@elevenlabs/elevenlabs-js 2.30.0 → 2.32.0

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

@@ -16,6 +16,7 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
 Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./SpeechToTextConvertRequestEntityDetection"), exports);
 __exportStar(require("./SpeechToTextConvertRequestFileFormat"), exports);
+__exportStar(require("./SpeechToTextConvertRequestModelId"), exports);
 __exportStar(require("./SpeechToTextConvertRequestTimestampsGranularity"), exports);
 __exportStar(require("./SpeechToTextConvertRequestWebhookMetadata"), exports);
 __exportStar(require("./SpeechToTextConvertResponse"), exports);

package/api/resources/studio/client/requests/BodyCreatePodcastV1StudioPodcastsPost.d.ts

@@ -28,10 +28,10 @@ export interface BodyCreatePodcastV1StudioPodcastsPost {
     source: ElevenLabs.BodyCreatePodcastV1StudioPodcastsPostSource;
     /**
      * Output quality of the generated audio. Must be one of:
-     * standard - standard output format, 128kbps with 44.1kHz sample rate.
-     * high - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
-     * ultra - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
-     * ultra lossless - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
+     * 'standard' - standard output format, 128kbps with 44.1kHz sample rate.
+     * 'high' - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
+     * 'ultra' - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
+     * 'ultra_lossless' - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
      */
     qualityPreset?: ElevenLabs.BodyCreatePodcastV1StudioPodcastsPostQualityPreset;
     /**

package/api/resources/studio/resources/projects/client/Client.js

@@ -176,7 +176,9 @@ class ProjectsClient {
                 _request.append("from_content_json", request.fromContentJson);
             }
             if (request.qualityPreset != null) {
-                _request.append("quality_preset", request.qualityPreset);
+                _request.append("quality_preset", serializers.studio.ProjectsCreateRequestQualityPreset.jsonOrThrow(request.qualityPreset, {
+                    unrecognizedObjectKeys: "strip",
+                }));
             }
             if (request.title != null) {
                 _request.append("title", request.title);

package/api/resources/studio/resources/projects/client/requests/BodyCreateStudioProjectV1StudioProjectsPost.d.ts

@@ -29,12 +29,12 @@ export interface BodyCreateStudioProjectV1StudioProjectsPost {
     fromContentJson?: string;
     /**
      * Output quality of the generated audio. Must be one of:
-     * standard - standard output format, 128kbps with 44.1kHz sample rate.
-     * high - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
-     * ultra - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
-     * ultra lossless - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
+     * 'standard' - standard output format, 128kbps with 44.1kHz sample rate.
+     * 'high' - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
+     * 'ultra' - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
+     * 'ultra_lossless' - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
      */
-    qualityPreset?: string;
+    qualityPreset?: ElevenLabs.studio.ProjectsCreateRequestQualityPreset;
     /** An optional name of the author of the Studio project, this will be added as metadata to the mp3 file on Studio project or chapter download. */
     title?: string;
     /** An optional name of the author of the Studio project, this will be added as metadata to the mp3 file on Studio project or chapter download. */

package/api/resources/studio/resources/projects/types/ProjectsCreateRequestQualityPreset.d.ts

@@ -0,0 +1,14 @@
+/**
+ * Output quality of the generated audio. Must be one of:
+ * 'standard' - standard output format, 128kbps with 44.1kHz sample rate.
+ * 'high' - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
+ * 'ultra' - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
+ * 'ultra_lossless' - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
+ */
+export declare const ProjectsCreateRequestQualityPreset: {
+    readonly Standard: "standard";
+    readonly High: "high";
+    readonly Ultra: "ultra";
+    readonly UltraLossless: "ultra_lossless";
+};
+export type ProjectsCreateRequestQualityPreset = (typeof ProjectsCreateRequestQualityPreset)[keyof typeof ProjectsCreateRequestQualityPreset];

package/api/resources/studio/resources/projects/types/ProjectsCreateRequestQualityPreset.js

