@elevenlabs/elevenlabs-js 2.29.0 → 2.31.0

package/dist/api/resources/dubbing/resources/transcripts/client/Client.d.ts

@@ -0,0 +1,28 @@
+import type { BaseClientOptions, BaseRequestOptions } from "../../../../../../BaseClient";
+import { type NormalizedClientOptions } from "../../../../../../BaseClient";
+import * as core from "../../../../../../core";
+import * as ElevenLabs from "../../../../../index";
+export declare namespace TranscriptsClient {
+    type Options = BaseClientOptions;
+    interface RequestOptions extends BaseRequestOptions {
+    }
+}
+export declare class TranscriptsClient {
+    protected readonly _options: NormalizedClientOptions<TranscriptsClient.Options>;
+    constructor(options?: TranscriptsClient.Options);
+    /**
+     * Fetch the transcript for one of the languages in a dub.
+     *
+     * @param {string} dubbing_id - ID of the dubbing project.
+     * @param {string} language_code - ISO-693 language code to retrieve the transcript for. Use 'source' to fetch the transcript of the original media.
+     * @param {ElevenLabs.dubbing.TranscriptsGetRequestFormatType} format_type - Format to return transcript in. For subtitles use either 'srt' or 'webvtt', and for a full transcript use 'json'. The 'json' format is not yet supported for Dubbing Studio.
+     * @param {TranscriptsClient.RequestOptions} requestOptions - Request-specific configuration.
+     *
+     * @throws {@link ElevenLabs.UnprocessableEntityError}
+     *
+     * @example
+     *     await client.dubbing.transcripts.get("dubbing_id", "source", "srt")
+     */
+    get(dubbing_id: string, language_code: string, format_type: ElevenLabs.dubbing.TranscriptsGetRequestFormatType, requestOptions?: TranscriptsClient.RequestOptions): core.HttpResponsePromise<ElevenLabs.DubbingTranscriptsResponseModel>;
+    private __get;
+}

