/** * Copyright 2019 Google LLC * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ import { GaxiosPromise } from 'gaxios'; import { Compute, JWT, OAuth2Client, UserRefreshClient } from 'google-auth-library'; import { BodyResponseCallback, GlobalOptions, GoogleConfigurable, MethodOptions } from 'googleapis-common'; export declare namespace speech_v1p1beta1 { interface Options extends GlobalOptions { version: 'v1p1beta1'; } interface StandardParameters { /** * V1 error format. */ '$.xgafv'?: string; /** * OAuth access token. */ access_token?: string; /** * Data format for response. */ alt?: string; /** * JSONP */ callback?: string; /** * Selector specifying which fields to include in a partial response. */ fields?: string; /** * API key. Your API key identifies your project and provides you with API * access, quota, and reports. Required unless you provide an OAuth 2.0 * token. */ key?: string; /** * OAuth 2.0 token for the current user. */ oauth_token?: string; /** * Returns response with indentations and line breaks. */ prettyPrint?: boolean; /** * Available to use for quota purposes for server-side applications. Can be * any arbitrary string assigned to a user, but should not exceed 40 * characters. */ quotaUser?: string; /** * Legacy upload protocol for media (e.g. "media", "multipart"). */ uploadType?: string; /** * Upload protocol for media (e.g. "raw", "multipart"). */ upload_protocol?: string; } /** * Cloud Speech-to-Text API * * Converts audio to text by applying powerful neural network models. * * @example * const {google} = require('googleapis'); * const speech = google.speech('v1p1beta1'); * * @namespace speech * @type {Function} * @version v1p1beta1 * @variation v1p1beta1 * @param {object=} options Options for Speech */ class Speech { operations: Resource$Operations; projects: Resource$Projects; speech: Resource$Speech; constructor(options: GlobalOptions, google?: GoogleConfigurable); } /** * The response message for Operations.ListOperations. */ interface Schema$ListOperationsResponse { /** * The standard List next-page token. */ nextPageToken?: string; /** * A list of operations that matches the specified filter in the request. */ operations?: Schema$Operation[]; } /** * 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. */ interface Schema$LongRunningRecognizeMetadata { /** * Time of the most recent processing update. */ lastUpdateTime?: string; /** * Approximate percentage of audio processed thus far. Guaranteed to be 100 * when the audio is fully processed and the results are available. */ progressPercent?: number; /** * Time when the request was received. */ startTime?: string; } /** * The top-level message sent by the client for the `LongRunningRecognize` * method. */ interface Schema$LongRunningRecognizeRequest { /** * *Required* The audio data to be recognized. */ audio?: Schema$RecognitionAudio; /** * *Required* Provides information to the recognizer that specifies how to * process the request. */ config?: Schema$RecognitionConfig; } /** * 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. */ interface Schema$LongRunningRecognizeResponse { /** * Output only. Sequential list of transcription results corresponding to * sequential portions of audio. */ results?: Schema$SpeechRecognitionResult[]; } /** * This resource represents a long-running operation that is the result of a * network API call. */ interface Schema$Operation { /** * If the value is `false`, it means the operation is still in progress. If * `true`, the operation is completed, and either `error` or `response` is * available. */ done?: boolean; /** * The error result of the operation in case of failure or cancellation. */ error?: Schema$Status; /** * 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. */ metadata?: { [key: string]: any; }; /** * 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 have the format of `operations/some/unique/name`. */ name?: string; /** * 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`. */ response?: { [key: string]: any; }; } /** * 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](/speech-to-text/quotas#content). */ interface Schema$RecognitionAudio { /** * The audio data bytes encoded as specified in `RecognitionConfig`. Note: * as with all bytes fields, protobuffers use a pure binary representation, * whereas JSON representations use base64. */ content?: string; /** * URI that points to a file that contains audio data bytes as specified in * `RecognitionConfig`. The file must not be compressed (for example, gzip). * Currently, only Google Cloud Storage URIs are supported, which must be * specified in the following format: `gs://bucket_name/object_name` (other * URI formats return google.rpc.Code.INVALID_ARGUMENT). For more * information, see [Request * URIs](https://cloud.google.com/storage/docs/reference-uris). */ uri?: string; } /** * Provides information to the recognizer that specifies how to process the * request. */ interface Schema$RecognitionConfig { /** * *Optional* A list of up to 3 additional * [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags, * listing possible alternative languages of the supplied audio. See * [Language Support](/speech-to-text/docs/languages) for a list of the * currently supported language codes. If alternative languages are listed, * recognition result will contain recognition in the most likely language * detected including the main language_code. The recognition result will * include the language tag of the language detected in the audio. Note: * This feature is only supported for Voice Command and Voice Search use * cases and performance may vary for other use cases (e.g., phone call * transcription). */ alternativeLanguageCodes?: string[]; /** * *Optional* 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'. */ audioChannelCount?: number; /** * *Optional* 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. */ diarizationConfig?: Schema$SpeakerDiarizationConfig; /** * *Optional* If set, specifies the estimated number of speakers in the * conversation. If not set, defaults to '2'. Ignored unless * enable_speaker_diarization is set to true." Note: Use * diarization_config instead. This field will be DEPRECATED soon. */ diarizationSpeakerCount?: number; /** * *Optional* 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. * Note: This is currently offered as an experimental service, complimentary * to all users. In the future this may be exclusively available as a * premium feature. */ enableAutomaticPunctuation?: boolean; /** * This needs to be set to `true` explicitly and `audio_channel_count` > * 1 to get each channel recognized separately. The recognition result will * contain a `channel_tag` field to state which channel that result belongs * to. If this is not true, we will only recognize the first channel. The * request is billed cumulatively for all channels recognized: * `audio_channel_count` multiplied by the length of the audio. */ enableSeparateRecognitionPerChannel?: boolean; /** * *Optional* If 'true', enables speaker detection for each * recognized word in the top alternative of the recognition result using a * speaker_tag provided in the WordInfo. Note: Use diarization_config * instead. This field will be DEPRECATED soon. */ enableSpeakerDiarization?: boolean; /** * *Optional* If `true`, the top result includes a list of words and the * confidence for those words. If `false`, no word-level confidence * information is returned. The default is `false`. */ enableWordConfidence?: boolean; /** * *Optional* 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`. */ enableWordTimeOffsets?: boolean; /** * 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. */ encoding?: string; /** * *Required* The language of the supplied audio as a * [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. * Example: "en-US". See [Language * Support](/speech-to-text/docs/languages) for a list of the currently * supported language codes. */ languageCode?: string; /** * *Optional* 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. */ maxAlternatives?: number; /** * *Optional* Metadata regarding this request. */ metadata?: Schema$RecognitionMetadata; /** * *Optional* 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. <table> <tr> * <td><b>Model</b></td> * <td><b>Description</b></td> </tr> * <tr> * <td><code>command_and_search</code></td> * <td>Best for short queries such as voice commands or voice * search.</td> </tr> <tr> * <td><code>phone_call</code></td> <td>Best * for audio that originated from a phone call (typically recorded at an * 8khz sampling rate).</td> </tr> <tr> * <td><code>video</code></td> <td>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.</td> </tr> <tr> * <td><code>default</code></td> <td>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.