@cartesia/cartesia-js - npm Package Compare versions

Comparing version 1.1.0 to 1.2.0-alpha.0

dist/index.d.ts

 export { Cartesia, Cartesia as default } from './lib/index.js';
-export { Chunk, ClientOptions, CloneOptions, CloneResponse, ConnectionEventData, ContinueRequest, CreateVoice, EmitteryCallbacks, Emotion, EmotionControl, Encoding, Intensity, Language, LocalizeOptions, LocalizeResponse, MixVoicesOptions, MixVoicesResponse, Sentinel, SourceEventData, StreamOptions, StreamRequest, TypedArray, UpdateVoice, Voice, VoiceOptions, VoiceSpecifier, VoiceToMix, WebSocketBaseResponse, WebSocketChunkResponse, WebSocketErrorResponse, WebSocketOptions, WebSocketResponse, WebSocketTimestampsResponse, WordTimestamps } from './types/index.js';
+export { BytesRequest, Chunk, ClientOptions, CloneOptions, CloneResponse, ConnectionEventData, ContinueRequest, CreateVoice, EmitteryCallbacks, Emotion, EmotionControl, Encoding, Intensity, Language, LocalizeOptions, LocalizeResponse, MixVoicesOptions, MixVoicesResponse, Sentinel, SourceEventData, StreamOptions, StreamRequest, TypedArray, UpdateVoice, Voice, VoiceChangerBytesResponse, VoiceChangerOptions, VoiceOptions, VoiceSpecifier, VoiceToMix, WebSocketBaseResponse, WebSocketChunkResponse, WebSocketErrorResponse, WebSocketOptions, WebSocketResponse, WebSocketTimestampsResponse, WordTimestamps } from './types/index.js';
 export { default as WebPlayer } from './tts/player.js';
@@ -8,4 +8,5 @@ export { default as Source } from './tts/source.js';
 import './lib/client.js';
+import './voice-changer/index.js';
 import './voices/index.js';
 import 'emittery';
 import 'partysocket';

dist/index.js

@@ -1,20 +0,21 @@
-import "./chunk-FXPGR372.js";
 import {
+  Player
+} from "./chunk-CSOXALSC.js";
+import {
   Cartesia
-} from "./chunk-4GEDAGVY.js";
-import "./chunk-CWIJUBG6.js";
-import "./chunk-MUPVAEL7.js";
+} from "./chunk-YUGIYUMT.js";
+import "./chunk-EYRYHK3X.js";
 import {
   WebSocket
-} from "./chunk-L3OMQKWL.js";
-import "./chunk-6PWLZAMS.js";
-import "./chunk-2BFEKY3F.js";
+} from "./chunk-HQOC2S6C.js";
+import "./chunk-5SBAQNWQ.js";
 import {
-  Player
-} from "./chunk-MNOPO7G6.js";
-import "./chunk-VCZESWYA.js";
-import {
   Source
-} from "./chunk-VVDJR3OA.js";
-import "./chunk-WIFMLPT5.js";
+} from "./chunk-I5YVYTNK.js";
+import "./chunk-RJICGVPL.js";
+import "./chunk-FXPGR372.js";
+import "./chunk-WLEVU3HN.js";
+import "./chunk-FLWYXP5Z.js";
+import "./chunk-2BFEKY3F.js";
+import "./chunk-NJDRWDQ3.js";
 export {
@@ -21,0 +22,0 @@ Cartesia,

dist/lib/client.js

 import {
   Client
-} from "../chunk-6PWLZAMS.js";
+} from "../chunk-FLWYXP5Z.js";
 import "../chunk-2BFEKY3F.js";
-import "../chunk-WIFMLPT5.js";
+import "../chunk-NJDRWDQ3.js";
 export {
   Client
 };

dist/lib/constants.js

@@ -6,3 +6,3 @@ import {
 } from "../chunk-2BFEKY3F.js";
-import "../chunk-WIFMLPT5.js";
+import "../chunk-NJDRWDQ3.js";
 export {
@@ -9,0 +9,0 @@ BASE_URL,

