Index: discovery/googleapis/speech__v1.json |
diff --git a/discovery/googleapis/speech__v1.json b/discovery/googleapis/speech__v1.json |
index b28560f7b7fcd22bfee599fa07da38e86a6aecba..de6b89420b4882f5a44354b6c2cbfe5e1e16ed9b 100644 |
--- a/discovery/googleapis/speech__v1.json |
+++ b/discovery/googleapis/speech__v1.json |
@@ -25,45 +25,6 @@ |
"ownerDomain": "google.com", |
"ownerName": "Google", |
"parameters": { |
- "upload_protocol": { |
- "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", |
- "location": "query", |
- "type": "string" |
- }, |
- "prettyPrint": { |
- "default": "true", |
- "description": "Returns response with indentations and line breaks.", |
- "location": "query", |
- "type": "boolean" |
- }, |
- "uploadType": { |
- "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", |
- "location": "query", |
- "type": "string" |
- }, |
- "fields": { |
- "description": "Selector specifying which fields to include in a partial response.", |
- "location": "query", |
- "type": "string" |
- }, |
- "callback": { |
- "description": "JSONP", |
- "location": "query", |
- "type": "string" |
- }, |
- "$.xgafv": { |
- "description": "V1 error format.", |
- "enum": [ |
- "1", |
- "2" |
- ], |
- "enumDescriptions": [ |
- "v1 error format", |
- "v2 error format" |
- ], |
- "location": "query", |
- "type": "string" |
- }, |
"alt": { |
"default": "json", |
"description": "Data format for response.", |
@@ -101,57 +62,58 @@ |
"location": "query", |
"type": "boolean" |
}, |
+ "bearer_token": { |
+ "description": "OAuth bearer token.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
"oauth_token": { |
"description": "OAuth 2.0 token for the current user.", |
"location": "query", |
"type": "string" |
}, |
- "bearer_token": { |
- "description": "OAuth bearer token.", |
+ "upload_protocol": { |
+ "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "prettyPrint": { |
+ "default": "true", |
+ "description": "Returns response with indentations and line breaks.", |
+ "location": "query", |
+ "type": "boolean" |
+ }, |
+ "uploadType": { |
+ "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "fields": { |
+ "description": "Selector specifying which fields to include in a partial response.", |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "$.xgafv": { |
+ "description": "V1 error format.", |
+ "enum": [ |
+ "1", |
+ "2" |
+ ], |
+ "enumDescriptions": [ |
+ "v1 error format", |
+ "v2 error format" |
+ ], |
+ "location": "query", |
+ "type": "string" |
+ }, |
+ "callback": { |
+ "description": "JSONP", |
"location": "query", |
"type": "string" |
} |
}, |
"protocol": "rest", |
"resources": { |
- "speech": { |
- "methods": { |
- "recognize": { |
- "description": "Performs synchronous speech recognition: receive results after all audio\nhas been sent and processed.", |
- "httpMethod": "POST", |
- "id": "speech.speech.recognize", |
- "parameterOrder": [], |
- "parameters": {}, |
- "path": "v1/speech:recognize", |
- "request": { |
- "$ref": "RecognizeRequest" |
- }, |
- "response": { |
- "$ref": "RecognizeResponse" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform" |
- ] |
- }, |
- "longrunningrecognize": { |
- "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.", |
- "httpMethod": "POST", |
- "id": "speech.speech.longrunningrecognize", |
- "parameterOrder": [], |
- "parameters": {}, |
- "path": "v1/speech:longrunningrecognize", |
- "request": { |
- "$ref": "LongRunningRecognizeRequest" |
- }, |
- "response": { |
- "$ref": "Operation" |
- }, |
- "scopes": [ |
- "https://www.googleapis.com/auth/cloud-platform" |
- ] |
- } |
- } |
- }, |
"operations": { |
"methods": { |
"cancel": { |
@@ -266,17 +228,171 @@ |
] |
} |
} |
+ }, |
+ "speech": { |
+ "methods": { |
+ "longrunningrecognize": { |
+ "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.", |
+ "httpMethod": "POST", |
+ "id": "speech.speech.longrunningrecognize", |
+ "parameterOrder": [], |
+ "parameters": {}, |
+ "path": "v1/speech:longrunningrecognize", |
+ "request": { |
+ "$ref": "LongRunningRecognizeRequest" |
+ }, |
+ "response": { |
+ "$ref": "Operation" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform" |
+ ] |
+ }, |
+ "recognize": { |
+ "description": "Performs synchronous speech recognition: receive results after all audio\nhas been sent and processed.", |
+ "httpMethod": "POST", |
+ "id": "speech.speech.recognize", |
+ "parameterOrder": [], |
+ "parameters": {}, |
+ "path": "v1/speech:recognize", |
+ "request": { |
+ "$ref": "RecognizeRequest" |
+ }, |
+ "response": { |
+ "$ref": "RecognizeResponse" |
+ }, |
+ "scopes": [ |
+ "https://www.googleapis.com/auth/cloud-platform" |
+ ] |
+ } |
+ } |
} |
}, |
- "revision": "20170705", |
+ "revision": "20170728", |
"rootUrl": "https://speech.googleapis.com/", |