package/dist/api/resources/dubbing/resources/transcripts/client/Client.js

@@ -0,0 +1,122 @@
+"use strict";
+// This file was auto-generated by Fern from our API Definition.
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
+var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
+    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
+    return new (P || (P = Promise))(function (resolve, reject) {
+        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
+        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
+        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
+        step((generator = generator.apply(thisArg, _arguments || [])).next());
+    });
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.TranscriptsClient = void 0;
+const BaseClient_1 = require("../../../../../../BaseClient");
+const core = __importStar(require("../../../../../../core"));
+const headers_1 = require("../../../../../../core/headers");
+const environments = __importStar(require("../../../../../../environments"));
+const handleNonStatusCodeError_1 = require("../../../../../../errors/handleNonStatusCodeError");
+const errors = __importStar(require("../../../../../../errors/index"));
+const serializers = __importStar(require("../../../../../../serialization/index"));
+const ElevenLabs = __importStar(require("../../../../../index"));
+class TranscriptsClient {
+    constructor(options = {}) {
+        this._options = (0, BaseClient_1.normalizeClientOptions)(options);
+    }
+    /**
+     * Fetch the transcript for one of the languages in a dub.
+     *
+     * @param {string} dubbing_id - ID of the dubbing project.
+     * @param {string} language_code - ISO-693 language code to retrieve the transcript for. Use 'source' to fetch the transcript of the original media.
+     * @param {ElevenLabs.dubbing.TranscriptsGetRequestFormatType} format_type - Format to return transcript in. For subtitles use either 'srt' or 'webvtt', and for a full transcript use 'json'. The 'json' format is not yet supported for Dubbing Studio.
+     * @param {TranscriptsClient.RequestOptions} requestOptions - Request-specific configuration.
+     *
+     * @throws {@link ElevenLabs.UnprocessableEntityError}
+     *
+     * @example
+     *     await client.dubbing.transcripts.get("dubbing_id", "source", "srt")
+     */
+    get(dubbing_id, language_code, format_type, requestOptions) {
+        return core.HttpResponsePromise.fromPromise(this.__get(dubbing_id, language_code, format_type, requestOptions));
+    }
+    __get(dubbing_id, language_code, format_type, requestOptions) {
+        return __awaiter(this, void 0, void 0, function* () {
+            var _a, _b, _c, _d, _e, _f, _g, _h, _j, _k, _l, _m;
+            const _headers = (0, headers_1.mergeHeaders)((_a = this._options) === null || _a === void 0 ? void 0 : _a.headers, (0, headers_1.mergeOnlyDefinedHeaders)({ "xi-api-key": (_b = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.apiKey) !== null && _b !== void 0 ? _b : (_c = this._options) === null || _c === void 0 ? void 0 : _c.apiKey }), requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.headers);
+            const _response = yield ((_d = this._options.fetcher) !== null && _d !== void 0 ? _d : core.fetcher)({
+                url: core.url.join((_f = (_e = (yield core.Supplier.get(this._options.baseUrl))) !== null && _e !== void 0 ? _e : (yield core.Supplier.get(this._options.environment))) !== null && _f !== void 0 ? _f : environments.ElevenLabsEnvironment.Production, `v1/dubbing/${core.url.encodePathParam(dubbing_id)}/transcripts/${core.url.encodePathParam(language_code)}/format/${core.url.encodePathParam(serializers.dubbing.TranscriptsGetRequestFormatType.jsonOrThrow(format_type))}`),
+                method: "GET",
+                headers: _headers,
+                queryParameters: requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.queryParams,
+                timeoutMs: ((_j = (_g = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.timeoutInSeconds) !== null && _g !== void 0 ? _g : (_h = this._options) === null || _h === void 0 ? void 0 : _h.timeoutInSeconds) !== null && _j !== void 0 ? _j : 240) * 1000,
+                maxRetries: (_k = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.maxRetries) !== null && _k !== void 0 ? _k : (_l = this._options) === null || _l === void 0 ? void 0 : _l.maxRetries,
+                abortSignal: requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.abortSignal,
+                fetchFn: (_m = this._options) === null || _m === void 0 ? void 0 : _m.fetch,
+                logging: this._options.logging,
+            });
+            if (_response.ok) {
+                return {
+                    data: serializers.DubbingTranscriptsResponseModel.parseOrThrow(_response.body, {
+                        unrecognizedObjectKeys: "passthrough",
+                        allowUnrecognizedUnionMembers: true,
+                        allowUnrecognizedEnumValues: true,
+                        breadcrumbsPrefix: ["response"],
+                    }),
+                    rawResponse: _response.rawResponse,
+                };
+            }
+            if (_response.error.reason === "status-code") {
+                switch (_response.error.statusCode) {
+                    case 422:
+                        throw new ElevenLabs.UnprocessableEntityError(serializers.HttpValidationError.parseOrThrow(_response.error.body, {
+                            unrecognizedObjectKeys: "passthrough",
+                            allowUnrecognizedUnionMembers: true,
+                            allowUnrecognizedEnumValues: true,
+                            breadcrumbsPrefix: ["response"],
+                        }), _response.rawResponse);
+                    default:
+                        throw new errors.ElevenLabsError({
+                            statusCode: _response.error.statusCode,
+                            body: _response.error.body,
+                            rawResponse: _response.rawResponse,
+                        });
+                }
+            }
+            return (0, handleNonStatusCodeError_1.handleNonStatusCodeError)(_response.error, _response.rawResponse, "GET", "/v1/dubbing/{dubbing_id}/transcripts/{language_code}/format/{format_type}");
+        });
+    }
+}
+exports.TranscriptsClient = TranscriptsClient;

package/dist/api/resources/dubbing/resources/transcripts/client/index.d.ts

@@ -0,0 +1 @@
+export {};

package/dist/api/resources/dubbing/resources/transcripts/client/index.js

@@ -0,0 +1,2 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/api/resources/dubbing/resources/transcripts/index.d.ts

@@ -0,0 +1,2 @@
+export * from "./client";
+export * from "./types";

package/dist/api/resources/dubbing/resources/transcripts/index.js

@@ -0,0 +1,18 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __exportStar = (this && this.__exportStar) || function(m, exports) {
+    for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+__exportStar(require("./client"), exports);
+__exportStar(require("./types"), exports);

package/dist/api/resources/dubbing/resources/transcripts/types/TranscriptsGetRequestFormatType.d.ts