</td> </tr> </table> */ model?: string; /** * *Optional* 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. */ profanityFilter?: boolean; /** * 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`, `WAV`. and * 'MP3' audio files, and is required for all other audio formats. * For details, see AudioEncoding. */ sampleRateHertz?: number; /** * *Optional* array of SpeechContext. A means to provide context to assist * the speech recognition. For more information, see [Phrase * Hints](/speech-to-text/docs/basics#phrase-hints). */ speechContexts?: Schema$SpeechContext[]; /** * *Optional* Set to true to use an enhanced model for speech recognition. * If `use_enhanced` is set to true and the `model` field is not set, then * an appropriate enhanced model is chosen if: 1. project is eligible for * requesting enhanced models 2. an enhanced model exists for the audio If * `use_enhanced` is true and an enhanced version of the specified model * does not exist, then the speech is recognized using the standard version * of the specified model. Enhanced speech models require that you opt-in * to data logging using instructions in the * [documentation](/speech-to-text/docs/enable-data-logging). If you set * `use_enhanced` to true and you have not enabled audio logging, then you * will receive an error. */ useEnhanced?: boolean; } /** * Description of audio data to be recognized. */ interface Schema$RecognitionMetadata { /** * Description of the content. Eg. "Recordings of federal supreme court * hearings from 2012". */ audioTopic?: string; /** * 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/. */ industryNaicsCodeOfAudio?: number; /** * The use case most closely describing the audio content to be recognized. */ interactionType?: string; /** * The audio type that most closely describes the audio being recognized. */ microphoneDistance?: string; /** * Obfuscated (privacy-protected) ID of the user, to identify number of * unique users using the service. */ obfuscatedId?: string; /** * The original media the speech was recorded on. */ originalMediaType?: string; /** * Mime type of the original audio file. For example `audio/m4a`, * `audio/x-alaw-basic`, `audio/mp3`, `audio/3gpp`. A list of possible audio * mime types is maintained at * http://www.iana.org/assignments/media-types/media-types.xhtml#audio */ originalMimeType?: string; /** * The device used to make the recording. Examples 'Nexus 5X' or * 'Polycom SoundStation IP 6000' or 'POTS' or * 'VoIP' or 'Cardioid Microphone'. */ recordingDeviceName?: string; /** * The type of device the speech was recorded with. */ recordingDeviceType?: string; } /** * The top-level message sent by the client for the `Recognize` method. */ interface Schema$RecognizeRequest { /** * *Required* The audio data to be recognized. */ audio?: Schema$RecognitionAudio; /** * *Required* Provides information to the recognizer that specifies how to * process the request. */ config?: Schema$RecognitionConfig; } /** * The only message returned to the client by the `Recognize` method. It * contains the result as zero or more sequential `SpeechRecognitionResult` * messages. */ interface Schema$RecognizeResponse { /** * Output only. Sequential list of transcription results corresponding to * sequential portions of audio. */ results?: Schema$SpeechRecognitionResult[]; } interface Schema$SpeakerDiarizationConfig { /** * *Optional* 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. */ enableSpeakerDiarization?: boolean; /** * *Optional* Only used if diarization_speaker_count is not set. 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. */ maxSpeakerCount?: number; /** * *Optional* Only used if diarization_speaker_count is not set. 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. */ minSpeakerCount?: number; } /** * Provides "hints" to the speech recognizer to favor specific words * and phrases in the results. */ interface Schema$SpeechContext { /** * *Optional* A list of strings containing words and phrases * "hints" so that the speech recognition is more likely to * recognize them. This can be used to improve the accuracy for specific * words and phrases, for example, if specific commands are typically spoken * by the user. This can also be used to add additional words to the * vocabulary of the recognizer. See [usage * limits](/speech-to-text/quotas#content). */ phrases?: string[]; } /** * Alternative hypotheses (a.k.a. n-best list). */ interface Schema$SpeechRecognitionAlternative { /** * Output only. 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. */ confidence?: number; /** * Output only. Transcript text representing the words that the user spoke. */ transcript?: string; /** * Output only. 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. */ words?: Schema$WordInfo[]; } /** * A speech recognition result corresponding to a portion of the audio. */ interface Schema$SpeechRecognitionResult { /** * Output only. 