |
| "startTime": { |
| "description": "Time when the request was received.", |
| "format": "google-datetime", |
| "type": "string" |
| }, |
| "uri": { |
| "description": "Output only. The URI of the audio file being transcribed. Empty if the audio was sent as byte content.", |
| "readOnly": true, |
| "type": "string" |
| } |
| }, |
| "type": "object", |
| "description": "Describes the progress of a long-running `LongRunningRecognize` call. It is included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service." |
| }, |
| "RecognitionMetadata": { |
| "description": "Description of audio data to be recognized.", |
| "type": "object", |
| "id": "RecognitionMetadata", |
| "properties": { |
| "microphoneDistance": { |
| "description": "The audio type that most closely describes the audio being recognized.", |
| "enumDescriptions": [ |
| "Audio type is not known.", |
| "The audio was captured from a closely placed microphone. Eg. phone, dictaphone, or handheld microphone. Generally if there speaker is within 1 meter of the microphone.", |
| "The speaker if within 3 meters of the microphone.", |
| "The speaker is more than 3 meters away from the microphone." |
| ], |
| "enum": [ |
| "MICROPHONE_DISTANCE_UNSPECIFIED", |
| "NEARFIELD", |
| "MIDFIELD", |
| "FARFIELD" |
| ], |
| "type": "string" |
| }, |
| "originalMimeType": { |
| "description": "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", |
| "type": "string" |
| }, |
| "recordingDeviceType": { |
| "enumDescriptions": [ |
| "The recording device is unknown.", |
| "Speech was recorded on a smartphone.", |
| "Speech was recorded using a personal computer or tablet.", |
| "Speech was recorded over a phone line.", |
| "Speech was recorded in a vehicle.", |
| "Speech was recorded outdoors.", |
| "Speech was recorded indoors." |
| ], |
| "type": "string", |
| "enum": [ |
| "RECORDING_DEVICE_TYPE_UNSPECIFIED", |
| "SMARTPHONE", |
| "PC", |
| "PHONE_LINE", |
| "VEHICLE", |
| "OTHER_OUTDOOR_DEVICE", |
| "OTHER_INDOOR_DEVICE" |
| ], |
| "description": "The type of device the speech was recorded with." |
| }, |
| "audioTopic": { |
| "description": "Description of the content. Eg. \"Recordings of federal supreme court hearings from 2012\".", |
| "type": "string" |
| }, |
| "recordingDeviceName": { |
| "type": "string", |
| "description": "The device used to make the recording. Examples 'Nexus 5X' or 'Polycom SoundStation IP 6000' or 'POTS' or 'VoIP' or 'Cardioid Microphone'." |
| }, |
| "industryNaicsCodeOfAudio": { |
| "type": "integer", |
| "format": "uint32", |
| "description": "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/." |
| }, |
| "originalMediaType": { |
| "enumDescriptions": [ |
| "Unknown original media type.", |
| "The speech data is an audio recording.", |
| "The speech data originally recorded on a video." |
| ], |
| "enum": [ |
| "ORIGINAL_MEDIA_TYPE_UNSPECIFIED", |
| "AUDIO", |
| "VIDEO" |
| ], |
| "description": "The original media the speech was recorded on.", |
| "type": "string" |
| }, |
| "interactionType": { |
| "enum": [ |
| "INTERACTION_TYPE_UNSPECIFIED", |
| "DISCUSSION", |
| "PRESENTATION", |
| "PHONE_CALL", |
| "VOICEMAIL", |
| "PROFESSIONALLY_PRODUCED", |
| "VOICE_SEARCH", |
| "VOICE_COMMAND", |
| "DICTATION" |
| ], |
| "enumDescriptions": [ |
| "Use case is either unknown or is something other than one of the other values below.", |
| "Multiple people in a conversation or discussion. For example in a meeting with two or more people actively participating. Typically all the primary people speaking would be in the same room (if not, see PHONE_CALL)", |
| "One or more persons lecturing or presenting to others, mostly uninterrupted.", |
| "A phone-call or video-conference in which two or more people, who are not in the same room, are actively participating.", |
| "A recorded message intended for another person to listen to.", |
| "Professionally produced audio (eg. TV Show, Podcast).", |
| "Transcribe spoken questions and queries into text.", |
| "Transcribe voice commands, such as for controlling a device.", |
| "Transcribe speech to text to create a written document, such as a text-message, email or report." |
| ], |
| "type": "string", |
| "description": "The use case most closely describing the audio content to be recognized." |
| } |
| } |
| }, |
| "SpeechContext": { |
| "properties": { |
| "phrases": { |
| "type": "array", |
| "items": { |
| "type": "string" |
| }, |
