blob: 0dba38ce4bb8ae5d4d5819594db6ef33c4ef2b40 [file] [log] [blame]
{
"discoveryVersion": "v1",
"version_module": true,
"schemas": {
"Empty": {
"description": "A generic empty message that you can re-use to avoid defining duplicated\nempty messages in your APIs. A typical example is to use it as the request\nor the response type of an API method. For instance:\n\n service Foo {\n rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);\n }\n\nThe JSON representation for `Empty` is empty JSON object `{}`.",
"type": "object",
"properties": {},
"id": "Empty"
},
"RecognizeRequest": {
"id": "RecognizeRequest",
"description": "The top-level message sent by the client for the `Recognize` method.",
"type": "object",
"properties": {
"audio": {
"description": "*Required* The audio data to be recognized.",
"$ref": "RecognitionAudio"
},
"config": {
"$ref": "RecognitionConfig",
"description": "*Required* Provides information to the recognizer that specifies how to\nprocess the request."
}
}
},
"SpeechRecognitionAlternative": {
"id": "SpeechRecognitionAlternative",
"description": "Alternative hypotheses (a.k.a. n-best list).",
"type": "object",
"properties": {
"words": {
"description": "*Output-only* A list of word-specific information for each recognized word.",
"items": {
"$ref": "WordInfo"
},
"type": "array"
},
"transcript": {
"description": "*Output-only* Transcript text representing the words that the user spoke.",
"type": "string"
},
"confidence": {
"format": "float",
"description": "*Output-only* The confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is typically provided only for the top hypothesis, and\nonly for `is_final=true` results. Clients should not rely on the\n`confidence` field as it is not guaranteed to be accurate or consistent.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.",
"type": "number"
}
}
},
"ListOperationsResponse": {
"id": "ListOperationsResponse",
"description": "The response message for Operations.ListOperations.",
"type": "object",
"properties": {
"nextPageToken": {
"description": "The standard List next-page token.",
"type": "string"
},
"operations": {
"description": "A list of operations that matches the specified filter in the request.",
"items": {
"$ref": "Operation"
},
"type": "array"
}
}
},
"SpeechContext": {
"description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases\nin the results.",
"type": "object",
"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](https://cloud.google.com/speech/limits#content).",
"items": {
"type": "string"
},
"type": "array"
}
},
"id": "SpeechContext"
},
"SpeechRecognitionResult": {
"description": "A speech recognition result corresponding to a portion of the audio.",
"type": "object",
"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": {
"$ref": "SpeechRecognitionAlternative"
},
"type": "array"
}
},
"id": "SpeechRecognitionResult"
},
"RecognitionAudio": {
"description": "Contains audio data in the encoding specified in the `RecognitionConfig`.\nEither `content` or `uri` must be supplied. Supplying both or neither\nreturns google.rpc.Code.INVALID_ARGUMENT. See\n[audio limits](https://cloud.google.com/speech/limits#content).",
"type": "object",
"properties": {
"content": {
"format": "byte",
"description": "The audio data bytes encoded as specified in\n`RecognitionConfig`. Note: as with all bytes fields, protobuffers use a\npure binary representation, whereas JSON representations use base64.",
"type": "string"
},
"uri": {
"description": "URI that points to a file that contains audio data bytes as specified in\n`RecognitionConfig`. Currently, only Google Cloud Storage URIs are\nsupported, which must be specified in the following format:\n`gs://bucket_name/object_name` (other URI formats return\ngoogle.rpc.Code.INVALID_ARGUMENT). For more information, see\n[Request URIs](https://cloud.google.com/storage/docs/reference-uris).",
"type": "string"
}
},
"id": "RecognitionAudio"
},
"LongRunningRecognizeRequest": {
"description": "The top-level message sent by the client for the `LongRunningRecognize`\nmethod.",
"type": "object",
"properties": {
"audio": {
"description": "*Required* The audio data to be recognized.",
"$ref": "RecognitionAudio"
},
"config": {
"$ref": "RecognitionConfig",
"description": "*Required* Provides information to the recognizer that specifies how to\nprocess the request."
