@cartesia/cartesia-js 2.1.5 → 2.1.7

package/reference.md

@@ -98,7 +98,7 @@ await client.datasets.list();
 
 ```typescript
 await client.datasets.create({
-    name: "string",
+    name: "name",
 });
 ```
 
@@ -147,7 +147,7 @@ await client.datasets.create({
 <dd>
 
 ```typescript
-await client.datasets.listFiles("string");
+await client.datasets.listFiles("id");
 ```
 
 </dd>
@@ -182,70 +182,6 @@ await client.datasets.listFiles("string");
 </dl>
 </details>
 
-<details><summary><code>client.datasets.<a href="/src/api/resources/datasets/client/Client.ts">uploadFile</a>(file, id, { ...params }) -> void</code></summary>
-<dl>
-<dd>
-
-#### 🔌 Usage
-
-<dl>
-<dd>
-
-<dl>
-<dd>
-
-```typescript
-await client.datasets.uploadFile(fs.createReadStream("/path/to/your/file"), "string", {});
-```
-
-</dd>
-</dl>
-</dd>
-</dl>
-
-#### ⚙️ Parameters
-
-<dl>
-<dd>
-
-<dl>
-<dd>
-
-**file:** `File | fs.ReadStream | Blob`
-
-</dd>
-</dl>
-
-<dl>
-<dd>
-
-**id:** `string`
-
-</dd>
-</dl>
-
-<dl>
-<dd>
-
-**request:** `Cartesia.UploadDatasetFileRequest`
-
-</dd>
-</dl>
-
-<dl>
-<dd>
-
-**requestOptions:** `Datasets.RequestOptions`
-
-</dd>
-</dl>
-</dd>
-</dl>
-
-</dd>
-</dl>
-</details>
-
 ## Infill
 
 <details><summary><code>client.infill.<a href="/src/api/resources/infill/client/Client.ts">bytes</a>(leftAudio, rightAudio, { ...params }) -> stream.Readable</code></summary>
@@ -262,16 +198,24 @@ await client.datasets.uploadFile(fs.createReadStream("/path/to/your/file"), "str
 
 Generate audio that smoothly connects two existing audio segments. This is useful for inserting new speech between existing speech segments while maintaining natural transitions.
 
-The cost is 1 credit per character of the infill text plus a fixed cost of 300 credits.
+**The cost is 1 credit per character of the infill text plus a fixed cost of 300 credits.**
 
 Only the `sonic-preview` model is supported for infill at this time.
 
 At least one of `left_audio` or `right_audio` must be provided.
 
-</dd>
-</dl>
-</dd>
-</dl>
+As with all generative models, there's some inherent variability, but here's some tips we recommend to get the best results from infill:
+
+- Use longer infill transcripts
+    - This gives the model more flexibility to adapt to the rest of the audio
+- Target natural pauses in the audio when deciding where to clip
+    - This means you don't need word-level timestamps to be as precise
+- Clip right up to the start and end of the audio segment you want infilled, keeping as much silence in the left/right audio segments as possible
+    - This helps the model generate more natural transitions
+      </dd>
+      </dl>
+      </dd>
+      </dl>
 
 #### 🔌 Usage
 
@@ -359,7 +303,7 @@ await client.infill.bytes(fs.createReadStream("/path/to/your/file"), fs.createRe
 
 ```typescript
 await client.tts.bytes({
-    modelId: "sonic-english",
+    modelId: "sonic",
     transcript: "Hello, world!",
     voice: {
         mode: "id",
@@ -420,7 +364,7 @@ await client.tts.bytes({
 
 ```typescript
 const response = await client.tts.sse({
-    modelId: "sonic-english",
+    modelId: "sonic",
     transcript: "Hello, world!",
     voice: {
         mode: "id",
@@ -656,10 +600,29 @@ await client.voices.list();
 </dl>
 </details>
 
-<details><summary><code>client.voices.<a href="/src/api/resources/voices/client/Client.ts">create</a>({ ...params }) -> Cartesia.Voice</code></summary>
+<details><summary><code>client.voices.<a href="/src/api/resources/voices/client/Client.ts">clone</a>(clip, { ...params }) -> Cartesia.VoiceMetadata</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
 <dl>
 <dd>
 