@@ -0,0 +1,17 @@
+"use strict";
+// This file was auto-generated by Fern from our API Definition.
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.ProjectsCreateRequestQualityPreset = void 0;
+/**
+ * Output quality of the generated audio. Must be one of:
+ * 'standard' - standard output format, 128kbps with 44.1kHz sample rate.
+ * 'high' - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
+ * 'ultra' - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
+ * 'ultra_lossless' - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
+ */
+exports.ProjectsCreateRequestQualityPreset = {
+    Standard: "standard",
+    High: "high",
+    Ultra: "ultra",
+    UltraLossless: "ultra_lossless",
+};

package/api/resources/studio/resources/projects/types/index.d.ts

@@ -1,4 +1,5 @@
 export * from "./ProjectsCreateRequestApplyTextNormalization";
 export * from "./ProjectsCreateRequestFiction";
+export * from "./ProjectsCreateRequestQualityPreset";
 export * from "./ProjectsCreateRequestSourceType";
 export * from "./ProjectsCreateRequestTargetAudience";

package/api/resources/studio/resources/projects/types/index.js

@@ -16,5 +16,6 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
 Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./ProjectsCreateRequestApplyTextNormalization"), exports);
 __exportStar(require("./ProjectsCreateRequestFiction"), exports);
+__exportStar(require("./ProjectsCreateRequestQualityPreset"), exports);
 __exportStar(require("./ProjectsCreateRequestSourceType"), exports);
 __exportStar(require("./ProjectsCreateRequestTargetAudience"), exports);

package/api/resources/studio/types/BodyCreatePodcastV1StudioPodcastsPostQualityPreset.d.ts

@@ -1,9 +1,9 @@
 /**
  * Output quality of the generated audio. Must be one of:
- * standard - standard output format, 128kbps with 44.1kHz sample rate.
- * high - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
- * ultra - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
- * ultra lossless - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
+ * 'standard' - standard output format, 128kbps with 44.1kHz sample rate.
+ * 'high' - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
+ * 'ultra' - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
+ * 'ultra_lossless' - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
  */
 export declare const BodyCreatePodcastV1StudioPodcastsPostQualityPreset: {
     readonly Standard: "standard";

package/api/resources/studio/types/BodyCreatePodcastV1StudioPodcastsPostQualityPreset.js

@@ -4,10 +4,10 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.BodyCreatePodcastV1StudioPodcastsPostQualityPreset = void 0;
 /**
  * Output quality of the generated audio. Must be one of:
- * standard - standard output format, 128kbps with 44.1kHz sample rate.
- * high - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
- * ultra - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
- * ultra lossless - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
+ * 'standard' - standard output format, 128kbps with 44.1kHz sample rate.
+ * 'high' - high quality output format, 192kbps with 44.1kHz sample rate and major improvements on our side.
+ * 'ultra' - ultra quality output format, 192kbps with 44.1kHz sample rate and highest improvements on our side.
+ * 'ultra_lossless' - ultra quality output format, 705.6kbps with 44.1kHz sample rate and highest improvements on our side in a fully lossless format.
  */
 exports.BodyCreatePodcastV1StudioPodcastsPostQualityPreset = {
     Standard: "standard",

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

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

package/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/api/resources/textToSpeech/client/Client.d.ts

@@ -29,7 +29,7 @@ export declare class TextToSpeechClient {
      *     await client.textToSpeech.convertWithTimestamps("21m00Tcm4TlvDq8ikWAM", {
      *         enableLogging: true,
      *         optimizeStreamingLatency: 1,
-     *         outputFormat: "mp3_22050_32",
+     *         outputFormat: "alaw_8000",
      *         text: "This is a test for the API of ElevenLabs."
      *     })
      */

package/api/resources/textToSpeech/client/Client.js

@@ -142,7 +142,7 @@ class TextToSpeechClient {
      *     await client.textToSpeech.convertWithTimestamps("21m00Tcm4TlvDq8ikWAM", {
      *         enableLogging: true,
      *         optimizeStreamingLatency: 1,
-     *         outputFormat: "mp3_22050_32",
+     *         outputFormat: "alaw_8000",
      *         text: "This is a test for the API of ElevenLabs."
      *     })
      */