}
},
"id": "LongRunningRecognizeRequest"
},
"RecognizeResponse": {
"description": "The only message returned to the client by the `Recognize` method. It\ncontains the result as zero or more sequential `SpeechRecognitionResult`\nmessages.",
"type": "object",
"properties": {
"results": {
"description": "*Output-only* Sequential list of transcription results corresponding to\nsequential portions of audio.",
"items": {
"$ref": "SpeechRecognitionResult"
},
"type": "array"
}
},
"id": "RecognizeResponse"
},
"CancelOperationRequest": {
"description": "The request message for Operations.CancelOperation.",
"type": "object",
"properties": {},
"id": "CancelOperationRequest"
},
"Operation": {
"id": "Operation",
"description": "This resource represents a long-running operation that is the result of a\nnetwork API call.",
"type": "object",
"properties": {
"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 have the format of `operations/some/unique/name`.",
"type": "string"
},
"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"
},
"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"
},
"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"
}
}
},
"RecognitionConfig": {
"id": "RecognitionConfig",
"description": "Provides information to the recognizer that specifies how to process the\nrequest.",
"type": "object",
"properties": {
"sampleRateHertz": {
"format": "int32",
"description": "*Required* Sample rate in Hertz of the audio data sent in all\n`RecognitionAudio` messages. Valid values are: 8000-48000.\n16000 is optimal. For best results, set the sampling rate of the audio\nsource to 16000 Hz. If that's not possible, use the native sample rate of\nthe audio source (instead of re-sampling).",
"type": "integer"
},
"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`.",
"type": "boolean"
},
"maxAlternatives": {
"format": "int32",
"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.",
"type": "integer"
},
"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](https://cloud.google.com/speech/docs/languages)\nfor a list of the currently supported language codes.",
"type": "string"
},
"speechContexts": {
"description": "*Optional* A means to provide context to assist the speech recognition.",
"items": {
"$ref": "SpeechContext"
},
"type": "array"
},
"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.",
"type": "boolean"
},
"encoding": {
"enumDescriptions": [
"Not specified. Will return result google.rpc.Code.INVALID_ARGUMENT.",
"Uncompressed 16-bit signed little-endian samples (Linear PCM).",
"[`FLAC`](https://xiph.org/flac/documentation.html) (Free Lossless Audio\nCodec) is the recommended encoding because it is\nlossless--therefore recognition is not compromised--and\nrequires only about half the bandwidth of `LINEAR16`. `FLAC` stream\nencoding supports 16-bit and 24-bit samples, however, not all fields in\n`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\n([OggOpus](https://wiki.xiph.org/OggOpus)).\n`sample_rate_hertz` must be 16000.",
"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."
],
"enum": [
"ENCODING_UNSPECIFIED",
"LINEAR16",
"FLAC",
"MULAW",
"AMR",
"AMR_WB",
"OGG_OPUS",
"SPEEX_WITH_HEADER_BYTE"
],
"description": "*Required* Encoding of audio data sent in all `RecognitionAudio` messages.",
"type": "string"
}
}
},
"WordInfo": {
"description": "Word-specific information for recognized words. Word information is only\nincluded in the response when certain request parameters are set, such\nas `enable_word_time_offsets`.",
"type": "object",
"properties": {
"endTime": {
"format": "google-duration",
"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.",
"type": "string"
},
"startTime": {
"format": "google-duration",
"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.",
"type": "string"
},
"word": {
"description": "*Output-only* The word corresponding to this set of information.",
"type": "string"
}
},
"id": "WordInfo"
},
"Status": {
