Release 2.1.3

reference.md

@@ -273,7 +273,6 @@ await client.tts.bytes({
         container: "mp3",
         sampleRate: 44100,
         bitRate: 128000,
-        loudness: -17,
     },
 });
 ```
@@ -291,7 +290,7 @@ await client.tts.bytes({
 <dl>
 <dd>
 
-**request:** `Cartesia.TtsBytesRequest`
+**request:** `Cartesia.TtsRequest`
 
 </dd>
 </dl>
@@ -355,7 +354,7 @@ for await (const item of response) {
 <dl>
 <dd>
 
-**request:** `Cartesia.TtssseRequest`
+**request:** `Cartesia.TtsRequest`
 
 </dd>
 </dl>

src/api/resources/tts/types/Mp3OutputFormat.ts

@@ -6,9 +6,4 @@ export interface Mp3OutputFormat {
     sampleRate: number;
     /** The bit rate of the audio in bits per second. Supported bit rates are 32000, 64000, 96000, 128000, 192000. */
     bitRate: number;
-    /**
-     * The loudness of the audio in LUFS.
-     * Supports values between -14 (loudest) and -24 (quietest).
-     */
-    loudness?: number;
 }

src/api/resources/tts/types/TtssseRequest.ts → src/api/resources/tts/types/TtsRequest.ts

@@ -4,13 +4,13 @@
 
 import * as Cartesia from "../../../index";
 
-export interface TtssseRequest {
+export interface TtsRequest {
     /** The ID of the model to use for the generation. See [Models](/build-with-sonic/models) for available models. */
     modelId: string;
     transcript: string;
     voice: Cartesia.TtsRequestVoiceSpecifier;
     language?: Cartesia.SupportedLanguage;
-    outputFormat: Cartesia.SseOutputFormat;
+    outputFormat: Cartesia.OutputFormat;
     /**
      * The maximum duration of the audio in seconds. You do not usually need to specify this.
      * If the duration is not appropriate for the length of the transcript, the output audio may be truncated.

src/api/resources/tts/types/index.ts

@@ -13,13 +13,12 @@ export * from "./GenerationRequest";
 export * from "./WebSocketRawOutputFormat";
 export * from "./WebSocketRequest";
 export * from "./WebSocketTtsRequest";
+export * from "./TtsRequest";
 export * from "./SupportedLanguage";
 export * from "./OutputFormat";
 export * from "./RawOutputFormat";
-export * from "./RawBytesOutputFormat";
 export * from "./RawEncoding";
 export * from "./WavOutputFormat";
-export * from "./WavBytesOutputFormat";
 export * from "./Mp3OutputFormat";
 export * from "./TtsRequestVoiceSpecifier";
 export * from "./TtsRequestIdSpecifier";
@@ -29,7 +28,3 @@ export * from "./Speed";
 export * from "./NumericalSpecifier";
 export * from "./NaturalSpecifier";
 export * from "./Emotion";
-export * from "./TtsBytesRequest";
-export * from "./BytesOutputFormat";
-export * from "./TtssseRequest";
-export * from "./SseOutputFormat";

src/serialization/resources/tts/types/Mp3OutputFormat.ts

@@ -12,13 +12,11 @@ export const Mp3OutputFormat: core.serialization.ObjectSchema<
 > = core.serialization.object({
     sampleRate: core.serialization.property("sample_rate", core.serialization.number()),
     bitRate: core.serialization.property("bit_rate", core.serialization.number()),
-    loudness: core.serialization.number().optional(),
 });
 
 export declare namespace Mp3OutputFormat {
     interface Raw {
         sample_rate: number;
         bit_rate: number;
-        loudness?: number | null;
     }
 }

src/serialization/resources/tts/types/TtssseRequest.ts → src/serialization/resources/tts/types/TtsRequest.ts

@@ -7,25 +7,25 @@ import * as Cartesia from "../../../../api/index";
 import * as core from "../../../../core";
 import { TtsRequestVoiceSpecifier } from "./TtsRequestVoiceSpecifier";
 import { SupportedLanguage } from "./SupportedLanguage";
-import { SseOutputFormat } from "./SseOutputFormat";
+import { OutputFormat } from "./OutputFormat";
 
-export const TtssseRequest: core.serialization.ObjectSchema<serializers.TtssseRequest.Raw, Cartesia.TtssseRequest> =
+export const TtsRequest: core.serialization.ObjectSchema<serializers.TtsRequest.Raw, Cartesia.TtsRequest> =
     core.serialization.object({
         modelId: core.serialization.property("model_id", core.serialization.string()),
         transcript: core.serialization.string(),
         voice: TtsRequestVoiceSpecifier,
         language: SupportedLanguage.optional(),
-        outputFormat: core.serialization.property("output_format", SseOutputFormat),
+        outputFormat: core.serialization.property("output_format", OutputFormat),
         duration: core.serialization.number().optional(),
     });
 
-export declare namespace TtssseRequest {
+export declare namespace TtsRequest {
     interface Raw {
         model_id: string;
         transcript: string;
         voice: TtsRequestVoiceSpecifier.Raw;
         language?: SupportedLanguage.Raw | null;
-        output_format: SseOutputFormat.Raw;
+        output_format: OutputFormat.Raw;
         duration?: number | null;
     }
 }

src/serialization/resources/tts/types/index.ts

@@ -13,13 +13,12 @@ export * from "./GenerationRequest";
 export * from "./WebSocketRawOutputFormat";
 export * from "./WebSocketRequest";
 export * from "./WebSocketTtsRequest";
+export * from "./TtsRequest";
 export * from "./SupportedLanguage";
 export * from "./OutputFormat";
 export * from "./RawOutputFormat";
-export * from "./RawBytesOutputFormat";
 export * from "./RawEncoding";
 export * from "./WavOutputFormat";
-export * from "./WavBytesOutputFormat";
 export * from "./Mp3OutputFormat";
 export * from "./TtsRequestVoiceSpecifier";
 export * from "./TtsRequestIdSpecifier";
@@ -29,7 +28,3 @@ export * from "./Speed";
 export * from "./NumericalSpecifier";
 export * from "./NaturalSpecifier";
 export * from "./Emotion";
-export * from "./TtsBytesRequest";
-export * from "./BytesOutputFormat";
-export * from "./TtssseRequest";
-export * from "./SseOutputFormat";