package/api/resources/textToSpeech/client/requests/BodyTextToSpeechFull.d.ts

@@ -21,7 +21,7 @@ export interface BodyTextToSpeechFull {
      * Defaults to None.
      */
     optimizeStreamingLatency?: number;
-    /** 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. */
+    /** 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 and WAV formats 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.TextToSpeechConvertRequestOutputFormat;
     /** The text that will get converted into speech. */
     text: string;

package/api/resources/textToSpeech/client/requests/BodyTextToSpeechFullWithTimestamps.d.ts

@@ -4,7 +4,7 @@ import type * as ElevenLabs from "../../../../index";
  *     {
  *         enableLogging: true,
  *         optimizeStreamingLatency: 1,
- *         outputFormat: "mp3_22050_32",
+ *         outputFormat: "alaw_8000",
  *         text: "This is a test for the API of ElevenLabs."
  *     }
  */
@@ -22,7 +22,7 @@ export interface BodyTextToSpeechFullWithTimestamps {
      * Defaults to None.
      */
     optimizeStreamingLatency?: number;
-    /** 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. */
+    /** 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 and WAV formats 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.TextToSpeechConvertWithTimestampsRequestOutputFormat;
     /** The text that will get converted into speech. */
     text: string;

package/api/resources/textToSpeech/types/TextToSpeechConvertRequestOutputFormat.d.ts

@@ -1,25 +1,32 @@
-/** 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. */
+/** 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 and WAV formats 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. */
 export declare const TextToSpeechConvertRequestOutputFormat: {
+    readonly Alaw8000: "alaw_8000";
     readonly Mp32205032: "mp3_22050_32";
     readonly Mp32400048: "mp3_24000_48";
+    readonly Mp344100128: "mp3_44100_128";
+    readonly Mp344100192: "mp3_44100_192";
     readonly Mp34410032: "mp3_44100_32";
     readonly Mp34410064: "mp3_44100_64";
     readonly Mp34410096: "mp3_44100_96";
-    readonly Mp344100128: "mp3_44100_128";
-    readonly Mp344100192: "mp3_44100_192";
-    readonly Pcm8000: "pcm_8000";
+    readonly Opus48000128: "opus_48000_128";
+    readonly Opus48000192: "opus_48000_192";
+    readonly Opus4800032: "opus_48000_32";
+    readonly Opus4800064: "opus_48000_64";
+    readonly Opus4800096: "opus_48000_96";
     readonly Pcm16000: "pcm_16000";
     readonly Pcm22050: "pcm_22050";
     readonly Pcm24000: "pcm_24000";
     readonly Pcm32000: "pcm_32000";
     readonly Pcm44100: "pcm_44100";
     readonly Pcm48000: "pcm_48000";
+    readonly Pcm8000: "pcm_8000";
     readonly Ulaw8000: "ulaw_8000";
-    readonly Alaw8000: "alaw_8000";
-    readonly Opus4800032: "opus_48000_32";
-    readonly Opus4800064: "opus_48000_64";
-    readonly Opus4800096: "opus_48000_96";
-    readonly Opus48000128: "opus_48000_128";
-    readonly Opus48000192: "opus_48000_192";
+    readonly Wav16000: "wav_16000";
+    readonly Wav22050: "wav_22050";
+    readonly Wav24000: "wav_24000";
+    readonly Wav32000: "wav_32000";
+    readonly Wav44100: "wav_44100";
+    readonly Wav48000: "wav_48000";
+    readonly Wav8000: "wav_8000";
 };
 export type TextToSpeechConvertRequestOutputFormat = (typeof TextToSpeechConvertRequestOutputFormat)[keyof typeof TextToSpeechConvertRequestOutputFormat];

package/api/resources/textToSpeech/types/TextToSpeechConvertRequestOutputFormat.js

