@cartesia/cartesia-js 2.1.4 → 2.1.6

package/dist/api/resources/tts/types/WebSocketFlushDoneResponse.d.ts

@@ -0,0 +1,8 @@
+/**
+ * This file was auto-generated by Fern from our API Definition.
+ */
+import * as Cartesia from "../../../index";
+export interface WebSocketFlushDoneResponse extends Cartesia.WebSocketBaseResponse {
+    flushId: Cartesia.FlushId;
+    flushDone: boolean;
+}

package/dist/api/resources/tts/types/WebSocketFlushDoneResponse.js

@@ -0,0 +1,5 @@
+"use strict";
+/**
+ * This file was auto-generated by Fern from our API Definition.
+ */
+Object.defineProperty(exports, "__esModule", { value: true });

package/dist/api/resources/tts/types/WebSocketRequest.d.ts

@@ -2,7 +2,7 @@
  * This file was auto-generated by Fern from our API Definition.
  */
 import * as Cartesia from "../../../index";
-export declare type WebSocketRequest = 
+export type WebSocketRequest = 
 /**
  * Use this to generate speech for a transcript.
  *  */

package/dist/api/resources/tts/types/WebSocketResponse.d.ts

@@ -2,11 +2,14 @@
  * This file was auto-generated by Fern from our API Definition.
  */
 import * as Cartesia from "../../../index";
-export declare type WebSocketResponse = Cartesia.WebSocketResponse.Chunk | Cartesia.WebSocketResponse.Done | Cartesia.WebSocketResponse.Timestamps | Cartesia.WebSocketResponse.Error_ | Cartesia.WebSocketResponse.PhonemeTimestamps;
+export type WebSocketResponse = Cartesia.WebSocketResponse.Chunk | Cartesia.WebSocketResponse.FlushDone | Cartesia.WebSocketResponse.Done | Cartesia.WebSocketResponse.Timestamps | Cartesia.WebSocketResponse.Error_ | Cartesia.WebSocketResponse.PhonemeTimestamps;
 export declare namespace WebSocketResponse {
     interface Chunk extends Cartesia.WebSocketChunkResponse {
         type: "chunk";
     }
+    interface FlushDone extends Cartesia.WebSocketFlushDoneResponse {
+        type: "flush_done";
+    }
     interface Done extends Cartesia.WebSocketDoneResponse {
         type: "done";
     }

package/dist/api/resources/tts/types/WebSocketTtsOutput.d.ts

@@ -7,4 +7,6 @@ export interface WebSocketTtsOutput {
     phonemeTimestamps?: Cartesia.PhonemeTimestamps;
     audio?: unknown;
     contextId?: Cartesia.ContextId;
+    flushId?: Cartesia.FlushId;
+    flushDone?: boolean;
 }

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

@@ -1,4 +1,5 @@
 export * from "./ContextId";
+export * from "./FlushId";
 export * from "./WebSocketBaseResponse";
 export * from "./WebSocketResponse";
 export * from "./WebSocketErrorResponse";
@@ -10,6 +11,7 @@ export * from "./WebSocketStreamOptions";
 export * from "./WordTimestamps";
 export * from "./PhonemeTimestamps";
 export * from "./WebSocketDoneResponse";
+export * from "./WebSocketFlushDoneResponse";
 export * from "./CancelContextRequest";
 export * from "./GenerationRequest";
 export * from "./WebSocketRawOutputFormat";