| "description": "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 $MONTH class improves the likelihood of correctly transcribing audio that includes months." |
| } |
| }, |
| "id": "SpeechContext", |
| "type": "object", |
| "description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases in the results." |
| }, |
| "Operation": { |
| "id": "Operation", |
| "properties": { |
| "metadata": { |
| "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.", |
| "additionalProperties": { |
| "type": "any", |
| "description": "Properties of the object. Contains field @type with type URL." |
| }, |
| "type": "object" |
| }, |
| "error": { |
| "description": "The error result of the operation in case of failure or cancellation.", |
| "$ref": "Status" |
| }, |
| "response": { |
| "description": "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`.", |
| "additionalProperties": { |
| "type": "any", |
| "description": "Properties of the object. Contains field @type with type URL." |
| }, |
| "type": "object" |
| }, |
| "name": { |
| "type": "string", |
| "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`." |
| }, |
| "done": { |
| "type": "boolean", |
| "description": "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." |
| } |
| }, |
| "description": "This resource represents a long-running operation that is the result of a network API call.", |
| "type": "object" |
| }, |
| "WordInfo": { |
| "properties": { |
| "startTime": { |
| "type": "string", |
| "description": "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.", |
| "format": "google-duration" |
| }, |
| "speakerTag": { |
| "format": "int32", |
| "type": "integer", |
| "readOnly": true, |
| "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from '1' to diarization_speaker_count. speaker_tag is set if enable_speaker_diarization = 'true' and only in the top alternative." |
| }, |
| "endTime": { |
| "description": "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.", |
| "format": "google-duration", |
| "type": "string" |
| }, |
| "word": { |
| "type": "string", |
| "description": "The word corresponding to this set of information." |
| } |
| }, |
| "type": "object", |
| "description": "Word-specific information for recognized words.", |
| "id": "WordInfo" |
| }, |
| "LongRunningRecognizeRequest": { |
| "id": "LongRunningRecognizeRequest", |
| "type": "object", |
| "description": "The top-level message sent by the client for the `LongRunningRecognize` method.", |
| "properties": { |
| "config": { |
| "description": "Required. Provides information to the recognizer that specifies how to process the request.", |
| "$ref": "RecognitionConfig" |
| }, |
| "audio": { |
| "$ref": "RecognitionAudio", |
| "description": "Required. The audio data to be recognized." |
| } |
| } |
| }, |
| "ListOperationsResponse": { |
| "properties": { |
| "operations": { |
| "description": "A list of operations that matches the specified filter in the request.", |
| "type": "array", |
| "items": { |
| "$ref": "Operation" |
| } |
| }, |
| "nextPageToken": { |
| "type": "string", |
| "description": "The standard List next-page token." |
| } |
| }, |
| "id": "ListOperationsResponse", |
| "type": "object", |
| "description": "The response message for Operations.ListOperations." |
| }, |
| "SpeakerDiarizationConfig": { |
| "type": "object", |
| "id": "SpeakerDiarizationConfig", |
| "properties": { |
| "minSpeakerCount": { |
| "type": "integer", |
| "format": "int32", |
| "description": "Minimum number of speakers in the conversation. This range gives you more flexibility by allowing the system to automatically determine the correct number of speakers. If not set, the default value is 2." |
| }, |
| "speakerTag": { |
| "readOnly": true, |
| "format": "int32", |
| "description": "Output only. Unused.", |
| "type": "integer" |
| }, |
| "enableSpeakerDiarization": { |
| "type": "boolean", |
| "description": "If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo." |
| }, |
| "maxSpeakerCount": { |
| "format": "int32", |
| "description": "Maximum number of speakers in the conversation. This range gives you more flexibility by allowing the system to automatically determine the correct number of speakers. If not set, the default value is 6.", |
| "type": "integer" |
| } |
| }, |
| "description": "Config to enable speaker diarization." |
| }, |
| "RecognizeRequest": { |
| "description": "The top-level message sent by the client for the `Recognize` method.", |
| "properties": { |
| "config": { |
