@elevenlabs/elevenlabs-js 2.31.0 → 2.32.0

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

@@ -25,7 +25,7 @@ export declare class SpeechToTextClient {
      *     import { createReadStream } from "fs";
      *     await client.speechToText.convert({
      *         enableLogging: true,
-     *         modelId: "model_id"
+     *         modelId: "scribe_v1"
      *     })
      */
     convert(request: ElevenLabs.BodySpeechToTextV1SpeechToTextPost, requestOptions?: SpeechToTextClient.RequestOptions): core.HttpResponsePromise<ElevenLabs.SpeechToTextConvertResponse>;

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

@@ -74,7 +74,7 @@ class SpeechToTextClient {
      *     import { createReadStream } from "fs";
      *     await client.speechToText.convert({
      *         enableLogging: true,
-     *         modelId: "model_id"
+     *         modelId: "scribe_v1"
      *     })
      */
     convert(request, requestOptions) {
@@ -88,7 +88,9 @@ class SpeechToTextClient {
                 _queryParams.enable_logging = request.enableLogging.toString();
             }
             const _request = yield core.newFormData();
-            _request.append("model_id", request.modelId);
+            _request.append("model_id", serializers.SpeechToTextConvertRequestModelId.jsonOrThrow(request.modelId, {
+                unrecognizedObjectKeys: "strip",
+            }));
             if (request.file != null) {
                 yield _request.appendFile("file", request.file);
             }

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

@@ -4,20 +4,20 @@ import type * as ElevenLabs from "../../../../index";
  * @example
  *     {
  *         enableLogging: true,
- *         modelId: "model_id"
+ *         modelId: "scribe_v1"
  *     }
  *
  * @example
  *     {
  *         enableLogging: true,
- *         modelId: "model_id"
+ *         modelId: "scribe_v1"
  *     }
  */
 export interface BodySpeechToTextV1SpeechToTextPost {
     /** When enable_logging is set to false zero retention mode will be used for the request. This will mean log and transcript storage features are unavailable for this request. Zero retention mode may only be used by enterprise customers. */
     enableLogging?: boolean;
-    /** The ID of the model to use for transcription, currently only 'scribe_v1' and 'scribe_v1_experimental' are available. */
-    modelId: string;
+    /** The ID of the model to use for transcription. */
+    modelId: ElevenLabs.SpeechToTextConvertRequestModelId;
     /** The file to transcribe. All major audio and video formats are supported. Exactly one of the file or cloud_storage_url parameters must be provided. The file size must be less than 3.0GB. */
     file?: core.file.Uploadable | undefined;
     /** An ISO-639-1 or ISO-639-3 language_code corresponding to the language of the audio file. Can sometimes improve transcription performance if known beforehand. Defaults to null, in this case the language is predicted automatically. */

package/api/resources/speechToText/types/SpeechToTextConvertRequestModelId.d.ts

@@ -0,0 +1,6 @@
+/** The ID of the model to use for transcription. */
+export declare const SpeechToTextConvertRequestModelId: {
+    readonly ScribeV1: "scribe_v1";
+    readonly ScribeV2: "scribe_v2";
+};
+export type SpeechToTextConvertRequestModelId = (typeof SpeechToTextConvertRequestModelId)[keyof typeof SpeechToTextConvertRequestModelId];

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

@@ -0,0 +1,9 @@
+"use strict";
+// This file was auto-generated by Fern from our API Definition.
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.SpeechToTextConvertRequestModelId = void 0;
+/** The ID of the model to use for transcription. */
+exports.SpeechToTextConvertRequestModelId = {
+    ScribeV1: "scribe_v1",
+    ScribeV2: "scribe_v2",
+};

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

@@ -1,5 +1,6 @@
 export * from "./SpeechToTextConvertRequestEntityDetection";
 export * from "./SpeechToTextConvertRequestFileFormat";
+export * from "./SpeechToTextConvertRequestModelId";
 export * from "./SpeechToTextConvertRequestTimestampsGranularity";
 export * from "./SpeechToTextConvertRequestWebhookMetadata";
 export * from "./SpeechToTextConvertResponse";

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/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/voices/client/Client.js

@@ -47,6 +47,7 @@ exports.VoicesClient = void 0;
 const BaseClient_1 = require("../../../../BaseClient");
 const core = __importStar(require("../../../../core"));
 const headers_1 = require("../../../../core/headers");
+const json_1 = require("../../../../core/json");
 const environments = __importStar(require("../../../../environments"));
 const handleNonStatusCodeError_1 = require("../../../../errors/handleNonStatusCodeError");
 const errors = __importStar(require("../../../../errors/index"));
@@ -420,7 +421,12 @@ class VoicesClient {
                 _request.append("description", request.description);
             }
             if (request.labels != null) {
-                _request.append("labels", request.labels);
+                _request.append("labels", (() => {
+                    const mapped = serializers.VoicesUpdateRequestLabels.jsonOrThrow(request.labels, {
+                        unrecognizedObjectKeys: "strip",
+                    });
+                    return typeof mapped === "string" ? mapped : (0, json_1.toJson)(mapped);
+                })());
             }
             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);

package/api/resources/voices/client/requests/BodyEditVoiceV1VoicesVoiceIdEditPost.d.ts

