feat(api): Change TTS call signature

BREAKING CHANGE: Change call signature for `audio.create` to `audio.speech.create` to match spec with python library and add space for future APIs

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 45
 openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/togetherai%2Ftogetherai-b86f8e6c4674d1a7829ffa8ddff4bc93d21334d231e6a4d0fd734d411c07a4eb.yml
 openapi_spec_hash: 8af4975be6ae8f4655fa92fd26af9682
-config_hash: b337cdd3c62dbd3383529592a029b347
+config_hash: afbbabb8eb5bfbbf8139546a13addd9a

api.md

@@ -148,9 +148,11 @@ Types:
 - <code><a href="./src/resources/audio/audio.ts">AudioFile</a></code>
 - <code><a href="./src/resources/audio/audio.ts">AudioSpeechStreamChunk</a></code>
 
+## Speech
+
 Methods:
 
-- <code title="post /audio/speech">client.audio.<a href="./src/resources/audio/audio.ts">create</a>({ ...params }) -> Response</code>
+- <code title="post /audio/speech">client.audio.speech.<a href="./src/resources/audio/speech.ts">create</a>({ ...params }) -> Response</code>
 
 ## Voices
 

src/client.ts

@@ -93,14 +93,7 @@ import { JobListResponse, JobRetrieveResponse, Jobs } from './resources/jobs';
 import { ModelListResponse, ModelUploadParams, ModelUploadResponse, Models } from './resources/models';
 import { Rerank, RerankCreateParams, RerankCreateResponse } from './resources/rerank';
 import { VideoCreateParams, VideoCreateResponse, VideoJob, Videos } from './resources/videos';
-import {
-  Audio,
-  AudioCreateParams,
-  AudioCreateParamsNonStreaming,
-  AudioCreateParamsStreaming,
-  AudioFile,
-  AudioSpeechStreamChunk,
-} from './resources/audio/audio';
+import { Audio, AudioFile, AudioSpeechStreamChunk } from './resources/audio/audio';
 import { Chat } from './resources/chat/chat';
 import {
   CodeInterpreter,
@@ -920,9 +913,6 @@ export declare namespace Together {
     Audio as Audio,
     type AudioFile as AudioFile,
     type AudioSpeechStreamChunk as AudioSpeechStreamChunk,
-    type AudioCreateParams as AudioCreateParams,
-    type AudioCreateParamsNonStreaming as AudioCreateParamsNonStreaming,
-    type AudioCreateParamsStreaming as AudioCreateParamsStreaming,
   };
 
   export {

src/resources/audio/audio.ts

@@ -2,58 +2,25 @@
 
 import { APIResource } from '../../core/resource';
 import * as AudioAPI from './audio';
+import * as SpeechAPI from './speech';
+import {
+  Speech,
+  SpeechCreateParams,
+  SpeechCreateParamsNonStreaming,
+  SpeechCreateParamsStreaming,
+} from './speech';
 import * as TranscriptionsAPI from './transcriptions';
 import { TranscriptionCreateParams, TranscriptionCreateResponse, Transcriptions } from './transcriptions';
 import * as TranslationsAPI from './translations';
 import { TranslationCreateParams, TranslationCreateResponse, Translations } from './translations';
 import * as VoicesAPI from './voices';
 import { VoiceListResponse, Voices } from './voices';
-import { APIPromise } from '../../core/api-promise';
-import { Stream } from '../../core/streaming';
-import { buildHeaders } from '../../internal/headers';
-import { RequestOptions } from '../../internal/request-options';
 
 export class Audio extends APIResource {
+  speech: SpeechAPI.Speech = new SpeechAPI.Speech(this._client);
   voices: VoicesAPI.Voices = new VoicesAPI.Voices(this._client);
   transcriptions: TranscriptionsAPI.Transcriptions = new TranscriptionsAPI.Transcriptions(this._client);
   translations: TranslationsAPI.Translations = new TranslationsAPI.Translations(this._client);
-
-  /**
-   * Generate audio from input text
-   *
-   * @example
-   * ```ts
-   * const audio = await client.audio.create({
-   *   input: 'input',
-   *   model: 'canopylabs/orpheus-3b-0.1-ft',
-   *   voice: 'voice',
-   * });
-   *
-   * const content = await audio.blob();
-   * console.log(content);
-   * ```
-   */
-  create(body: AudioCreateParamsNonStreaming, options?: RequestOptions): APIPromise<Response>;
-  create(
-    body: AudioCreateParamsStreaming,
-    options?: RequestOptions,
-  ): APIPromise<Stream<AudioSpeechStreamChunk>>;
-  create(
-    body: AudioCreateParamsBase,
-    options?: RequestOptions,
-  ): APIPromise<Stream<AudioSpeechStreamChunk> | Response>;
-  create(
-    body: AudioCreateParams,
-    options?: RequestOptions,
-  ): APIPromise<Response> | APIPromise<Stream<AudioSpeechStreamChunk>> {
-    return this._client.post('/audio/speech', {
-      body,
-      ...options,
-      headers: buildHeaders([{ Accept: 'application/octet-stream' }, options?.headers]),
-      stream: body.stream ?? false,
-      __binaryResponse: true,
-    }) as APIPromise<Response> | APIPromise<Stream<AudioSpeechStreamChunk>>;
-  }
 }
 
 export type AudioFile = AudioFile.AudioSpeechStreamEvent | AudioFile.StreamSentinel;
@@ -79,116 +46,19 @@ export interface AudioSpeechStreamChunk {
   object: 'audio.tts.chunk';
 }
 