dist/lib/index.d.ts

 import TTS from '../tts/index.js';
 import { ClientOptions } from '../types/index.js';
+import VoiceChanger from '../voice-changer/index.js';
 import Voices from '../voices/index.js';
@@ -13,2 +14,3 @@ import { Client } from './client.js';
     voices: Voices;
+    voiceChanger: VoiceChanger;
     constructor(options?: ClientOptions);
@@ -15,0 +17,0 @@ }

dist/lib/index.js

 import {
   Cartesia
-} from "../chunk-4GEDAGVY.js";
-import "../chunk-CWIJUBG6.js";
-import "../chunk-MUPVAEL7.js";
-import "../chunk-L3OMQKWL.js";
-import "../chunk-6PWLZAMS.js";
+} from "../chunk-YUGIYUMT.js";
+import "../chunk-EYRYHK3X.js";
+import "../chunk-HQOC2S6C.js";
+import "../chunk-5SBAQNWQ.js";
+import "../chunk-I5YVYTNK.js";
+import "../chunk-RJICGVPL.js";
+import "../chunk-WLEVU3HN.js";
+import "../chunk-FLWYXP5Z.js";
 import "../chunk-2BFEKY3F.js";
-import "../chunk-VCZESWYA.js";
-import "../chunk-VVDJR3OA.js";
-import "../chunk-WIFMLPT5.js";
+import "../chunk-NJDRWDQ3.js";
 export {
   Cartesia
 };

dist/react/index.js

 import {
+  Player
+} from "../chunk-CSOXALSC.js";
+import {
   Cartesia
-} from "../chunk-4GEDAGVY.js";
-import "../chunk-CWIJUBG6.js";
+} from "../chunk-YUGIYUMT.js";
+import "../chunk-EYRYHK3X.js";
+import "../chunk-HQOC2S6C.js";
+import "../chunk-5SBAQNWQ.js";
+import "../chunk-I5YVYTNK.js";
+import "../chunk-RJICGVPL.js";
 import {
   pingServer
-} from "../chunk-3FL2SNIR.js";
-import "../chunk-MUPVAEL7.js";
-import "../chunk-L3OMQKWL.js";
-import "../chunk-6PWLZAMS.js";
+} from "../chunk-LKKWJLUG.js";
+import "../chunk-WLEVU3HN.js";
+import "../chunk-FLWYXP5Z.js";
 import "../chunk-2BFEKY3F.js";
 import {
-  Player
-} from "../chunk-MNOPO7G6.js";
-import "../chunk-VCZESWYA.js";
-import "../chunk-VVDJR3OA.js";
-import {
   __async
-} from "../chunk-WIFMLPT5.js";
+} from "../chunk-NJDRWDQ3.js";
 
@@ -21,0 +22,0 @@ // src/react/index.ts

dist/react/utils.js

 import {
   pingServer
-} from "../chunk-3FL2SNIR.js";
-import "../chunk-WIFMLPT5.js";
+} from "../chunk-LKKWJLUG.js";
+import "../chunk-NJDRWDQ3.js";
 export {
   pingServer
 };

dist/tts/index.d.ts

 import { Client } from '../lib/client.js';
-import { WebSocketOptions } from '../types/index.js';
+import { WebSocketOptions, BytesRequest } from '../types/index.js';
 import WebSocket from './websocket.js';
@@ -15,4 +15,11 @@ import 'emittery';
     websocket(options: WebSocketOptions): WebSocket;
+    /**
+     * Generate audio bytes from text.
+     *
+     * @param options - The options for the request.
+     * @returns {Promise<ArrayBuffer>} A promise that resolves to an ArrayBuffer containing the audio bytes.
+     */
+    bytes(options: BytesRequest): Promise<ArrayBuffer>;
 }
 
 export { TTS as default };