@@ -2,27 +2,34 @@
 // This file was auto-generated by Fern from our API Definition.
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.TextToSpeechConvertRequestOutputFormat = void 0;
-/** 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. */
+/** 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 and WAV formats 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. */
 exports.TextToSpeechConvertRequestOutputFormat = {
+    Alaw8000: "alaw_8000",
     Mp32205032: "mp3_22050_32",
     Mp32400048: "mp3_24000_48",
+    Mp344100128: "mp3_44100_128",
+    Mp344100192: "mp3_44100_192",
     Mp34410032: "mp3_44100_32",
     Mp34410064: "mp3_44100_64",
     Mp34410096: "mp3_44100_96",
-    Mp344100128: "mp3_44100_128",
-    Mp344100192: "mp3_44100_192",
-    Pcm8000: "pcm_8000",
+    Opus48000128: "opus_48000_128",
+    Opus48000192: "opus_48000_192",
+    Opus4800032: "opus_48000_32",
+    Opus4800064: "opus_48000_64",
+    Opus4800096: "opus_48000_96",
     Pcm16000: "pcm_16000",
     Pcm22050: "pcm_22050",
     Pcm24000: "pcm_24000",
     Pcm32000: "pcm_32000",
     Pcm44100: "pcm_44100",
     Pcm48000: "pcm_48000",
+    Pcm8000: "pcm_8000",
     Ulaw8000: "ulaw_8000",
-    Alaw8000: "alaw_8000",
-    Opus4800032: "opus_48000_32",
-    Opus4800064: "opus_48000_64",
-    Opus4800096: "opus_48000_96",
-    Opus48000128: "opus_48000_128",
-    Opus48000192: "opus_48000_192",
+    Wav16000: "wav_16000",
+    Wav22050: "wav_22050",
+    Wav24000: "wav_24000",
+    Wav32000: "wav_32000",
+    Wav44100: "wav_44100",
+    Wav48000: "wav_48000",
+    Wav8000: "wav_8000",
 };

package/api/resources/textToSpeech/types/TextToSpeechConvertWithTimestampsRequestOutputFormat.d.ts

@@ -1,25 +1,32 @@
-/** 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. */
+/** 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 and WAV formats 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. */
 export declare const TextToSpeechConvertWithTimestampsRequestOutputFormat: {
+    readonly Alaw8000: "alaw_8000";
     readonly Mp32205032: "mp3_22050_32";
     readonly Mp32400048: "mp3_24000_48";
+    readonly Mp344100128: "mp3_44100_128";
+    readonly Mp344100192: "mp3_44100_192";
     readonly Mp34410032: "mp3_44100_32";
     readonly Mp34410064: "mp3_44100_64";
     readonly Mp34410096: "mp3_44100_96";
-    readonly Mp344100128: "mp3_44100_128";
-    readonly Mp344100192: "mp3_44100_192";
-    readonly Pcm8000: "pcm_8000";
+    readonly Opus48000128: "opus_48000_128";
+    readonly Opus48000192: "opus_48000_192";
+    readonly Opus4800032: "opus_48000_32";
+    readonly Opus4800064: "opus_48000_64";
+    readonly Opus4800096: "opus_48000_96";
     readonly Pcm16000: "pcm_16000";
     readonly Pcm22050: "pcm_22050";
     readonly Pcm24000: "pcm_24000";
     readonly Pcm32000: "pcm_32000";
     readonly Pcm44100: "pcm_44100";
     readonly Pcm48000: "pcm_48000";
+    readonly Pcm8000: "pcm_8000";
     readonly Ulaw8000: "ulaw_8000";
-    readonly Alaw8000: "alaw_8000";
-    readonly Opus4800032: "opus_48000_32";
-    readonly Opus4800064: "opus_48000_64";
-    readonly Opus4800096: "opus_48000_96";
-    readonly Opus48000128: "opus_48000_128";
-    readonly Opus48000192: "opus_48000_192";
+    readonly Wav16000: "wav_16000";
+    readonly Wav22050: "wav_22050";
+    readonly Wav24000: "wav_24000";
+    readonly Wav32000: "wav_32000";
+    readonly Wav44100: "wav_44100";
+    readonly Wav48000: "wav_48000";
+    readonly Wav8000: "wav_8000";
 };
 export type TextToSpeechConvertWithTimestampsRequestOutputFormat = (typeof TextToSpeechConvertWithTimestampsRequestOutputFormat)[keyof typeof TextToSpeechConvertWithTimestampsRequestOutputFormat];