-export type AudioCreateParams = AudioCreateParamsNonStreaming | AudioCreateParamsStreaming;
-
-export interface AudioCreateParamsBase {
-  /**
-   * Input text to generate the audio for
-   */
-  input: string;
-
-  /**
-   * The name of the model to query.
-   *
-   * [See all of Together AI's chat models](https://docs.together.ai/docs/serverless-models#audio-models)
-   * The current supported tts models are: - cartesia/sonic - hexgrad/Kokoro-82M -
-   * canopylabs/orpheus-3b-0.1-ft
-   */
-  model: 'cartesia/sonic' | 'hexgrad/Kokoro-82M' | 'canopylabs/orpheus-3b-0.1-ft' | (string & {});
-
-  /**
-   * The voice to use for generating the audio. The voices supported are different
-   * for each model. For eg - for canopylabs/orpheus-3b-0.1-ft, one of the voices
-   * supported is tara, for hexgrad/Kokoro-82M, one of the voices supported is
-   * af_alloy and for cartesia/sonic, one of the voices supported is "friendly
-   * sidekick".
-   *
-   * You can view the voices supported for each model using the /v1/voices endpoint
-   * sending the model name as the query parameter.
-   * [View all supported voices here](https://docs.together.ai/docs/text-to-speech#voices-available).
-   */
-  voice: string;
-
-  /**
-   * Language of input text.
-   */
-  language?:
-    | 'en'
-    | 'de'
-    | 'fr'
-    | 'es'
-    | 'hi'
-    | 'it'
-    | 'ja'
-    | 'ko'
-    | 'nl'
-    | 'pl'
-    | 'pt'
-    | 'ru'
-    | 'sv'
-    | 'tr'
-    | 'zh';
-
-  /**
-   * Audio encoding of response
-   */
-  response_encoding?: 'pcm_f32le' | 'pcm_s16le' | 'pcm_mulaw' | 'pcm_alaw';
-
-  /**
-   * The format of audio output. Supported formats are mp3, wav, raw if streaming is
-   * false. If streaming is true, the only supported format is raw.
-   */
-  response_format?: 'mp3' | 'wav' | 'raw';
-
-  /**
-   * Sampling rate to use for the output audio. The default sampling rate for
-   * canopylabs/orpheus-3b-0.1-ft and hexgrad/Kokoro-82M is 24000 and for
-   * cartesia/sonic is 44100.
-   */
-  sample_rate?: number;
-
-  /**
-   * If true, output is streamed for several characters at a time instead of waiting
-   * for the full response. The stream terminates with `data: [DONE]`. If false,
-   * return the encoded audio as octet stream
-   */
-  stream?: boolean;
-}
-
-export namespace AudioCreateParams {
-  export type AudioCreateParamsNonStreaming = AudioAPI.AudioCreateParamsNonStreaming;
-  export type AudioCreateParamsStreaming = AudioAPI.AudioCreateParamsStreaming;
-}
-
-export interface AudioCreateParamsNonStreaming extends AudioCreateParamsBase {
-  /**
-   * If true, output is streamed for several characters at a time instead of waiting
-   * for the full response. The stream terminates with `data: [DONE]`. If false,
-   * return the encoded audio as octet stream
-   */
-  stream?: false;
-}
-
-export interface AudioCreateParamsStreaming extends AudioCreateParamsBase {
-  /**
-   * If true, output is streamed for several characters at a time instead of waiting
-   * for the full response. The stream terminates with `data: [DONE]`. If false,
-   * return the encoded audio as octet stream
-   */
-  stream: true;
-}
-
+Audio.Speech = Speech;
 Audio.Voices = Voices;
 Audio.Transcriptions = Transcriptions;
 Audio.Translations = Translations;
 
 export declare namespace Audio {
+  export { type AudioFile as AudioFile, type AudioSpeechStreamChunk as AudioSpeechStreamChunk };
+
   export {
-    type AudioFile as AudioFile,
-    type AudioSpeechStreamChunk as AudioSpeechStreamChunk,
-    type AudioCreateParams as AudioCreateParams,
-    type AudioCreateParamsNonStreaming as AudioCreateParamsNonStreaming,
-    type AudioCreateParamsStreaming as AudioCreateParamsStreaming,
+    Speech as Speech,
+    type SpeechCreateParams as SpeechCreateParams,
+    type SpeechCreateParamsNonStreaming as SpeechCreateParamsNonStreaming,
+    type SpeechCreateParamsStreaming as SpeechCreateParamsStreaming,
   };
 
   export { Voices as Voices, type VoiceListResponse as VoiceListResponse };

src/resources/audio/index.ts

@@ -1,13 +1,12 @@
 // File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
+export { Audio, type AudioFile, type AudioSpeechStreamChunk } from './audio';
 export {
-  Audio,
-  type AudioFile,
-  type AudioSpeechStreamChunk,
-  type AudioCreateParams,
-  type AudioCreateParamsNonStreaming,
-  type AudioCreateParamsStreaming,
-} from './audio';
+  Speech,
+  type SpeechCreateParams,
+  type SpeechCreateParamsNonStreaming,
+  type SpeechCreateParamsStreaming,
+} from './speech';
 export {
   Transcriptions,
   type TranscriptionCreateResponse,