+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.
+
+</dd>
+</dl>
+</dd>
+</dl>
+
 #### 🔌 Usage
 
 <dl>
@@ -669,18 +632,12 @@ await client.voices.list();
 <dd>
 
 ```typescript
-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,
-    ],
+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,
 });
 ```
 
@@ -697,7 +654,15 @@ await client.voices.create({
 <dl>
 <dd>
 
-**request:** `Cartesia.CreateVoiceRequest`
+**clip:** `File | fs.ReadStream | Blob`
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request:** `Cartesia.CloneVoiceRequest`
 
 </dd>
 </dl>
@@ -729,7 +694,7 @@ await client.voices.create({
 <dd>
 
 ```typescript
-await client.voices.delete("string");
+await client.voices.delete("id");
 ```
 
 </dd>
@@ -777,9 +742,9 @@ await client.voices.delete("string");
 <dd>
 
 ```typescript
-await client.voices.update("string", {
-    name: "string",
-    description: "string",
+await client.voices.update("id", {
+    name: "name",
+    description: "description",
 });
 ```
 
@@ -836,7 +801,7 @@ await client.voices.update("string", {
 <dd>
 
 ```typescript
-await client.voices.get("string");
+await client.voices.get("id");
 ```
 
 </dd>
@@ -871,10 +836,25 @@ await client.voices.get("string");
 </dl>
 </details>
 
-<details><summary><code>client.voices.<a href="/src/api/resources/voices/client/Client.ts">localize</a>({ ...params }) -> Cartesia.EmbeddingResponse</code></summary>
+<details><summary><code>client.voices.<a href="/src/api/resources/voices/client/Client.ts">localize</a>({ ...params }) -> Cartesia.VoiceMetadata</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
 <dl>
 <dd>
 
+Create a new voice from an existing voice localized to a new language and dialect.
+
+</dd>
+</dl>
+</dd>
+</dl>
+
 #### 🔌 Usage
 
 <dl>
@@ -885,17 +865,12 @@ await client.voices.get("string");
 
 ```typescript
 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,
-    ],
-    language: "en",
-    originalSpeakerGender: "male",
-    dialect: "au",
+    voiceId: "694f9389-aac1-45b6-b726-9d9369183238",
+    name: "Sarah Peninsular Spanish",
+    description: "Sarah Voice in Peninsular Spanish",
+    language: "es",
+    originalSpeakerGender: "female",
+    dialect: "pe",
 });
 ```
 
@@ -947,7 +922,11 @@ await client.voices.localize({
 await client.voices.mix({
     voices: [
         {
-            id: "string",
+            id: "id",
+            weight: 1.1,
+        },
+        {
+            id: "id",
             weight: 1.1,
         },
     ],
@@ -986,7 +965,7 @@ await client.voices.mix({
 </dl>
 </details>
 
-<details><summary><code>client.voices.<a href="/src/api/resources/voices/client/Client.ts">clone</a>(clip, { ...params }) -> Cartesia.VoiceMetadata</code></summary>
+<details><summary><code>client.voices.<a href="/src/api/resources/voices/client/Client.ts">create</a>({ ...params }) -> Cartesia.VoiceMetadata</code></summary>
 <dl>
 <dd>
 
@@ -998,11 +977,7 @@ await client.voices.mix({
 <dl>
 <dd>
 
-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.
+Create voice from raw features. If you'd like to clone a voice from an audio file, please use Clone Voice instead.
 
 </dd>
 </dl>
@@ -1018,12 +993,12 @@ Stability mode clones are more stable, but may not sound as similar to the sourc
 <dd>
 
 ```typescript
-await client.voices.clone(fs.createReadStream("/path/to/your/file"), {
-    name: "A high-stability cloned voice",
-    description: "Copied from Cartesia docs",
-    mode: "stability",
+await client.voices.create({
+    name: "My Custom Voice",
+    description: "A custom voice created through the API",
+    embedding: [],
     language: "en",
-    enhance: true,
+    baseVoiceId: "123e4567-e89b-12d3-a456-426614174000",
 });
 ```
 
@@ -1040,15 +1015,7 @@ await client.voices.clone(fs.createReadStream("/path/to/your/file"), {
 <dl>
 <dd>
 