"description": "The `Status` type defines a logical error model that is suitable for different\nprogramming environments, including REST APIs and RPC APIs. It is used by\n[gRPC](https://github.com/grpc). The error model is designed to be:\n\n- Simple to use and understand for most users\n- Flexible enough to meet unexpected needs\n\n# Overview\n\nThe `Status` message contains three pieces of data: error code, error message,\nand error details. The error code should be an enum value of\ngoogle.rpc.Code, but it may accept additional error codes if needed. The\nerror message should be a developer-facing English message that helps\ndevelopers *understand* and *resolve* the error. If a localized user-facing\nerror message is needed, put the localized message in the error details or\nlocalize it in the client. The optional error details may contain arbitrary\ninformation about the error. There is a predefined set of error detail types\nin the package `google.rpc` that can be used for common error conditions.\n\n# Language mapping\n\nThe `Status` message is the logical representation of the error model, but it\nis not necessarily the actual wire format. When the `Status` message is\nexposed in different client libraries and different wire protocols, it can be\nmapped differently. For example, it will likely be mapped to some exceptions\nin Java, but more likely mapped to some error codes in C.\n\n# Other uses\n\nThe error model and the `Status` message can be used in a variety of\nenvironments, either with or without APIs, to provide a\nconsistent developer experience across different environments.\n\nExample uses of this error model include:\n\n- Partial errors. If a service needs to return partial errors to the client,\n it may embed the `Status` in the normal response to indicate the partial\n errors.\n\n- Workflow errors. A typical workflow has multiple steps. Each step may\n have a `Status` message for error reporting.\n\n- Batch operations. If a client uses batch request and batch response, the\n `Status` message should be used directly inside batch response, one for\n each error sub-response.\n\n- Asynchronous operations. If an API call embeds asynchronous operation\n results in its response, the status of those operations should be\n represented directly using the `Status` message.\n\n- Logging. If some API errors are stored in logs, the message `Status` could\n be used directly after any stripping needed for security/privacy reasons.",
"type": "object",
"properties": {
"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"
},
"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"
},
"code": {
"format": "int32",
"description": "The status code, which should be an enum value of google.rpc.Code.",
"type": "integer"
}
},
"id": "Status"
}
},
"icons": {
"x32": "http://www.google.com/images/icons/product/search-32.gif",
"x16": "http://www.google.com/images/icons/product/search-16.gif"
},
"protocol": "rest",
"canonicalName": "Speech",
"auth": {
"oauth2": {
"scopes": {
"https://www.googleapis.com/auth/cloud-platform": {
"description": "View and manage your data across Google Cloud Platform services"
}
}
}
},
"rootUrl": "https://speech.googleapis.com/",
"ownerDomain": "google.com",
"name": "speech",
"batchPath": "batch",
"title": "Google Cloud Speech API",
"ownerName": "Google",
"resources": {
"operations": {
"methods": {
"delete": {
"path": "v1/operations/{+name}",
"id": "speech.operations.delete",
"description": "Deletes a long-running operation. This method indicates that the client is\nno longer interested in the operation result. It does not cancel the\noperation. If the server doesn't support this method, it returns\n`google.rpc.Code.UNIMPLEMENTED`.",
"httpMethod": "DELETE",
"response": {
"$ref": "Empty"
},
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"pattern": "^[^/]+$",
"location": "path",
"description": "The name of the operation resource to be deleted.",
"type": "string",
"required": true
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"flatPath": "v1/operations/{operationsId}"
},
"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.",
"httpMethod": "GET",
"response": {
"$ref": "Operation"
},
"parameterOrder": [
"name"
],
"parameters": {
"name": {
"description": "The name of the operation resource.",
"type": "string",
"required": true,
"pattern": "^[^/]+$",
"location": "path"
}
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"flatPath": "v1/operations/{operationsId}",
"path": "v1/operations/{+name}",
"id": "speech.operations.get"
},
"list": {
"path": "v1/operations",
"id": "speech.operations.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.",
"httpMethod": "GET",
"parameterOrder": [],
"response": {
"$ref": "ListOperationsResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"pageToken": {
"location": "query",
"description": "The standard list page token.",
"type": "string"
},
"name": {
"location": "query",