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

@@ -15,6 +15,7 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
 };
 Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./ContextId"), exports);
+__exportStar(require("./FlushId"), exports);
 __exportStar(require("./WebSocketBaseResponse"), exports);
 __exportStar(require("./WebSocketResponse"), exports);
 __exportStar(require("./WebSocketErrorResponse"), exports);
@@ -26,6 +27,7 @@ __exportStar(require("./WebSocketStreamOptions"), exports);
 __exportStar(require("./WordTimestamps"), exports);
 __exportStar(require("./PhonemeTimestamps"), exports);
 __exportStar(require("./WebSocketDoneResponse"), exports);
+__exportStar(require("./WebSocketFlushDoneResponse"), exports);
 __exportStar(require("./CancelContextRequest"), exports);
 __exportStar(require("./GenerationRequest"), exports);
 __exportStar(require("./WebSocketRawOutputFormat"), exports);

package/dist/api/resources/voiceChanger/client/Client.d.ts

@@ -1,11 +1,10 @@
 /**
  * This file was auto-generated by Fern from our API Definition.
  */
-/// <reference types="node" />
-import * as environments from "../../../../environments";
-import * as core from "../../../../core";
-import * as fs from "fs";
 import { Blob } from "buffer";
+import * as fs from "fs";
+import * as core from "../../../../core";
+import * as environments from "../../../../environments";
 import * as Cartesia from "../../../index";
 export declare namespace VoiceChanger {
     interface Options {

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

@@ -18,13 +18,23 @@ var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (
 }) : function(o, v) {
     o["default"] = v;
 });
-var __importStar = (this && this.__importStar) || function (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
-};
+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) {
@@ -39,9 +49,9 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
 };
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.VoiceChanger = void 0;
-const environments = __importStar(require("../../../../environments"));
-const core = __importStar(require("../../../../core"));
 const url_join_1 = __importDefault(require("url-join"));
+const core = __importStar(require("../../../../core"));
+const environments = __importStar(require("../../../../environments"));
 const errors = __importStar(require("../../../../errors/index"));
 const serializers = __importStar(require("../../../../serialization/index"));
 class VoiceChanger {
@@ -54,8 +64,8 @@ class VoiceChanger {
      * This endpoint is priced at 15 characters per second of input audio.
      */
     bytes(clip, request, requestOptions) {
-        var _a, _b, _c, _d, _e;
         return __awaiter(this, void 0, void 0, function* () {
+            var _a, _b, _c, _d, _e;
             const _request = yield core.newFormData();
             yield _request.appendFile("clip", clip);
             yield _request.append("voice[id]", request.voiceId);
@@ -96,7 +106,7 @@ class VoiceChanger {
                         body: _response.error.rawBody,
                     });
                 case "timeout":
-                    throw new errors.CartesiaTimeoutError();
+                    throw new errors.CartesiaTimeoutError("Timeout exceeded when calling POST /voice-changer/bytes.");
                 case "unknown":
                     throw new errors.CartesiaError({
                         message: _response.error.errorMessage,
@@ -105,8 +115,8 @@ class VoiceChanger {
         });
     }
     sse(clip, request, requestOptions) {
-        var _a, _b, _c, _d, _e;
         return __awaiter(this, void 0, void 0, function* () {
+            var _a, _b, _c, _d, _e;
             const _request = yield core.newFormData();
             yield _request.appendFile("clip", clip);
             yield _request.append("voice[id]", request.voiceId);
@@ -163,7 +173,7 @@ class VoiceChanger {
                         body: _response.error.rawBody,
                     });
                 case "timeout":
-                    throw new errors.CartesiaTimeoutError();
+                    throw new errors.CartesiaTimeoutError("Timeout exceeded when calling POST /voice-changer/sse.");
                 case "unknown":
                     throw new errors.CartesiaError({
                         message: _response.error.errorMessage,

package/dist/api/resources/voiceChanger/types/OutputFormatContainer.d.ts

@@ -1,7 +1,7 @@
 /**
  * This file was auto-generated by Fern from our API Definition.
  */
-export declare type OutputFormatContainer = "raw" | "wav" | "mp3";
+export type OutputFormatContainer = "raw" | "wav" | "mp3";
 export declare const OutputFormatContainer: {
     readonly Raw: "raw";
     readonly Wav: "wav";