@@ -0,0 +1,7 @@
+/** Format to return transcript in. For subtitles use either 'srt' or 'webvtt', and for a full transcript use 'json'. The 'json' format is not yet supported for Dubbing Studio. */
+export declare const TranscriptsGetRequestFormatType: {
+    readonly Srt: "srt";
+    readonly Webvtt: "webvtt";
+    readonly Json: "json";
+};
+export type TranscriptsGetRequestFormatType = (typeof TranscriptsGetRequestFormatType)[keyof typeof TranscriptsGetRequestFormatType];

package/dist/api/resources/dubbing/resources/transcripts/types/TranscriptsGetRequestFormatType.js

@@ -0,0 +1,10 @@
+"use strict";
+// This file was auto-generated by Fern from our API Definition.
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.TranscriptsGetRequestFormatType = void 0;
+/** Format to return transcript in. For subtitles use either 'srt' or 'webvtt', and for a full transcript use 'json'. The 'json' format is not yet supported for Dubbing Studio. */
+exports.TranscriptsGetRequestFormatType = {
+    Srt: "srt",
+    Webvtt: "webvtt",
+    Json: "json",
+};

package/dist/api/resources/dubbing/resources/transcripts/types/index.d.ts

@@ -0,0 +1 @@
+export * from "./TranscriptsGetRequestFormatType";

package/{api/resources/textToSoundEffects → dist/api/resources/dubbing/resources/transcripts}/types/index.js

@@ -14,4 +14,4 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
     for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
 };
 Object.defineProperty(exports, "__esModule", { value: true });
-__exportStar(require("./TextToSoundEffectsConvertRequestOutputFormat"), exports);
+__exportStar(require("./TranscriptsGetRequestFormatType"), exports);

package/dist/api/resources/dubbing/types/DubbingCreateRequestMode.d.ts

@@ -1,4 +1,4 @@
-/** The mode in which to run this Dubbing job. Defaults to automatic, use manual if specifically providing a CSV transcript to use. */
+/** The mode in which to run this Dubbing job. Defaults to automatic, use manual if specifically providing a CSV transcript to use. Note that manual mode is experimental and production use is strongly discouraged. */
 export declare const DubbingCreateRequestMode: {
     readonly Automatic: "automatic";
     readonly Manual: "manual";

package/dist/api/resources/dubbing/types/DubbingCreateRequestMode.js

@@ -2,7 +2,7 @@
 // This file was auto-generated by Fern from our API Definition.
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.DubbingCreateRequestMode = void 0;
-/** The mode in which to run this Dubbing job. Defaults to automatic, use manual if specifically providing a CSV transcript to use. */
+/** The mode in which to run this Dubbing job. Defaults to automatic, use manual if specifically providing a CSV transcript to use. Note that manual mode is experimental and production use is strongly discouraged. */
 exports.DubbingCreateRequestMode = {
     Automatic: "automatic",
     Manual: "manual",

package/dist/api/resources/index.d.ts

@@ -37,7 +37,6 @@ export * from "./textToDialogue/client/requests";
 export * from "./textToDialogue/types";
 export * as textToSoundEffects from "./textToSoundEffects";
 export * from "./textToSoundEffects/client/requests";
-export * from "./textToSoundEffects/types";
 export * as textToSpeech from "./textToSpeech";
 export * from "./textToSpeech/client/requests";
 export * from "./textToSpeech/types";

package/dist/api/resources/index.js

@@ -76,7 +76,6 @@ __exportStar(require("./textToDialogue/client/requests"), exports);
 __exportStar(require("./textToDialogue/types"), exports);
 exports.textToSoundEffects = __importStar(require("./textToSoundEffects"));
 __exportStar(require("./textToSoundEffects/client/requests"), exports);
-__exportStar(require("./textToSoundEffects/types"), exports);
 exports.textToSpeech = __importStar(require("./textToSpeech"));
 __exportStar(require("./textToSpeech/client/requests"), exports);
 __exportStar(require("./textToSpeech/types"), exports);

package/dist/api/resources/music/client/Client.js

@@ -85,7 +85,7 @@ class MusicClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.MusicComposeRequestOutputFormat.jsonOrThrow(outputFormat, {
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
                     unrecognizedObjectKeys: "strip",
                 });
             }
@@ -141,7 +141,7 @@ class MusicClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.MusicComposeDetailedRequestOutputFormat.jsonOrThrow(outputFormat, {
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
                     unrecognizedObjectKeys: "strip",
                 });
             }
@@ -199,7 +199,7 @@ class MusicClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.MusicStreamRequestOutputFormat.jsonOrThrow(outputFormat, {
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
                     unrecognizedObjectKeys: "strip",
                 });
             }
@@ -256,7 +256,9 @@ class MusicClient {
             var _a, _b, _c, _d, _e, _f, _g, _h, _j, _k, _l, _m;
             const _queryParams = {};
             if (request.outputFormat != null) {
-                _queryParams.output_format = serializers.MusicSeparateStemsRequestOutputFormat.jsonOrThrow(request.outputFormat, { unrecognizedObjectKeys: "strip" });
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(request.outputFormat, {
+                    unrecognizedObjectKeys: "strip",
+                });
             }
             const _request = yield core.newFormData();
             yield _request.appendFile("file", request.file);

