v2beta1.d.ts 15.9 KB
/**
 * 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 { OAuth2Client, JWT, Compute, UserRefreshClient } from 'google-auth-library';
import { GoogleConfigurable, MethodOptions, GlobalOptions, BodyResponseCallback, APIRequestContext } from 'googleapis-common';
import { GaxiosPromise } from 'gaxios';
export declare namespace speech_v2beta1 {
    export interface Options extends GlobalOptions {
        version: 'v2beta1';
    }
    interface StandardParameters {
        /**
         * V1 error format.
         */
        '$.xgafv'?: string;
        /**
         * OAuth access token.
         */
        access_token?: string;
        /**
         * Data format for response.
         */
        alt?: string;
        /**
         * JSONP
         */
        callback?: string;
        /**
         * Selector specifying which fields to include in a partial response.
         */
        fields?: string;
        /**
         * API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
         */
        key?: string;
        /**
         * OAuth 2.0 token for the current user.
         */
        oauth_token?: string;
        /**
         * Returns response with indentations and line breaks.
         */
        prettyPrint?: boolean;
        /**
         * Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
         */
        quotaUser?: string;
        /**
         * Legacy upload protocol for media (e.g. "media", "multipart").
         */
        uploadType?: string;
        /**
         * Upload protocol for media (e.g. "raw", "multipart").
         */
        upload_protocol?: string;
    }
    /**
     * Cloud Speech-to-Text API
     *
     * Converts audio to text by applying powerful neural network models.
     *
     * @example
     * const {google} = require('googleapis');
     * const speech = google.speech('v2beta1');
     *
     * @namespace speech
     * @type {Function}
     * @version v2beta1
     * @variation v2beta1
     * @param {object=} options Options for Speech
     */
    export class Speech {
        context: APIRequestContext;
        projects: Resource$Projects;
        constructor(options: GlobalOptions, google?: GoogleConfigurable);
    }
    /**
     * The response message for Operations.ListOperations.
     */
    export interface Schema$ListOperationsResponse {
        /**
         * The standard List next-page token.
         */
        nextPageToken?: string | null;
        /**
         * A list of operations that matches the specified filter in the request.
         */
        operations?: Schema$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.
     */
    export interface Schema$LongRunningRecognizeMetadata {
        /**
         * Output only. Time of the most recent processing update.
         */
        lastUpdateTime?: string | null;
        /**
         * Output only. Approximate percentage of audio processed thus far. Guaranteed to be 100 when the audio is fully processed and the results are available.
         */
        progressPercent?: number | null;
        /**
         * Output only. Time when the request was received.
         */
        startTime?: string | null;
    }
    /**
     * The only message returned to the client by the `LongRunningRecognize` method. It contains the result as zero or more sequential SpeechRecognitionResult messages. It is included in the `result.response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.
     */
    export interface Schema$LongRunningRecognizeResponse {
        /**
         * Output only. Sequential list of transcription results corresponding to sequential portions of audio.
         */
        results?: Schema$SpeechRecognitionResult[];
    }
    /**
     * This resource represents a long-running operation that is the result of a network API call.
     */
    export interface Schema$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 | null;
        /**
         * The error result of the operation in case of failure or cancellation.
         */
        error?: Schema$Status;
        /**
         * Service-specific metadata associated with the operation.  It typically contains progress information and common metadata such as create time. Some services might not provide such metadata.  Any method that returns a long-running operation should document the metadata type, if any.
         */
        metadata?: {
            [key: string]: any;
        } | null;
        /**
         * The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
         */
        name?: string | null;
        /**
         * The normal response of the operation in case of success.  If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`.  If the original method is standard `Get`/`Create`/`Update`, the response should be the resource.  For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name.  For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
         */
        response?: {
            [key: string]: any;
        } | null;
    }
    /**
     * Alternative hypotheses (a.k.a. n-best list).
     */
    export interface Schema$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 | null;
        /**
         * Output only. Transcript text representing the words that the user spoke.
         */
        transcript?: string | null;
        /**
         * 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$WordInfo[];
    }
    /**
     * A speech recognition result corresponding to a portion of the audio.
     */
    export interface Schema$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$SpeechRecognitionAlternative[];
        /**
         * Output only. For multi-channel audio, this is the channel number corresponding to the recognized result for the audio from that channel. For `audio_channel_count` = N, its output values can range from `1` to `N`.
         */
        channelTag?: number | null;
        /**
         * Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.
         */
        languageCode?: string | null;
    }
    /**
     * The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details.  You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).
     */
    export interface Schema$Status {
        /**
         * The status code, which should be an enum value of google.rpc.Code.
         */
        code?: number | null;
        /**
         * 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;
        }> | null;
        /**
         * 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 | null;
    }
    /**
     * Word-specific information for recognized words.
     */
    export interface Schema$WordInfo {
        /**
         * Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative of a non-streaming result or, of a streaming result where `is_final=true`. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.
         */
        confidence?: number | null;
        /**
         * Output only. Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.
         */
        endOffset?: string | null;
        /**
         * Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from `1` to `diarization_config.max_speaker_count` . `speaker_tag` is set if `diarization_config.enable_speaker_diarization` = `true` and only in the top alternative.
         */
        speakerTag?: number | null;
        /**
         * Output only. Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.
         */
        startOffset?: string | null;
        /**
         * Output only. The word corresponding to this set of information.
         */
        word?: string | null;
    }
    export class Resource$Projects {
        context: APIRequestContext;
        locations: Resource$Projects$Locations;
        constructor(context: APIRequestContext);
    }
    export class Resource$Projects$Locations {
        context: APIRequestContext;
        operations: Resource$Projects$Locations$Operations;
        constructor(context: APIRequestContext);
    }
    export class Resource$Projects$Locations$Operations {
        context: APIRequestContext;
        constructor(context: APIRequestContext);
        /**
         * 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$Get, options?: MethodOptions): GaxiosPromise<Schema$Operation>;
        get(params: Params$Resource$Projects$Locations$Operations$Get, options: MethodOptions | BodyResponseCallback<Schema$Operation>, callback: BodyResponseCallback<Schema$Operation>): void;
        get(params: Params$Resource$Projects$Locations$Operations$Get, callback: BodyResponseCallback<Schema$Operation>): void;
        get(callback: BodyResponseCallback<Schema$Operation>): 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$List, options?: MethodOptions): GaxiosPromise<Schema$ListOperationsResponse>;
        list(params: Params$Resource$Projects$Locations$Operations$List, options: MethodOptions | BodyResponseCallback<Schema$ListOperationsResponse>, callback: BodyResponseCallback<Schema$ListOperationsResponse>): void;
        list(params: Params$Resource$Projects$Locations$Operations$List, callback: BodyResponseCallback<Schema$ListOperationsResponse>): void;
        list(callback: BodyResponseCallback<Schema$ListOperationsResponse>): void;
    }
    export interface Params$Resource$Projects$Locations$Operations$Get extends StandardParameters {
        /**
         * Auth client or API Key for the request
         */
        auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient;
        /**
         * The name of the operation resource.
         */
        name?: string;
    }
    export interface Params$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;
    }
    export {};
}