package/dist/api/resources/voiceChanger/types/StreamingResponse.d.ts

@@ -2,7 +2,7 @@
  * This file was auto-generated by Fern from our API Definition.
  */
 import * as Cartesia from "../../../index";
-export declare type StreamingResponse = Cartesia.StreamingResponse.Chunk | Cartesia.StreamingResponse.Done | Cartesia.StreamingResponse.Error_;
+export type StreamingResponse = Cartesia.StreamingResponse.Chunk | Cartesia.StreamingResponse.Done | Cartesia.StreamingResponse.Error_;
 export declare namespace StreamingResponse {
     interface Chunk extends Cartesia.WebSocketChunkResponse {
         type: "chunk";

package/dist/api/resources/voices/client/Client.d.ts

@@ -1,7 +1,6 @@
 /**
  * This file was auto-generated by Fern from our API Definition.
  */
-/// <reference types="node" />
 import * as environments from "../../../../environments";
 import * as core from "../../../../core";
 import * as Cartesia from "../../../index";
@@ -10,6 +9,8 @@ import { Blob } from "buffer";
 export declare namespace Voices {
     interface Options {
         environment?: core.Supplier<environments.CartesiaEnvironment | string>;
+        /** Specify a custom URL to connect the client to. */
+        baseUrl?: core.Supplier<string>;
         apiKey?: core.Supplier<string | undefined>;
         /** Override the Cartesia-Version header */
         cartesiaVersion?: "2024-06-10";
@@ -24,6 +25,8 @@ export declare namespace Voices {
         abortSignal?: AbortSignal;
         /** Override the Cartesia-Version header */
         cartesiaVersion?: "2024-06-10";
+        /** Additional headers to include in the request. */
+        headers?: Record<string, string>;
     }
 }
 export declare class Voices {
@@ -37,24 +40,42 @@ export declare class Voices {
      */
     list(requestOptions?: Voices.RequestOptions): Promise<Cartesia.Voice[]>;
     /**
-     * @param {Cartesia.CreateVoiceRequest} request
+     * Clone a voice from an audio clip. This endpoint has two modes, stability and similarity.
+     *
+     * Similarity mode clones are more similar to the source clip, but may reproduce background noise. For these, use an audio clip about 5 seconds long.
+     *
+     * Stability mode clones are more stable, but may not sound as similar to the source clip. For these, use an audio clip 10-20 seconds long.
+     *
+     * @param {File | fs.ReadStream | Blob} clip
+     * @param {Cartesia.CloneVoiceRequest} request
      * @param {Voices.RequestOptions} requestOptions - Request-specific configuration.
      *
      * @example
-     *     await client.voices.create({
-     *         name: "string",
-     *         description: "string",
-     *         embedding: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
-     *         language: "en"
+     *     await client.voices.clone(fs.createReadStream("/path/to/your/file"), {
+     *         name: "A high-stability cloned voice",
+     *         description: "Copied from Cartesia docs",
+     *         mode: "stability",
+     *         language: "en",
+     *         enhance: true
+     *     })
+     *
+     * @example
+     *     await client.voices.clone(fs.createReadStream("/path/to/your/file"), {
+     *         name: "A high-similarity cloned voice",
+     *         description: "Copied from Cartesia docs",
+     *         mode: "similarity",
+     *         language: "en",
+     *         transcript: "A transcript of the words spoken in the audio clip.",
+     *         enhance: false
      *     })
      */
-    create(request: Cartesia.CreateVoiceRequest, requestOptions?: Voices.RequestOptions): Promise<Cartesia.Voice>;
+    clone(clip: File | fs.ReadStream | Blob, request: Cartesia.CloneVoiceRequest, requestOptions?: Voices.RequestOptions): Promise<Cartesia.VoiceMetadata>;
     /**
      * @param {Cartesia.VoiceId} id
      * @param {Voices.RequestOptions} requestOptions - Request-specific configuration.
      *
      * @example
-     *     await client.voices.delete("string")
+     *     await client.voices.delete("id")
      */
     delete(id: Cartesia.VoiceId, requestOptions?: Voices.RequestOptions): Promise<void>;
     /**