package/dist/api/resources/music/client/requests/BodyComposeMusicV1MusicPost.d.ts

@@ -5,7 +5,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface BodyComposeMusicV1MusicPost {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.MusicComposeRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** A simple text prompt to generate a song from. Cannot be used in conjunction with `composition_plan`. */
     prompt?: string;
     /** A detailed composition plan to guide music generation. Cannot be used in conjunction with `prompt`. */

package/dist/api/resources/music/client/requests/BodyComposeMusicWithADetailedResponseV1MusicDetailedPost.d.ts

@@ -5,7 +5,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface BodyComposeMusicWithADetailedResponseV1MusicDetailedPost {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.MusicComposeDetailedRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** A simple text prompt to generate a song from. Cannot be used in conjunction with `composition_plan`. */
     prompt?: string;
     /** A detailed composition plan to guide music generation. Cannot be used in conjunction with `prompt`. */

package/dist/api/resources/music/client/requests/BodyStemSeparationV1MusicStemSeparationPost.d.ts

@@ -2,7 +2,7 @@ import type * as core from "../../../../../core";
 import type * as ElevenLabs from "../../../../index";
 export interface BodyStemSeparationV1MusicStemSeparationPost {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.MusicSeparateStemsRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** The audio file to separate into stems. */
     file: core.file.Uploadable;
     /** The id of the stem variation to use. */

package/dist/api/resources/music/client/requests/BodyStreamComposedMusicV1MusicStreamPost.d.ts

@@ -5,7 +5,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface BodyStreamComposedMusicV1MusicStreamPost {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.MusicStreamRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** A simple text prompt to generate a song from. Cannot be used in conjunction with `composition_plan`. */
     prompt?: string;
     /** A detailed composition plan to guide music generation. Cannot be used in conjunction with `prompt`. */

package/dist/api/resources/music/types/index.d.ts

@@ -1,5 +1 @@
-export * from "./MusicComposeDetailedRequestOutputFormat";
-export * from "./MusicComposeRequestOutputFormat";
-export * from "./MusicSeparateStemsRequestOutputFormat";
 export * from "./MusicSeparateStemsRequestStemVariationId";
-export * from "./MusicStreamRequestOutputFormat";

package/dist/api/resources/music/types/index.js

@@ -14,8 +14,4 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
     for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
 };
 Object.defineProperty(exports, "__esModule", { value: true });
-__exportStar(require("./MusicComposeDetailedRequestOutputFormat"), exports);
-__exportStar(require("./MusicComposeRequestOutputFormat"), exports);
-__exportStar(require("./MusicSeparateStemsRequestOutputFormat"), exports);
 __exportStar(require("./MusicSeparateStemsRequestStemVariationId"), exports);
-__exportStar(require("./MusicStreamRequestOutputFormat"), exports);

package/dist/api/resources/speechToText/client/Client.js

@@ -144,6 +144,17 @@ class SpeechToTextClient {
                     return typeof mapped === "string" ? mapped : (0, json_1.toJson)(mapped);
                 })());
             }
+            if (request.entityDetection != null) {
+                if (Array.isArray(request.entityDetection))
+                    for (const _item of request.entityDetection) {
+                        _request.append("entity_detection", typeof _item === "string" ? _item : (0, json_1.toJson)(_item));
+                    }
+            }
+            if (request.keyterms != null) {
+                for (const _item of request.keyterms) {
+                    _request.append("keyterms", _item);
+                }
+            }
             const _maybeEncodedRequest = yield _request.getRequest();
             const _headers = (0, headers_1.mergeHeaders)((_a = this._options) === null || _a === void 0 ? void 0 : _a.headers, (0, headers_1.mergeOnlyDefinedHeaders)(Object.assign({ "xi-api-key": (_b = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.apiKey) !== null && _b !== void 0 ? _b : (_c = this._options) === null || _c === void 0 ? void 0 : _c.apiKey }, _maybeEncodedRequest.headers)), requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.headers);
             const _response = yield ((_d = this._options.fetcher) !== null && _d !== void 0 ? _d : core.fetcher)({

package/dist/api/resources/speechToText/client/requests/BodySpeechToTextV1SpeechToTextPost.d.ts