-**clip:** `File | fs.ReadStream | Blob`
-
-</dd>
-</dl>
-
-<dl>
-<dd>
-
-**request:** `Cartesia.CloneVoiceRequest`
+**request:** `Cartesia.CreateVoiceRequest`
 
 </dd>
 </dl>

package/serialization/resources/voices/types/CreateVoiceRequest.d.ts

@@ -6,6 +6,7 @@ import * as Cartesia from "../../../../api/index";
 import * as core from "../../../../core";
 import { Embedding } from "../../embedding/types/Embedding";
 import { SupportedLanguage } from "../../tts/types/SupportedLanguage";
+import { BaseVoiceId } from "./BaseVoiceId";
 export declare const CreateVoiceRequest: core.serialization.ObjectSchema<serializers.CreateVoiceRequest.Raw, Cartesia.CreateVoiceRequest>;
 export declare namespace CreateVoiceRequest {
     interface Raw {
@@ -13,5 +14,6 @@ export declare namespace CreateVoiceRequest {
         description: string;
         embedding: Embedding.Raw;
         language?: SupportedLanguage.Raw | null;
+        base_voice_id?: BaseVoiceId.Raw | null;
     }
 }

package/serialization/resources/voices/types/CreateVoiceRequest.js

@@ -40,9 +40,11 @@ exports.CreateVoiceRequest = void 0;
 const core = __importStar(require("../../../../core"));
 const Embedding_1 = require("../../embedding/types/Embedding");
 const SupportedLanguage_1 = require("../../tts/types/SupportedLanguage");
+const BaseVoiceId_1 = require("./BaseVoiceId");
 exports.CreateVoiceRequest = core.serialization.object({
     name: core.serialization.string(),
     description: core.serialization.string(),
     embedding: Embedding_1.Embedding,
     language: SupportedLanguage_1.SupportedLanguage.optional(),
+    baseVoiceId: core.serialization.property("base_voice_id", BaseVoiceId_1.BaseVoiceId.optional()),
 });

package/serialization/resources/voices/types/LocalizeVoiceRequest.d.ts

@@ -4,14 +4,15 @@
 import * as serializers from "../../../index";
 import * as Cartesia from "../../../../api/index";
 import * as core from "../../../../core";
-import { Embedding } from "../../embedding/types/Embedding";
 import { LocalizeTargetLanguage } from "./LocalizeTargetLanguage";
 import { Gender } from "./Gender";
 import { LocalizeDialect } from "./LocalizeDialect";
 export declare const LocalizeVoiceRequest: core.serialization.ObjectSchema<serializers.LocalizeVoiceRequest.Raw, Cartesia.LocalizeVoiceRequest>;
 export declare namespace LocalizeVoiceRequest {
     interface Raw {
-        embedding: Embedding.Raw;
+        voice_id: string;
+        name: string;
+        description: string;
         language: LocalizeTargetLanguage.Raw;
         original_speaker_gender: Gender.Raw;
         dialect?: LocalizeDialect.Raw | null;

package/serialization/resources/voices/types/LocalizeVoiceRequest.js

@@ -38,12 +38,13 @@ var __importStar = (this && this.__importStar) || (function () {
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.LocalizeVoiceRequest = void 0;
 const core = __importStar(require("../../../../core"));
-const Embedding_1 = require("../../embedding/types/Embedding");
 const LocalizeTargetLanguage_1 = require("./LocalizeTargetLanguage");
 const Gender_1 = require("./Gender");
 const LocalizeDialect_1 = require("./LocalizeDialect");
 exports.LocalizeVoiceRequest = core.serialization.object({
-    embedding: Embedding_1.Embedding,
+    voiceId: core.serialization.property("voice_id", core.serialization.string()),
+    name: core.serialization.string(),
+    description: core.serialization.string(),
     language: LocalizeTargetLanguage_1.LocalizeTargetLanguage,
     originalSpeakerGender: core.serialization.property("original_speaker_gender", Gender_1.Gender),
     dialect: LocalizeDialect_1.LocalizeDialect.optional(),

package/version.d.ts

@@ -1 +1 @@
-export declare const SDK_VERSION = "2.1.5";
+export declare const SDK_VERSION = "2.1.7";

package/version.js

@@ -1,4 +1,4 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.SDK_VERSION = void 0;
-exports.SDK_VERSION = "2.1.5";
+exports.SDK_VERSION = "2.1.7";