"schemas": { |
+ "Operation": { |
+ "description": "This resource represents a long-running operation that is the result of a\nnetwork API call.", |
+ "id": "Operation", |
+ "properties": { |
+ "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" |
+ }, |
+ "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" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "RecognitionConfig": { |
+ "description": "Provides information to the recognizer that specifies how to process the\nrequest.", |
+ "id": "RecognitionConfig", |
+ "properties": { |
+ "enableWordTimeOffsets": { |
+ "description": "*Optional* If `true`, a list of `words` are returned in the top result,\ncontaining the start and end timestamps for those words. The default value,\n'false' does not return any word-level timing information.", |
+ "type": "boolean" |
+ }, |
+ "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.", |
+ "format": "int32", |
+ "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": { |
+ "description": "*Required* Encoding of audio data sent in all `RecognitionAudio` messages.", |
+ "enum": [ |
+ "ENCODING_UNSPECIFIED", |
+ "LINEAR16", |
+ "FLAC", |
+ "MULAW", |
+ "AMR", |
+ "AMR_WB", |
+ "OGG_OPUS", |
+ "SPEEX_WITH_HEADER_BYTE" |
+ ], |
+ "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." |
+ ], |
+ "type": "string" |
+ }, |
+ "sampleRateHertz": { |
+ "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).", |
+ "format": "int32", |
+ "type": "integer" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
+ "WordInfo": { |
+ "description": "Word-specific information detected along with speech recognition when certain\nrequest parameters are set.", |
+ "id": "WordInfo", |
+ "properties": { |
+ "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.", |
+ "format": "google-duration", |
+ "type": "string" |
+ }, |
+ "word": { |
+ "description": "*Output-only* The word corresponding to this set of information.", |
+ "type": "string" |
+ }, |
+ "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.", |
+ "format": "google-duration", |
+ "type": "string" |
+ } |
+ }, |
+ "type": "object" |
+ }, |
"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.", |
"id": "Status", |
"properties": { |
"details": { |
- "description": "A list of messages that carry the error details. There will be a\ncommon set of message types for APIs to use.", |
+ "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.", |
@@ -328,6 +444,13 @@ |
"format": "float", |
"type": "number" |
}, |
+ "words": { |
+ "description": "*Output-only* List of word-specific information for each recognized word.", |
+ "items": { |
+ "$ref": "WordInfo" |
+ }, |
+ "type": "array" |
+ }, |
"transcript": { |
"description": "*Output-only* Transcript text representing the words that the user spoke.", |
"type": "string" |
@@ -339,16 +462,16 @@ |
"description": "The response message for Operations.ListOperations.", |
"id": "ListOperationsResponse", |
"properties": { |
+ "nextPageToken": { |
+ "description": "The standard List next-page token.", |
+ "type": "string" |
+ }, |
"operations": { |
"description": "A list of operations that matches the specified filter in the request.", |
"items": { |
"$ref": "Operation" |
}, |
"type": "array" |
- }, |
- "nextPageToken": { |
- "description": "The standard List next-page token.", |
- "type": "string" |
} |
}, |
"type": "object" |
@@ -431,97 +554,6 @@ |
"id": "CancelOperationRequest", |
"properties": {}, |
"type": "object" |
- }, |
- "Operation": { |
- "description": "This resource represents a long-running operation that is the result of a\nnetwork API call.", |
- "id": "Operation", |
- "properties": { |
- "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" |
- }, |
- "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" |
- } |
- }, |
- "type": "object" |
- }, |
- "RecognitionConfig": { |
- "description": "Provides information to the recognizer that specifies how to process the\nrequest.", |
- "id": "RecognitionConfig", |
- "properties": { |
- "sampleRateHertz": { |
- "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).", |
- "format": "int32", |
- "type": "integer" |
- }, |
- "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.", |
- "format": "int32", |
- "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" |
- }, |
- "encoding": { |
- "description": "*Required* Encoding of audio data sent in all `RecognitionAudio` messages.", |
- "enum": [ |
- "ENCODING_UNSPECIFIED", |
- "LINEAR16", |
- "FLAC", |
- "MULAW", |
- "AMR", |
- "AMR_WB", |
- "OGG_OPUS", |
- "SPEEX_WITH_HEADER_BYTE" |
- ], |
- "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." |
- ], |
- "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.", |
- "type": "boolean" |
- } |
- }, |
- "type": "object" |
} |
}, |
"servicePath": "", |