| "description": "Required. Provides information to the recognizer that specifies how to process the request.", |
| "$ref": "RecognitionConfig" |
| }, |
| "audio": { |
| "$ref": "RecognitionAudio", |
| "description": "Required. The audio data to be recognized." |
| } |
| }, |
| "type": "object", |
| "id": "RecognizeRequest" |
| }, |
| "SpeechRecognitionResult": { |
| "properties": { |
| "alternatives": { |
| "items": { |
| "$ref": "SpeechRecognitionAlternative" |
| }, |
| "type": "array", |
| "description": "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." |
| }, |
| "channelTag": { |
| "description": "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'.", |
| "type": "integer", |
| "format": "int32" |
| } |
| }, |
| "type": "object", |
| "description": "A speech recognition result corresponding to a portion of the audio.", |
| "id": "SpeechRecognitionResult" |
| }, |
| "RecognitionAudio": { |
| "type": "object", |
| "id": "RecognitionAudio", |
| "description": "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).", |
| "properties": { |
| "content": { |
| "type": "string", |
| "format": "byte", |
| "description": "The audio data bytes encoded as specified in `RecognitionConfig`. Note: as with all bytes fields, proto buffers use a pure binary representation, whereas JSON representations use base64." |
| }, |
| "uri": { |
| "type": "string", |
| "description": "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)." |
| } |
| } |
| }, |
| "RecognizeResponse": { |
| "id": "RecognizeResponse", |
| "properties": { |
| "results": { |
| "type": "array", |
| "items": { |
| "$ref": "SpeechRecognitionResult" |
| }, |
| "description": "Sequential list of transcription results corresponding to sequential portions of audio." |
| } |
| }, |
| "type": "object", |
| "description": "The only message returned to the client by the `Recognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages." |
| }, |
| "RecognitionConfig": { |
| "id": "RecognitionConfig", |
| "description": "Provides information to the recognizer that specifies how to process the request.", |
| "type": "object", |
| "properties": { |
| "enableSeparateRecognitionPerChannel": { |
| "type": "boolean", |
| "description": "This needs to be set to `true` explicitly and `audio_channel_count` \u003e 1 to get each channel recognized separately. The recognition result will contain a `channel_tag` field to state which channel that result belongs to. If this is not true, we will only recognize the first channel. The request is billed cumulatively for all channels recognized: `audio_channel_count` multiplied by the length of the audio." |
| }, |
| "sampleRateHertz": { |
| "description": "Sample rate in Hertz of the audio data sent in all `RecognitionAudio` messages. Valid values are: 8000-48000. 16000 is optimal. For best results, set the sampling rate of the audio source to 16000 Hz. If that's not possible, use the native sample rate of the audio source (instead of re-sampling). This field is optional for FLAC and WAV audio files, but is required for all other audio formats. For details, see AudioEncoding.", |
| "type": "integer", |
| "format": "int32" |
| }, |
| "speechContexts": { |
| "description": "Array of SpeechContext. A means to provide context to assist the speech recognition. For more information, see [speech adaptation](https://cloud.google.com/speech-to-text/docs/context-strength).", |
| "type": "array", |
| "items": { |
| "$ref": "SpeechContext" |
| } |
| }, |
| "enableAutomaticPunctuation": { |
| "description": "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.", |
| "type": "boolean" |
| }, |
| "audioChannelCount": { |
| "description": "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'.", |
| "type": "integer", |
| "format": "int32" |
| }, |
| "profanityFilter": { |
| "description": "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.", |
| "type": "boolean" |
| }, |
| "useEnhanced": { |
| "type": "boolean", |
| "description": "Set to true to use an enhanced model for speech recognition. If `use_enhanced` is set to true and the `model` field is not set, then an appropriate enhanced model is chosen if an enhanced model exists for the audio. If `use_enhanced` is true and an enhanced version of the specified model does not exist, then the speech is recognized using the standard version of the specified model." |
| }, |
| "metadata": { |
| "description": "Metadata regarding this request.", |
| "$ref": "RecognitionMetadata" |