dist/tts/index.js

 import {
   TTS
-} from "../chunk-MUPVAEL7.js";
-import "../chunk-L3OMQKWL.js";
-import "../chunk-6PWLZAMS.js";
+} from "../chunk-EYRYHK3X.js";
+import "../chunk-HQOC2S6C.js";
+import "../chunk-5SBAQNWQ.js";
+import "../chunk-I5YVYTNK.js";
+import "../chunk-FLWYXP5Z.js";
 import "../chunk-2BFEKY3F.js";
-import "../chunk-VCZESWYA.js";
-import "../chunk-VVDJR3OA.js";
-import "../chunk-WIFMLPT5.js";
+import "../chunk-NJDRWDQ3.js";
 export {
   TTS as default
 };

dist/tts/player.js

 import {
   Player
-} from "../chunk-MNOPO7G6.js";
-import "../chunk-VCZESWYA.js";
-import "../chunk-VVDJR3OA.js";
-import "../chunk-WIFMLPT5.js";
+} from "../chunk-CSOXALSC.js";
+import "../chunk-5SBAQNWQ.js";
+import "../chunk-I5YVYTNK.js";
+import "../chunk-NJDRWDQ3.js";
 export {
   Player as default
 };

dist/tts/source.js

 import {
   ENCODING_MAP,
   Source
-} from "../chunk-VVDJR3OA.js";
-import "../chunk-WIFMLPT5.js";
+} from "../chunk-I5YVYTNK.js";
+import "../chunk-NJDRWDQ3.js";
 export {
@@ -7,0 +7,0 @@ ENCODING_MAP,

dist/tts/utils.js

@@ -10,5 +10,5 @@ import {
   playAudioBuffer
-} from "../chunk-VCZESWYA.js";
-import "../chunk-VVDJR3OA.js";
-import "../chunk-WIFMLPT5.js";
+} from "../chunk-5SBAQNWQ.js";
+import "../chunk-I5YVYTNK.js";
+import "../chunk-NJDRWDQ3.js";
 export {
@@ -15,0 +15,0 @@ base64ToArray,

dist/tts/websocket.d.ts

@@ -36,14 +36,14 @@ import * as emittery from 'emittery';
         } & emittery.OmnipresentEventData)[Name]) => void | Promise<void>) => emittery.UnsubscribeFunction;
-        off: <Name_1 extends "timestamps" | keyof emittery.OmnipresentEventData | "message">(eventName: Name_1 | readonly Name_1[], listener: (eventData: ({
+        off: <Name extends "timestamps" | keyof emittery.OmnipresentEventData | "message">(eventName: Name | readonly Name[], listener: (eventData: ({
             message: string;
             timestamps: WordTimestamps;
-        } & emittery.OmnipresentEventData)[Name_1]) => void | Promise<void>) => void;
-        once: <Name_2 extends "timestamps" | keyof emittery.OmnipresentEventData | "message">(eventName: Name_2 | readonly Name_2[]) => emittery.EmitteryOncePromise<({
+        } & emittery.OmnipresentEventData)[Name]) => void | Promise<void>) => void;
+        once: <Name extends "timestamps" | keyof emittery.OmnipresentEventData | "message">(eventName: Name | readonly Name[]) => emittery.EmitteryOncePromise<({
             message: string;
             timestamps: WordTimestamps;
-        } & emittery.OmnipresentEventData)[Name_2]>;
-        events: <Name_3 extends "timestamps" | "message">(eventName: Name_3 | readonly Name_3[]) => AsyncIterableIterator<{
+        } & emittery.OmnipresentEventData)[Name]>;
+        events: <Name extends "timestamps" | "message">(eventName: Name | readonly Name[]) => AsyncIterableIterator<{
             message: string;
             timestamps: WordTimestamps;
-        }[Name_3]>;
+        }[Name]>;
         source: Source;
@@ -50,0 +50,0 @@ };

dist/tts/websocket.js

 import {
   WebSocket
-} from "../chunk-L3OMQKWL.js";
-import "../chunk-6PWLZAMS.js";
+} from "../chunk-HQOC2S6C.js";
+import "../chunk-5SBAQNWQ.js";
+import "../chunk-I5YVYTNK.js";
+import "../chunk-FLWYXP5Z.js";
 import "../chunk-2BFEKY3F.js";
-import "../chunk-VCZESWYA.js";
-import "../chunk-VVDJR3OA.js";
-import "../chunk-WIFMLPT5.js";
+import "../chunk-NJDRWDQ3.js";
 export {
   WebSocket as default
 };