package/api/resources/textToSpeech/types/TextToSpeechConvertWithTimestampsRequestOutputFormat.js

@@ -2,27 +2,34 @@
 // This file was auto-generated by Fern from our API Definition.
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.TextToSpeechConvertWithTimestampsRequestOutputFormat = void 0;
-/** 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. */
+/** 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 and WAV formats 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. */
 exports.TextToSpeechConvertWithTimestampsRequestOutputFormat = {
+    Alaw8000: "alaw_8000",
     Mp32205032: "mp3_22050_32",
     Mp32400048: "mp3_24000_48",
+    Mp344100128: "mp3_44100_128",
+    Mp344100192: "mp3_44100_192",
     Mp34410032: "mp3_44100_32",
     Mp34410064: "mp3_44100_64",
     Mp34410096: "mp3_44100_96",
-    Mp344100128: "mp3_44100_128",
-    Mp344100192: "mp3_44100_192",
-    Pcm8000: "pcm_8000",
+    Opus48000128: "opus_48000_128",
+    Opus48000192: "opus_48000_192",
+    Opus4800032: "opus_48000_32",
+    Opus4800064: "opus_48000_64",
+    Opus4800096: "opus_48000_96",
     Pcm16000: "pcm_16000",
     Pcm22050: "pcm_22050",
     Pcm24000: "pcm_24000",
     Pcm32000: "pcm_32000",
     Pcm44100: "pcm_44100",
     Pcm48000: "pcm_48000",
+    Pcm8000: "pcm_8000",
     Ulaw8000: "ulaw_8000",
-    Alaw8000: "alaw_8000",
-    Opus4800032: "opus_48000_32",
-    Opus4800064: "opus_48000_64",
-    Opus4800096: "opus_48000_96",
-    Opus48000128: "opus_48000_128",
-    Opus48000192: "opus_48000_192",
+    Wav16000: "wav_16000",
+    Wav22050: "wav_22050",
+    Wav24000: "wav_24000",
+    Wav32000: "wav_32000",
+    Wav44100: "wav_44100",
+    Wav48000: "wav_48000",
+    Wav8000: "wav_8000",
 };

package/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/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/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. */

package/api/resources/textToVoice/client/requests/VoiceRemixRequestModel.d.ts

@@ -8,7 +8,7 @@ import type * as ElevenLabs from "../../../../index";
  */
 export interface VoiceRemixRequestModel {
     /** 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.TextToVoiceRemixRequestOutputFormat;
+    outputFormat?: ElevenLabs.AllowedOutputFormats;
     /** Description of the changes to make to the voice. */
     voiceDescription: string;
     /** Text to generate, text length has to be between 100 and 1000. */

package/api/resources/textToVoice/types/index.d.ts

@@ -1,4 +1 @@
-export * from "./TextToVoiceCreatePreviewsRequestOutputFormat";
-export * from "./TextToVoiceDesignRequestOutputFormat";
-export * from "./TextToVoiceRemixRequestOutputFormat";
 export * from "./VoiceDesignRequestModelModelId";

package/api/resources/textToVoice/types/index.js

@@ -14,7 +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("./TextToVoiceCreatePreviewsRequestOutputFormat"), exports);
-__exportStar(require("./TextToVoiceDesignRequestOutputFormat"), exports);
-__exportStar(require("./TextToVoiceRemixRequestOutputFormat"), exports);
 __exportStar(require("./VoiceDesignRequestModelModelId"), exports);