@@ -50,4 +50,8 @@ export interface BodySpeechToTextV1SpeechToTextPost {
     useMultiChannel?: boolean;
     /** Optional metadata to be included in the webhook response. This should be a JSON string representing an object with a maximum depth of 2 levels and maximum size of 16KB. Useful for tracking internal IDs, job references, or other contextual information. */
     webhookMetadata?: ElevenLabs.SpeechToTextConvertRequestWebhookMetadata;
+    /** Detect entities in the transcript. Can be 'all' to detect all entities, a single entity type or category string, or a list of entity types/categories. Categories include 'pii', 'phi', 'pci', 'other', 'offensive_language'. When enabled, detected entities will be returned in the 'entities' field with their text, type, and character positions. */
+    entityDetection?: ElevenLabs.SpeechToTextConvertRequestEntityDetection;
+    /** A list of keyterms to bias the transcription towards.           The keyterms are words or phrases you want the model to recognise more accurately.           The number of keyterms cannot exceed 100.           The length of each keyterm must be less than 50 characters.           Keyterms can contain at most 5 words (after normalisation).           For example ["hello", "world", "technical term"] */
+    keyterms?: string[];
 }

package/dist/api/resources/speechToText/types/SpeechToTextConvertRequestEntityDetection.d.ts

@@ -0,0 +1,4 @@
+/**
+ * Detect entities in the transcript. Can be 'all' to detect all entities, a single entity type or category string, or a list of entity types/categories. Categories include 'pii', 'phi', 'pci', 'other', 'offensive_language'. When enabled, detected entities will be returned in the 'entities' field with their text, type, and character positions.
+ */
+export type SpeechToTextConvertRequestEntityDetection = string | string[];

package/dist/api/resources/speechToText/types/SpeechToTextConvertRequestEntityDetection.js

@@ -0,0 +1,3 @@
+"use strict";
+// This file was auto-generated by Fern from our API Definition.
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/api/resources/speechToText/types/index.d.ts

@@ -1,3 +1,4 @@
+export * from "./SpeechToTextConvertRequestEntityDetection";
 export * from "./SpeechToTextConvertRequestFileFormat";
 export * from "./SpeechToTextConvertRequestTimestampsGranularity";
 export * from "./SpeechToTextConvertRequestWebhookMetadata";

package/dist/api/resources/speechToText/types/index.js

@@ -14,6 +14,7 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
     for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
 };
 Object.defineProperty(exports, "__esModule", { value: true });
+__exportStar(require("./SpeechToTextConvertRequestEntityDetection"), exports);
 __exportStar(require("./SpeechToTextConvertRequestFileFormat"), exports);
 __exportStar(require("./SpeechToTextConvertRequestTimestampsGranularity"), exports);
 __exportStar(require("./SpeechToTextConvertRequestWebhookMetadata"), exports);