"description": "The name of the operation's parent resource.",
"type": "string"
},
"pageSize": {
"format": "int32",
"description": "The standard list page size.",
"type": "integer",
"location": "query"
},
"filter": {
"location": "query",
"description": "The standard list filter.",
"type": "string"
}
},
"flatPath": "v1/operations"
},
"cancel": {
"request": {
"$ref": "CancelOperationRequest"
},
"description": "Starts asynchronous cancellation on a long-running operation. The server\nmakes a best effort to cancel the operation, but success is not\nguaranteed. If the server doesn't support this method, it returns\n`google.rpc.Code.UNIMPLEMENTED`. Clients can use\nOperations.GetOperation or\nother methods to check whether the cancellation succeeded or whether the\noperation completed despite cancellation. On successful cancellation,\nthe operation is not deleted; instead, it becomes an operation with\nan Operation.error value with a google.rpc.Status.code of 1,\ncorresponding to `Code.CANCELLED`.",
"response": {
"$ref": "Empty"
},
"parameterOrder": [
"name"
],
"httpMethod": "POST",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {
"name": {
"description": "The name of the operation resource to be cancelled.",
"type": "string",
"required": true,
"pattern": "^[^/]+$",
"location": "path"
}
},
"flatPath": "v1/operations/{operationsId}:cancel",
"id": "speech.operations.cancel",
"path": "v1/operations/{+name}:cancel"
}
}
},
"speech": {
"methods": {
"longrunningrecognize": {
"id": "speech.speech.longrunningrecognize",
"path": "v1/speech:longrunningrecognize",
"request": {
"$ref": "LongRunningRecognizeRequest"
},
"description": "Performs asynchronous speech recognition: receive results via the\ngoogle.longrunning.Operations interface. Returns either an\n`Operation.error` or an `Operation.response` which contains\na `LongRunningRecognizeResponse` message.",
"response": {
"$ref": "Operation"
},
"parameterOrder": [],
"httpMethod": "POST",
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {},
"flatPath": "v1/speech:longrunningrecognize"
},
"recognize": {
"request": {
"$ref": "RecognizeRequest"
},
"description": "Performs synchronous speech recognition: receive results after all audio\nhas been sent and processed.",
"httpMethod": "POST",
"parameterOrder": [],
"response": {
"$ref": "RecognizeResponse"
},
"scopes": [
"https://www.googleapis.com/auth/cloud-platform"
],
"parameters": {},
"flatPath": "v1/speech:recognize",
"path": "v1/speech:recognize",
"id": "speech.speech.recognize"
}
}
}
},
"parameters": {
"access_token": {
"location": "query",
"description": "OAuth access token.",
"type": "string"
},
"key": {
"location": "query",
"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.",
"type": "string"
},
"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.",
"type": "string",
"location": "query"
},
"pp": {
"description": "Pretty-print response.",
"default": "true",
"type": "boolean",
"location": "query"
},
"bearer_token": {
"description": "OAuth bearer token.",
"type": "string",
"location": "query"
},
"oauth_token": {
"location": "query",
"description": "OAuth 2.0 token for the current user.",
"type": "string"
},
"upload_protocol": {
"location": "query",
"description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
"type": "string"
},
"prettyPrint": {
"description": "Returns response with indentations and line breaks.",
"default": "true",
"type": "boolean",
"location": "query"
},
"uploadType": {
"location": "query",
"description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
"type": "string"
},
"fields": {
"location": "query",
"description": "Selector specifying which fields to include in a partial response.",
"type": "string"
},
"$.xgafv": {
"enumDescriptions": [
"v1 error format",
"v2 error format"
],
"location": "query",
"enum": [
"1",
"2"
],
"description": "V1 error format.",
"type": "string"
},
"callback": {
"description": "JSONP",
"type": "string",
"location": "query"
},
"alt": {
"type": "string",
"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",
"description": "Data format for response.",
"default": "json",
"enum": [
"json",
"media",
"proto"
]
}
},
"version": "v1",
"baseUrl": "https://speech.googleapis.com/",
"servicePath": "",
"description": "Converts audio to text by applying powerful neural network models.",
"kind": "discovery#restDescription",
"basePath": "",
"documentationLink": "https://cloud.google.com/speech/",
"revision": "20170822",
"id": "speech:v1"
}