| }, |
| "maxAlternatives": { |
| "type": "integer", |
| "description": "Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechRecognitionResult`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one.", |
| "format": "int32" |
| }, |
| "languageCode": { |
| "type": "string", |
| "description": "Required. The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: \"en-US\". See [Language Support](https://cloud.google.com/speech-to-text/docs/languages) for a list of the currently supported language codes." |
| }, |
| "enableWordTimeOffsets": { |
| "type": "boolean", |
| "description": "If `true`, the top result includes a list of words and the start and end time offsets (timestamps) for those words. If `false`, no word-level time offset information is returned. The default is `false`." |
| }, |
| "diarizationConfig": { |
| "$ref": "SpeakerDiarizationConfig", |
| "description": "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." |
| }, |
| "encoding": { |
| "enum": [ |
| "ENCODING_UNSPECIFIED", |
| "LINEAR16", |
| "FLAC", |
| "MULAW", |
| "AMR", |
| "AMR_WB", |
| "OGG_OPUS", |
| "SPEEX_WITH_HEADER_BYTE" |
| ], |
| "enumDescriptions": [ |
| "Not specified.", |
| "Uncompressed 16-bit signed little-endian samples (Linear PCM).", |
| "`FLAC` (Free Lossless Audio Codec) is the recommended encoding because it is lossless--therefore recognition is not compromised--and requires only about half the bandwidth of `LINEAR16`. `FLAC` stream encoding supports 16-bit and 24-bit samples, however, not all fields in `STREAMINFO` are supported.", |
| "8-bit samples that compand 14-bit audio samples using G.711 PCMU/mu-law.", |
| "Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.", |
| "Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.", |
| "Opus encoded audio frames in Ogg container ([OggOpus](https://wiki.xiph.org/OggOpus)). `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 bitrate encoding is required, `OGG_OPUS` is highly preferred over Speex encoding. The [Speex](https://speex.org/) encoding supported by Cloud Speech API has a header byte in each block, as in MIME type `audio/x-speex-with-header-byte`. It is a variant of the RTP Speex encoding defined in [RFC 5574](https://tools.ietf.org/html/rfc5574). The stream is a sequence of blocks, one block per RTP packet. Each block starts with a byte containing the length of the block, in bytes, followed by one or more frames of Speex data, padded to an integral number of bytes (octets) as specified in RFC 5574. In other words, each RTP header is replaced with a single byte containing the block length. Only Speex wideband is supported. `sample_rate_hertz` must be 16000." |
| ], |
| "type": "string", |
| "description": "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." |
| }, |
| "model": { |
| "description": "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. ", |
| "type": "string" |
| } |
| } |
| }, |
| "SpeechRecognitionAlternative": { |
| "id": "SpeechRecognitionAlternative", |
| "properties": { |
| "confidence": { |
| "format": "float", |
| "type": "number", |
| "description": "The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative of a non-streaming result or, of a streaming result where `is_final=true`. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set." |
| }, |
| "transcript": { |
| "description": "Transcript text representing the words that the user spoke.", |
| "type": "string" |
| }, |
| "words": { |
| "type": "array", |
| "description": "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.", |
| "items": { |
| "$ref": "WordInfo" |
| } |
| } |
| }, |
| "description": "Alternative hypotheses (a.k.a. n-best list).", |
| "type": "object" |
| }, |
| "Status": { |
| "description": "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).", |
| "type": "object", |
| "id": "Status", |
| "properties": { |
| "code": { |
| "description": "The status code, which should be an enum value of google.rpc.Code.", |
| "format": "int32", |
| "type": "integer" |
| }, |
| "message": { |
| "type": "string", |
| "description": "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." |
| }, |
| "details": { |
| "type": "array", |
| "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use.", |
| "items": { |
| "type": "object", |
| "additionalProperties": { |
| "description": "Properties of the object. Contains field @type with type URL.", |
| "type": "any" |
| } |
| } |
| } |
| } |
| } |
| }, |
| "discoveryVersion": "v1" |
| } |