package/dist/api/resources/textToDialogue/client/Client.js

@@ -80,7 +80,9 @@ class TextToDialogueClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.TextToDialogueConvertRequestOutputFormat.jsonOrThrow(outputFormat, { unrecognizedObjectKeys: "strip" });
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
+                    unrecognizedObjectKeys: "strip",
+                });
             }
             const _headers = (0, headers_1.mergeHeaders)((_a = this._options) === null || _a === void 0 ? void 0 : _a.headers, (0, headers_1.mergeOnlyDefinedHeaders)({ "xi-api-key": (_b = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.apiKey) !== null && _b !== void 0 ? _b : (_c = this._options) === null || _c === void 0 ? void 0 : _c.apiKey }), requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.headers);
             const _response = yield ((_d = this._options.fetcher) !== null && _d !== void 0 ? _d : core.fetcher)({
@@ -136,7 +138,7 @@ class TextToDialogueClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.TextToDialogueStreamRequestOutputFormat.jsonOrThrow(outputFormat, {
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
                     unrecognizedObjectKeys: "strip",
                 });
             }
@@ -193,7 +195,9 @@ class TextToDialogueClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.TextToDialogueStreamWithTimestampsRequestOutputFormat.jsonOrThrow(outputFormat, { unrecognizedObjectKeys: "strip" });
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
+                    unrecognizedObjectKeys: "strip",
+                });
             }
             const _headers = (0, headers_1.mergeHeaders)((_a = this._options) === null || _a === void 0 ? void 0 : _a.headers, (0, headers_1.mergeOnlyDefinedHeaders)({ "xi-api-key": (_b = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.apiKey) !== null && _b !== void 0 ? _b : (_c = this._options) === null || _c === void 0 ? void 0 : _c.apiKey }), requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.headers);
             const _response = yield ((_d = this._options.fetcher) !== null && _d !== void 0 ? _d : core.fetcher)({
@@ -283,7 +287,9 @@ class TextToDialogueClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.TextToDialogueConvertWithTimestampsRequestOutputFormat.jsonOrThrow(outputFormat, { unrecognizedObjectKeys: "strip" });
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
+                    unrecognizedObjectKeys: "strip",
+                });
             }
             const _headers = (0, headers_1.mergeHeaders)((_a = this._options) === null || _a === void 0 ? void 0 : _a.headers, (0, headers_1.mergeOnlyDefinedHeaders)({ "xi-api-key": (_b = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.apiKey) !== null && _b !== void 0 ? _b : (_c = this._options) === null || _c === void 0 ? void 0 : _c.apiKey }), requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.headers);
             const _response = yield ((_d = this._options.fetcher) !== null && _d !== void 0 ? _d : core.fetcher)({

package/dist/api/resources/textToDialogue/client/requests/BodyTextToDialogueFullWithTimestamps.d.ts

@@ -14,7 +14,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface BodyTextToDialogueFullWithTimestamps {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.TextToDialogueConvertWithTimestampsRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. */
     inputs: ElevenLabs.DialogueInput[];
     /** Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. */

package/dist/api/resources/textToDialogue/client/requests/BodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPost.d.ts

@@ -13,7 +13,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface BodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPost {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.TextToDialogueStreamRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. */
     inputs: ElevenLabs.DialogueInput[];
     /** Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. */

package/dist/api/resources/textToDialogue/client/requests/BodyTextToDialogueMultiVoiceV1TextToDialoguePost.d.ts

@@ -13,7 +13,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface BodyTextToDialogueMultiVoiceV1TextToDialoguePost {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.TextToDialogueConvertRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. */
     inputs: ElevenLabs.DialogueInput[];
     /** Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. */

package/dist/api/resources/textToDialogue/client/requests/BodyTextToDialogueStreamWithTimestamps.d.ts

@@ -14,7 +14,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface BodyTextToDialogueStreamWithTimestamps {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.TextToDialogueStreamWithTimestampsRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. */
     inputs: ElevenLabs.DialogueInput[];
     /** Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. */

package/dist/api/resources/textToDialogue/types/index.d.ts

@@ -2,7 +2,3 @@ export * from "./BodyTextToDialogueFullWithTimestampsApplyTextNormalization";
 export * from "./BodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPostApplyTextNormalization";
 export * from "./BodyTextToDialogueMultiVoiceV1TextToDialoguePostApplyTextNormalization";
 export * from "./BodyTextToDialogueStreamWithTimestampsApplyTextNormalization";
-export * from "./TextToDialogueConvertRequestOutputFormat";
-export * from "./TextToDialogueConvertWithTimestampsRequestOutputFormat";
-export * from "./TextToDialogueStreamRequestOutputFormat";
-export * from "./TextToDialogueStreamWithTimestampsRequestOutputFormat";

package/dist/api/resources/textToDialogue/types/index.js

@@ -18,7 +18,3 @@ __exportStar(require("./BodyTextToDialogueFullWithTimestampsApplyTextNormalizati
 __exportStar(require("./BodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPostApplyTextNormalization"), exports);
 __exportStar(require("./BodyTextToDialogueMultiVoiceV1TextToDialoguePostApplyTextNormalization"), exports);
 __exportStar(require("./BodyTextToDialogueStreamWithTimestampsApplyTextNormalization"), exports);
-__exportStar(require("./TextToDialogueConvertRequestOutputFormat"), exports);
-__exportStar(require("./TextToDialogueConvertWithTimestampsRequestOutputFormat"), exports);
-__exportStar(require("./TextToDialogueStreamRequestOutputFormat"), exports);
-__exportStar(require("./TextToDialogueStreamWithTimestampsRequestOutputFormat"), exports);