dist/types/index.d.ts

@@ -44,2 +44,3 @@ import emittery__default from 'emittery';
 };
+type BytesRequest = Omit<StreamRequest, "continue" | "add_timestamps" | "context_id">;
 type ContinueRequest = StreamRequest & {
@@ -91,2 +92,22 @@ context_id: string;
 };
+type VoiceChangerOptions = {
+    clip: File;
+    voice: {
+        id: string;
+    };
+    output_format: {
+        container: "mp3";
+        bit_rate: number;
+        sample_rate: number;
+    } | {
+        container: "wav";
+        encoding: Encoding;
+        sample_rate: number;
+        bit_rate: number;
+    } | {
+        container: "raw";
+        encoding: Encoding;
+        sample_rate: number;
+    };
+};
 type LocalizeOptions = {
@@ -123,2 +144,5 @@ mode: "embedding";
 };
+type VoiceChangerBytesResponse = {
+    buffer: ArrayBuffer;
+};
 type LocalizeResponse = {
@@ -144,2 +168,2 @@ embedding: number[];
 
-export type { Chunk, ClientOptions, CloneOptions, CloneResponse, ConnectionEventData, ContinueRequest, CreateVoice, EmitteryCallbacks, Emotion, EmotionControl, Encoding, Intensity, Language, LocalizeOptions, LocalizeResponse, MixVoicesOptions, MixVoicesResponse, Sentinel, SourceEventData, StreamOptions, StreamRequest, TypedArray, UpdateVoice, Voice, VoiceOptions, VoiceSpecifier, VoiceToMix, WebSocketBaseResponse, WebSocketChunkResponse, WebSocketErrorResponse, WebSocketOptions, WebSocketResponse, WebSocketTimestampsResponse, WordTimestamps };
+export type { BytesRequest, Chunk, ClientOptions, CloneOptions, CloneResponse, ConnectionEventData, ContinueRequest, CreateVoice, EmitteryCallbacks, Emotion, EmotionControl, Encoding, Intensity, Language, LocalizeOptions, LocalizeResponse, MixVoicesOptions, MixVoicesResponse, Sentinel, SourceEventData, StreamOptions, StreamRequest, TypedArray, UpdateVoice, Voice, VoiceChangerBytesResponse, VoiceChangerOptions, VoiceOptions, VoiceSpecifier, VoiceToMix, WebSocketBaseResponse, WebSocketChunkResponse, WebSocketErrorResponse, WebSocketOptions, WebSocketResponse, WebSocketTimestampsResponse, WordTimestamps };

dist/voices/index.js

 import {
   Voices
-} from "../chunk-CWIJUBG6.js";
-import "../chunk-6PWLZAMS.js";
+} from "../chunk-RJICGVPL.js";
+import "../chunk-FLWYXP5Z.js";
 import "../chunk-2BFEKY3F.js";
-import "../chunk-WIFMLPT5.js";
+import "../chunk-NJDRWDQ3.js";
 export {
   Voices as default
 };

package.json

@@ -7,3 +7,3 @@ {
 	},
-	"version": "1.1.0",
+	"version": "1.2.0-alpha.0",
 	"description": "Client for the Cartesia API.",
@@ -31,3 +31,4 @@ "type": "module",
 		"human-id": "^4.1.1",
-		"partysocket": "^1.0.1"
+		"partysocket": "^1.0.1",
+		"react": "^18.3.1"
 	},
@@ -39,20 +40,12 @@ "publishConfig": {
 		"build": "tsup src/ --format cjs,esm --dts",
-		"dev": "bun run build -- --watch"
+		"dev": "bun run build -- --watch",
+		"release": "rm -rf dist && bun run build && bun publish"
 	},
-	"peerDependencies": {
-		"react": "^18.2.0",
-		"@types/react": "^18.2.58"
-	},
-	"peerDependenciesMeta": {
-		"react": {
-			"optional": true
-		},
-		"@types/react": {
-			"optional": true
-		}
-	},
 	"devDependencies": {
-		"@repo/config-typescript": "workspace:*",
-		"tsup": "^8.0.2"
+		"@biomejs/biome": "^1.9.4",
+		"@types/node": "^22.7.9",
+		"@types/react": "^18.3.12",
+		"tsup": "^8.0.2",
+		"typescript": "^5.6.3"
 	}
 }