@@ -63,9 +84,9 @@ export declare class Voices {
      * @param {Voices.RequestOptions} requestOptions - Request-specific configuration.
      *
      * @example
-     *     await client.voices.update("string", {
-     *         name: "string",
-     *         description: "string"
+     *     await client.voices.update("id", {
+     *         name: "name",
+     *         description: "description"
      *     })
      */
     update(id: Cartesia.VoiceId, request: Cartesia.UpdateVoiceRequest, requestOptions?: Voices.RequestOptions): Promise<Cartesia.Voice>;
@@ -74,7 +95,7 @@ export declare class Voices {
      * @param {Voices.RequestOptions} requestOptions - Request-specific configuration.
      *
      * @example
-     *     await client.voices.get("string")
+     *     await client.voices.get("id")
      */
     get(id: Cartesia.VoiceId, requestOptions?: Voices.RequestOptions): Promise<Cartesia.Voice>;
     /**
@@ -83,10 +104,10 @@ export declare class Voices {
      *
      * @example
      *     await client.voices.localize({
-     *         embedding: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
+     *         embedding: [1.1, 1.1],
      *         language: "en",
      *         originalSpeakerGender: "male",
-     *         dialect: "au"
+     *         dialect: undefined
      *     })
      */
     localize(request: Cartesia.LocalizeVoiceRequest, requestOptions?: Voices.RequestOptions): Promise<Cartesia.EmbeddingResponse>;
@@ -97,43 +118,31 @@ export declare class Voices {
      * @example
      *     await client.voices.mix({
      *         voices: [{
-     *                 id: "string",
+     *                 id: "id",
+     *                 weight: 1.1
+     *             }, {
+     *                 id: "id",
      *                 weight: 1.1
      *             }]
      *     })
      */
     mix(request: Cartesia.MixVoicesRequest, requestOptions?: Voices.RequestOptions): Promise<Cartesia.EmbeddingResponse>;
     /**
-     * Clone a voice from an audio clip. This endpoint has two modes, stability and similarity.
-     *
-     * Similarity mode clones are more similar to the source clip, but may reproduce background noise. For these, use an audio clip about 5 seconds long.
+     * Create voice from raw features. If you'd like to clone a voice from an audio file, please use Clone Voice instead.
      *
-     * Stability mode clones are more stable, but may not sound as similar to the source clip. For these, use an audio clip 10-20 seconds long.
-     *
-     * @param {File | fs.ReadStream | Blob} clip
-     * @param {Cartesia.CloneVoiceRequest} request
+     * @param {Cartesia.CreateVoiceRequest} request
      * @param {Voices.RequestOptions} requestOptions - Request-specific configuration.
      *
      * @example
-     *     await client.voices.clone(fs.createReadStream("/path/to/your/file"), {
-     *         name: "A high-stability cloned voice",
-     *         description: "Copied from Cartesia docs",
-     *         mode: "stability",
-     *         language: "en",
-     *         enhance: true
-     *     })
-     *
-     * @example
-     *     await client.voices.clone(fs.createReadStream("/path/to/your/file"), {
-     *         name: "A high-similarity cloned voice",
-     *         description: "Copied from Cartesia docs",
-     *         mode: "similarity",
+     *     await client.voices.create({
+     *         name: "My Custom Voice",
+     *         description: "A custom voice created through the API",
+     *         embedding: [],
      *         language: "en",
-     *         transcript: "A transcript of the words spoken in the audio clip.",
-     *         enhance: false
+     *         baseVoiceId: "123e4567-e89b-12d3-a456-426614174000"
      *     })
      */
-    clone(clip: File | fs.ReadStream | Blob, request: Cartesia.CloneVoiceRequest, requestOptions?: Voices.RequestOptions): Promise<Cartesia.VoiceMetadata>;
+    create(request: Cartesia.CreateVoiceRequest, requestOptions?: Voices.RequestOptions): Promise<Cartesia.Voice>;
     protected _getCustomAuthorizationHeaders(): Promise<{
         "X-API-Key": string | undefined;
     }>;