package/dist/api/resources/textToSoundEffects/client/Client.js

@@ -80,7 +80,9 @@ class TextToSoundEffectsClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.TextToSoundEffectsConvertRequestOutputFormat.jsonOrThrow(outputFormat, { unrecognizedObjectKeys: "strip" });
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
+                    unrecognizedObjectKeys: "strip",
+                });
             }
             const _headers = (0, headers_1.mergeHeaders)((_a = this._options) === null || _a === void 0 ? void 0 : _a.headers, (0, headers_1.mergeOnlyDefinedHeaders)({ "xi-api-key": (_b = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.apiKey) !== null && _b !== void 0 ? _b : (_c = this._options) === null || _c === void 0 ? void 0 : _c.apiKey }), requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.headers);
             const _response = yield ((_d = this._options.fetcher) !== null && _d !== void 0 ? _d : core.fetcher)({

package/dist/api/resources/textToSoundEffects/client/requests/CreateSoundEffectRequest.d.ts

@@ -7,7 +7,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface CreateSoundEffectRequest {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.TextToSoundEffectsConvertRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** The text that will get converted into a sound effect. */
     text: string;
     /** Whether to create a sound effect that loops smoothly. Only available for the 'eleven_text_to_sound_v2 model'. */

package/dist/api/resources/textToSoundEffects/index.d.ts

@@ -1,2 +1 @@
 export * from "./client";
-export * from "./types";

package/dist/api/resources/textToSoundEffects/index.js

@@ -15,4 +15,3 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
 };
 Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./client"), exports);
-__exportStar(require("./types"), exports);

package/dist/api/resources/textToVoice/client/Client.js

@@ -95,7 +95,9 @@ class TextToVoiceClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.TextToVoiceCreatePreviewsRequestOutputFormat.jsonOrThrow(outputFormat, { unrecognizedObjectKeys: "strip" });
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
+                    unrecognizedObjectKeys: "strip",
+                });
             }
             const _headers = (0, headers_1.mergeHeaders)((_a = this._options) === null || _a === void 0 ? void 0 : _a.headers, (0, headers_1.mergeOnlyDefinedHeaders)({ "xi-api-key": (_b = requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.apiKey) !== null && _b !== void 0 ? _b : (_c = this._options) === null || _c === void 0 ? void 0 : _c.apiKey }), requestOptions === null || requestOptions === void 0 ? void 0 : requestOptions.headers);
             const _response = yield ((_d = this._options.fetcher) !== null && _d !== void 0 ? _d : core.fetcher)({
@@ -235,7 +237,7 @@ class TextToVoiceClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.TextToVoiceDesignRequestOutputFormat.jsonOrThrow(outputFormat, {
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
                     unrecognizedObjectKeys: "strip",
                 });
             }
@@ -309,7 +311,7 @@ class TextToVoiceClient {
             const { outputFormat } = request, _body = __rest(request, ["outputFormat"]);
             const _queryParams = {};
             if (outputFormat != null) {
-                _queryParams.output_format = serializers.TextToVoiceRemixRequestOutputFormat.jsonOrThrow(outputFormat, {
+                _queryParams.output_format = serializers.AllowedOutputFormats.jsonOrThrow(outputFormat, {
                     unrecognizedObjectKeys: "strip",
                 });
             }

package/dist/api/resources/textToVoice/client/requests/VoiceDesignRequest.d.ts

@@ -8,7 +8,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface VoiceDesignRequest {
     /** The output format of the generated audio. */
-    outputFormat?: ElevenLabs.TextToVoiceCreatePreviewsRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** Description to use for the created voice. */
     voiceDescription: string;
     /** Text to generate, text length has to be between 100 and 1000. */

package/dist/api/resources/textToVoice/client/requests/VoiceDesignRequestModel.d.ts

@@ -8,7 +8,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface VoiceDesignRequestModel {
     /** Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. */
-    outputFormat?: ElevenLabs.TextToVoiceDesignRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** Description to use for the created voice. */
     voiceDescription: string;
     /** Model to use for the voice generation. Possible values: eleven_multilingual_ttv_v2, eleven_ttv_v3. */