src/lib/index.ts

 import TTS from "../tts";
 import type { ClientOptions } from "../types";
+import VoiceChanger from "../voice-changer";
 import Voices from "../voices";
@@ -9,2 +10,3 @@ import { Client } from "./client";
 	voices: Voices;
+	voiceChanger: VoiceChanger;
 
@@ -16,3 +18,4 @@ constructor(options: ClientOptions = {}) {
 		this.voices = new Voices(options);
+		this.voiceChanger = new VoiceChanger(options);
 	}
 }

src/tts/index.ts

 import { Client } from "../lib/client";
-import type { WebSocketOptions } from "../types";
+import type { BytesRequest, WebSocketOptions } from "../types";
 import WebSocket from "./websocket";
@@ -17,2 +17,17 @@
 	}
+
+	/**
+	 * Generate audio bytes from text.
+	 *
+	 * @param options - The options for the request.
+	 * @returns {Promise<ArrayBuffer>} A promise that resolves to an ArrayBuffer containing the audio bytes.
+	 */
+	async bytes(options: BytesRequest): Promise<ArrayBuffer> {
+		const response = await this._fetch("/tts/bytes", {
+			method: "POST",
+			body: JSON.stringify(options),
+		});
+
+		return response.arrayBuffer();
+	}
 }

src/types/index.ts

@@ -59,2 +59,7 @@ import type Emittery from "emittery";
 
+export type BytesRequest = Omit<
+	StreamRequest,
+	"continue" | "add_timestamps" | "context_id"
+>;
+
 export type ContinueRequest = StreamRequest & {
@@ -130,2 +135,24 @@ context_id: string;
 
+export type VoiceChangerOptions = {
+	clip: File;
+	voice: { id: string }; // match VoiceSpecifier shape, but only id is supported for now
+	output_format:
+		| {
+				container: "mp3";
+				bit_rate: number;
+				sample_rate: number;
+		  }
+		| {
+				container: "wav";
+				encoding: Encoding;
+				sample_rate: number;
+				bit_rate: number;
+		  }
+		| {
+				container: "raw";
+				encoding: Encoding;
+				sample_rate: number;
+		  };
+};
+
 export type LocalizeOptions = {
@@ -172,2 +199,6 @@ mode: "embedding";
 
+export type VoiceChangerBytesResponse = {
+	buffer: ArrayBuffer;
+};
+
 export type LocalizeResponse = {
@@ -174,0 +205,0 @@ embedding: number[];

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Manifest confusion

Supply chain risk

This package has inconsistent metadata. This could be malicious or caused by an error when publishing the package.

Found 6 instances in 1 package

Unpublished package

Supply chain risk

Package version was not found on the registry. It may exist on a different registry and need to be configured to pull from that registry.

Found 1 instance in 1 package

No v1

Quality

Package is not semver >=1. This means it is not stable and does not support ^ ranges.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

300759

increased by4.23%

Dependency count

6

decreased by-14.29%

Number of package files

87

increased by4.82%

Lines of code

8294

increased by4.68%

Worsened metrics

Dev dependency count

5

increased by150%

Number of low quality alerts

2

increased by100%

Number of low supply chain risk alerts

10

increased by11.11%

Number of medium supply chain risk alerts

11

increased by175%

Dependency changes

• + Addedreact@^18.3.1

• - Removed@types/prop-types@15.7.14(transitive)

• - Removed@types/react@18.3.17(transitive)

• - Removedcsstype@3.1.3(transitive)