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. */ alternatives?: Schema$SpeechRecognitionAlternative[]; /** * 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'. */ channelTag?: number; /** * Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) * language tag of the language in this result. This language code was * detected to have the most likelihood of being spoken in the audio. */ languageCode?: string; } /** * 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). The error model is designed to be: * - Simple to use and understand for most users - Flexible enough to meet * unexpected needs # Overview The `Status` message contains three pieces of * data: error code, error message, and error details. The error code should * be an enum value of google.rpc.Code, but it may accept additional error * codes if needed. The error message should be a developer-facing English * message that helps developers *understand* and *resolve* the error. If a * localized user-facing error message is needed, put the localized message in * the error details or localize it in the client. The optional error details * may contain arbitrary information about the error. There is a predefined * set of error detail types in the package `google.rpc` that can be used for * common error conditions. # Language mapping The `Status` message is the * logical representation of the error model, but it is not necessarily the * actual wire format. When the `Status` message is exposed in different * client libraries and different wire protocols, it can be mapped * differently. For example, it will likely be mapped to some exceptions in * Java, but more likely mapped to some error codes in C. # Other uses The * error model and the `Status` message can be used in a variety of * environments, either with or without APIs, to provide a consistent * developer experience across different environments. Example uses of this * error model include: - Partial errors. If a service needs to return * partial errors to the client, it may embed the `Status` in the normal * response to indicate the partial errors. - Workflow errors. A typical * workflow has multiple steps. Each step may have a `Status` message for * error reporting. - Batch operations. If a client uses batch request and * batch response, the `Status` message should be used directly inside * batch response, one for each error sub-response. - Asynchronous * operations. If an API call embeds asynchronous operation results in its * response, the status of those operations should be represented directly * using the `Status` message. - Logging. If some API errors are stored in * logs, the message `Status` could be used directly after any stripping * needed for security/privacy reasons. */ interface Schema$Status { /** * The status code, which should be an enum value of google.rpc.Code. */ code?: number; /** * A list of messages that carry the error details. There is a common set * of message types for APIs to use. */ details?: Array<{ [key: string]: any; }>; /** * 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. */ message?: string; } /** * Word-specific information for recognized words. */ interface Schema$WordInfo { /** * Output only. The confidence estimate between 0.0 and 1.0. A higher number * indicates an estimated greater likelihood that the recognized words are * correct. This field is set only for the top alternative of a * non-streaming result or, of a streaming result where `is_final=true`. * This field is not guaranteed to be accurate and users should not rely on * it to be always provided. The default of 0.0 is a sentinel value * indicating `confidence` was not set. */ confidence?: number; /** * Output only. Time offset relative to the beginning of the audio, and * corresponding to the end of the spoken word. This field is only set if * `enable_word_time_offsets=true` and only in the top hypothesis. This is * an experimental feature and the accuracy of the time offset can vary. */ endTime?: string; /** * Output only. A distinct integer value is assigned for every speaker * within the audio. This field specifies which one of those speakers was * detected to have spoken this word. Value ranges from '1' to * diarization_speaker_count. speaker_tag is set if * enable_speaker_diarization = 'true' and only in the top * alternative. */ speakerTag?: number; /** * Output only. Time offset relative to the beginning of the audio, and * corresponding to the start of the spoken word. This field is only set if * `enable_word_time_offsets=true` and only in the top hypothesis. This is * an experimental feature and the accuracy of the time offset can vary. */ startTime?: string; /** * Output only. The word corresponding to this set of information. */ word?: string; } class Resource$Operations { constructor(); /** * speech.operations.get * @desc 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. * @alias speech.operations.get * @memberOf! () * * @param {object} params Parameters for request * @param {string} params.name The name of the operation resource. * @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`. * @param {callback} callback The callback that handles the response. * @return {object} Request object */ get(params?: Params$Resource$Operations$Get, options?: MethodOptions): GaxiosPromise; get(params: Params$Resource$Operations$Get, options: MethodOptions | BodyResponseCallback, callback: BodyResponseCallback): void; get(params: Params$Resource$Operations$Get, callback: BodyResponseCallback): void; get(callback: BodyResponseCallback): void; /** * speech.operations.list * @desc Lists operations that match the specified filter in the request. If * the server doesn't support this method, it returns `UNIMPLEMENTED`. NOTE: * the `name` binding allows API services to override the binding to use * different resource name schemes, such as `users/x/operations`. To * override the binding, API services can add a binding such as * `"/v1/{name=users/x}/operations"` to their service configuration. For * backwards compatibility, the default name includes the operations * collection id, however overriding users must ensure the name binding is * the parent resource, without the operations collection id. * @alias speech.operations.list * @memberOf! () * * @param {object} params Parameters for request * @param {string=} params.filter The standard list filter. * @param {string=} params.name The name of the operation's parent resource. * @param {integer=} params.pageSize The standard list page size. * @param {string=} params.pageToken The standard list page token. * @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`. * @param {callback} callback The callback that handles the response. * @return {object} Request object */ list(params?: Params$Resource$Operations$List, options?: MethodOptions): GaxiosPromise; list(params: Params$Resource$Operations$List, options: MethodOptions | BodyResponseCallback, callback: BodyResponseCallback): void; list(params: Params$Resource$Operations$List, callback: BodyResponseCallback): void; list(callback: BodyResponseCallback): void; } interface Params$Resource$Operations$Get extends StandardParameters { /** * Auth client or API Key for the request */ auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient; /** * The name of the operation resource. */ name?: string; } interface Params$Resource$Operations$List extends StandardParameters { /** * Auth client or API Key for the request */ auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient; /** * The standard list filter. */ filter?: string; /** * The name of the operation's parent resource. */ name?: string; /** * The standard list page size. */ pageSize?: number; /** * The standard list page token. */ pageToken?: string; } class Resource$Projects { locations: Resource$Projects$Locations; operations: Resource$Projects$Operations; constructor(); } class Resource$Projects$Locations { operations: Resource$Projects$Locations$Operations; constructor(); } class Resource$Projects$Locations$Operations { constructor(); /** * speech.projects.locations.operations.get * @desc Gets the latest state of a long-running operation. Clients can use * this method to poll the operation result at intervals as recommended by * the API service. * @alias speech.projects.locations.operations.get * @memberOf! () * * @param {object} params Parameters for request * @param {string} params.name The name of the operation resource. * @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`. * @param {callback} callback The callback that handles the response. * @return {object} Request object */ get(params?: Params$Resource$Projects$Locations$Operations$Get, options?: MethodOptions): GaxiosPromise; get(params: Params$Resource$Projects$Locations$Operations$Get, options: MethodOptions | BodyResponseCallback, callback: BodyResponseCallback): void; get(params: Params$Resource$Projects$Locations$Operations$Get, callback: BodyResponseCallback): void; get(callback: BodyResponseCallback): void; /** * speech.projects.locations.operations.list * @desc 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/x/operations`. To * override the binding, API services can add a binding such as * `"/v1/{name=users/x}/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. * @alias speech.projects.locations.operations.list * @memberOf! () * * @param {object} params Parameters for request * @param {string=} params.filter The standard list filter. * @param {string} params.name The name of the operation's parent resource. * @param {integer=} params.pageSize The standard list page size. * @param {string=} params.pageToken The standard list page token. * @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`. * @param {callback} callback The callback that handles the response. * @return {object} Request object */ list(params?: Params$Resource$Projects$Locations$Operations$List, options?: MethodOptions): GaxiosPromise; list(params: Params$Resource$Projects$Locations$Operations$List, options: MethodOptions | BodyResponseCallback, callback: BodyResponseCallback): void; list(params: Params$Resource$Projects$Locations$Operations$List, callback: BodyResponseCallback): void; list(callback: BodyResponseCallback): void; } interface Params$Resource$Projects$Locations$Operations$Get extends StandardParameters { /** * Auth client or API Key for the request */ auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient; /** * The name of the operation resource. */ name?: string; } interface Params$Resource$Projects$Locations$Operations$List extends StandardParameters { /** * Auth client or API Key for the request */ auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient; /** * The standard list filter. */ filter?: string; /** * The name of the operation's parent resource. */ name?: string; /** * The standard list page size. */ pageSize?: number; /** * The standard list page token. */ pageToken?: string; } class Resource$Projects$Operations { manualRecognitionTasks: Resource$Projects$Operations$Manualrecognitiontasks; constructor(); } class Resource$Projects$Operations$Manualrecognitiontasks { constructor(); /** * speech.projects.operations.manualRecognitionTasks.get * @desc Gets the latest state of a long-running operation. Clients can use * this method to poll the operation result at intervals as recommended by * the API service. * @alias speech.projects.operations.manualRecognitionTasks.get * @memberOf! () * * @param {object} params Parameters for request * @param {string} params.name The name of the operation resource. * @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`. * @param {callback} callback The callback that handles the response. * @return {object} Request object */ get(params?: Params$Resource$Projects$Operations$Manualrecognitiontasks$Get, options?: MethodOptions): GaxiosPromise; get(params: Params$Resource$Projects$Operations$Manualrecognitiontasks$Get, options: MethodOptions | BodyResponseCallback, callback: BodyResponseCallback): void; get(params: Params$Resource$Projects$Operations$Manualrecognitiontasks$Get, callback: BodyResponseCallback): void; get(callback: BodyResponseCallback): void; } interface Params$Resource$Projects$Operations$Manualrecognitiontasks$Get extends StandardParameters { /** * Auth client or API Key for the request */ auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient; /** * The name of the operation resource. */ name?: string; } class Resource$Speech { constructor(); /** * speech.speech.longrunningrecognize * @desc 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. * @alias speech.speech.longrunningrecognize * @memberOf! () * * @param {object} params Parameters for request * @param {().LongRunningRecognizeRequest} params.resource Request body data * @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`. * @param {callback} callback The callback that handles the response. * @return {object} Request object */ longrunningrecognize(params?: Params$Resource$Speech$Longrunningrecognize, options?: MethodOptions): GaxiosPromise; longrunningrecognize(params: Params$Resource$Speech$Longrunningrecognize, options: MethodOptions | BodyResponseCallback, callback: BodyResponseCallback): void; longrunningrecognize(params: Params$Resource$Speech$Longrunningrecognize, callback: BodyResponseCallback): void; longrunningrecognize(callback: BodyResponseCallback): void; /** * speech.speech.recognize * @desc Performs synchronous speech recognition: receive results after all * audio has been sent and processed. * @alias speech.speech.recognize * @memberOf! () * * @param {object} params Parameters for request * @param {().RecognizeRequest} params.resource Request body data * @param {object} [options] Optionally override request options, such as `url`, `method`, and `encoding`. * @param {callback} callback The callback that handles the response. * @return {object} Request object */ recognize(params?: Params$Resource$Speech$Recognize, options?: MethodOptions): GaxiosPromise; recognize(params: Params$Resource$Speech$Recognize, options: MethodOptions | BodyResponseCallback, callback: BodyResponseCallback): void; recognize(params: Params$Resource$Speech$Recognize, callback: BodyResponseCallback): void; recognize(callback: BodyResponseCallback): void; } interface Params$Resource$Speech$Longrunningrecognize extends StandardParameters { /** * Auth client or API Key for the request */ auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient; /** * Request body metadata */ requestBody?: Schema$LongRunningRecognizeRequest; } interface Params$Resource$Speech$Recognize extends StandardParameters { /** * Auth client or API Key for the request */ auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient; /** * Request body metadata */ requestBody?: Schema$RecognizeRequest; } }