@@ -1,4 +1,5 @@
 import type * as core from "../../../../../core";
+import type * as ElevenLabs from "../../../../index";
 /**
  * @example
  *     {
@@ -14,6 +15,6 @@ export interface BodyEditVoiceV1VoicesVoiceIdEditPost {
     removeBackgroundNoise?: boolean;
     /** A description of the voice. */
     description?: string;
-    /** Serialized labels dictionary for the voice. */
-    labels?: string;
+    /** Labels for the voice. Keys can be language, accent, gender, or age. */
+    labels?: ElevenLabs.VoicesUpdateRequestLabels;
 }

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

@@ -1,5 +1,6 @@
 export * as ivc from "./ivc";
 export * from "./ivc/client/requests";
+export * from "./ivc/types";
 export * as pvc from "./pvc";
 export * from "./pvc/client/requests";
 export * as samples from "./samples";

package/api/resources/voices/resources/index.js

@@ -39,6 +39,7 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.settings = exports.samples = exports.pvc = exports.ivc = void 0;
 exports.ivc = __importStar(require("./ivc"));
 __exportStar(require("./ivc/client/requests"), exports);
+__exportStar(require("./ivc/types"), exports);
 exports.pvc = __importStar(require("./pvc"));
 __exportStar(require("./pvc/client/requests"), exports);
 exports.samples = __importStar(require("./samples"));

package/api/resources/voices/resources/ivc/client/Client.js

@@ -47,6 +47,7 @@ exports.IvcClient = void 0;
 const BaseClient_1 = require("../../../../../../BaseClient");
 const core = __importStar(require("../../../../../../core"));
 const headers_1 = require("../../../../../../core/headers");
+const json_1 = require("../../../../../../core/json");
 const environments = __importStar(require("../../../../../../environments"));
 const handleNonStatusCodeError_1 = require("../../../../../../errors/handleNonStatusCodeError");
 const errors = __importStar(require("../../../../../../errors/index"));
@@ -89,7 +90,12 @@ class IvcClient {
                 _request.append("description", request.description);
             }
             if (request.labels != null) {
-                _request.append("labels", request.labels);
+                _request.append("labels", (() => {
+                    const mapped = serializers.voices.IvcCreateRequestLabels.jsonOrThrow(request.labels, {
+                        unrecognizedObjectKeys: "strip",
+                    });
+                    return typeof mapped === "string" ? mapped : (0, json_1.toJson)(mapped);
+                })());
             }
             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);

package/api/resources/voices/resources/ivc/client/requests/BodyAddVoiceV1VoicesAddPost.d.ts

@@ -1,4 +1,5 @@
 import type * as core from "../../../../../../../core";
+import type * as ElevenLabs from "../../../../../../index";
 /**
  * @example
  *     {
@@ -15,6 +16,6 @@ export interface BodyAddVoiceV1VoicesAddPost {
     removeBackgroundNoise?: boolean;
     /** A description of the voice. */
     description?: string;
-    /** Serialized labels dictionary for the voice. */
-    labels?: string;
+    /** Labels for the voice. Keys can be language, accent, gender, or age. */
+    labels?: ElevenLabs.voices.IvcCreateRequestLabels;
 }

package/api/resources/voices/resources/ivc/index.d.ts

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

package/api/resources/voices/resources/ivc/index.js

@@ -15,3 +15,4 @@ 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/voices/resources/ivc/types/IvcCreateRequestLabels.d.ts

@@ -0,0 +1,4 @@
+/**
+ * Labels for the voice. Keys can be language, accent, gender, or age.
+ */
+export type IvcCreateRequestLabels = Record<string, string> | string;

package/api/resources/voices/resources/ivc/types/IvcCreateRequestLabels.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/api/resources/voices/resources/ivc/types/index.d.ts

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

package/api/resources/voices/resources/ivc/types/index.js

@@ -0,0 +1,17 @@
+"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("./IvcCreateRequestLabels"), exports);

package/api/resources/voices/resources/pvc/client/requests/BodyEditPvcVoiceV1VoicesPvcVoiceIdPost.d.ts

@@ -9,6 +9,6 @@ export interface BodyEditPvcVoiceV1VoicesPvcVoiceIdPost {
     language?: string;
     /** Description to use for the created voice. */
     description?: string;
-    /** Serialized labels dictionary for the voice. */
+    /** Labels for the voice. Keys can be language, accent, gender, or age. */
     labels?: Record<string, string | undefined>;
 }