openai 4.65.0 → 4.67.0

package/src/resources/audio/transcriptions.ts

@@ -9,7 +9,23 @@ export class Transcriptions extends APIResource {
   /**
    * Transcribes audio into the input language.
    */
-  create(body: TranscriptionCreateParams, options?: Core.RequestOptions): Core.APIPromise<Transcription> {
+  create(
+    body: TranscriptionCreateParams<'json' | undefined>,
+    options?: Core.RequestOptions,
+  ): Core.APIPromise<Transcription>;
+  create(
+    body: TranscriptionCreateParams<'verbose_json'>,
+    options?: Core.RequestOptions,
+  ): Core.APIPromise<TranscriptionVerbose>;
+  create(
+    body: TranscriptionCreateParams<'srt' | 'vtt' | 'text'>,
+    options?: Core.RequestOptions,
+  ): Core.APIPromise<string>;
+  create(body: TranscriptionCreateParams, options?: Core.RequestOptions): Core.APIPromise<Transcription>;
+  create(
+    body: TranscriptionCreateParams,
+    options?: Core.RequestOptions,
+  ): Core.APIPromise<TranscriptionCreateResponse | string> {
     return this._client.post('/audio/transcriptions', Core.multipartFormRequestOptions({ body, ...options }));
   }
 }
@@ -25,7 +41,118 @@ export interface Transcription {
   text: string;
 }
 
-export interface TranscriptionCreateParams {
+export interface TranscriptionSegment {
+  /**
+   * Unique identifier of the segment.
+   */
+  id: number;
+
+  /**
+   * Average logprob of the segment. If the value is lower than -1, consider the
+   * logprobs failed.
+   */
+  avg_logprob: number;
+
+  /**
+   * Compression ratio of the segment. If the value is greater than 2.4, consider the
+   * compression failed.
+   */
+  compression_ratio: number;
+
+  /**
+   * End time of the segment in seconds.
+   */
+  end: number;
+
+  /**
+   * Probability of no speech in the segment. If the value is higher than 1.0 and the
+   * `avg_logprob` is below -1, consider this segment silent.
+   */
+  no_speech_prob: number;
+
+  /**
+   * Seek offset of the segment.
+   */
+  seek: number;
+
+  /**
+   * Start time of the segment in seconds.
+   */
+  start: number;
+
+  /**
+   * Temperature parameter used for generating the segment.
+   */
+  temperature: number;
+
+  /**
+   * Text content of the segment.
+   */
+  text: string;
+
+  /**
+   * Array of token IDs for the text content.
+   */
+  tokens: Array<number>;
+}
+
+/**
+ * Represents a verbose json transcription response returned by model, based on the
+ * provided input.
+ */
+export interface TranscriptionVerbose {
+  /**
+   * The duration of the input audio.
+   */
+  duration: string;
+
+  /**
+   * The language of the input audio.
+   */
+  language: string;
+
+  /**
+   * The transcribed text.
+   */
+  text: string;
+
+  /**
+   * Segments of the transcribed text and their corresponding details.
+   */
+  segments?: Array<TranscriptionSegment>;
+
+  /**
+   * Extracted words and their corresponding timestamps.
+   */
+  words?: Array<TranscriptionWord>;
+}
+
+export interface TranscriptionWord {
+  /**
+   * End time of the word in seconds.
+   */
+  end: number;
+
+  /**
+   * Start time of the word in seconds.
+   */
+  start: number;
+
+  /**
+   * The text content of the word.
+   */
+  word: string;
+}
+
+/**
+ * Represents a transcription response returned by model, based on the provided
+ * input.
+ */
+export type TranscriptionCreateResponse = Transcription | TranscriptionVerbose;
+
+export interface TranscriptionCreateParams<
+  ResponseFormat extends AudioAPI.AudioResponseFormat | undefined = AudioAPI.AudioResponseFormat | undefined,
+> {
   /**
    * The audio file object (not file name) to transcribe, in one of these formats:
    * flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
@@ -57,7 +184,7 @@ export interface TranscriptionCreateParams {
    * The format of the output, in one of these options: `json`, `text`, `srt`,
    * `verbose_json`, or `vtt`.
    */
-  response_format?: AudioAPI.AudioResponseFormat;
+  response_format?: ResponseFormat;
 
   /**
    * The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
@@ -80,5 +207,13 @@ export interface TranscriptionCreateParams {
 
 export namespace Transcriptions {
   export import Transcription = TranscriptionsAPI.Transcription;
-  export import TranscriptionCreateParams = TranscriptionsAPI.TranscriptionCreateParams;
+  export import TranscriptionSegment = TranscriptionsAPI.TranscriptionSegment;
+  export import TranscriptionVerbose = TranscriptionsAPI.TranscriptionVerbose;
+  export import TranscriptionWord = TranscriptionsAPI.TranscriptionWord;
+  export import TranscriptionCreateResponse = TranscriptionsAPI.TranscriptionCreateResponse;
+  export type TranscriptionCreateParams<
+    ResponseFormat extends AudioAPI.AudioResponseFormat | undefined =
+      | AudioAPI.AudioResponseFormat
+      | undefined,
+  > = TranscriptionsAPI.TranscriptionCreateParams<ResponseFormat>;
 }

package/src/resources/audio/translations.ts

@@ -4,12 +4,29 @@ import { APIResource } from '../../resource';
 import * as Core from '../../core';
 import * as TranslationsAPI from './translations';
 import * as AudioAPI from './audio';
+import * as TranscriptionsAPI from './transcriptions';
 
 export class Translations extends APIResource {
   /**
    * Translates audio into English.
    */
-  create(body: TranslationCreateParams, options?: Core.RequestOptions): Core.APIPromise<Translation> {
+  create(
+    body: TranslationCreateParams<'json' | undefined>,
+    options?: Core.RequestOptions,
+  ): Core.APIPromise<Translation>;
+  create(
+    body: TranslationCreateParams<'verbose_json'>,
+    options?: Core.RequestOptions,
+  ): Core.APIPromise<TranslationVerbose>;
+  create(
+    body: TranslationCreateParams<'text' | 'srt' | 'vtt'>,
+    options?: Core.RequestOptions,
+  ): Core.APIPromise<string>;
+  create(body: TranslationCreateParams, options?: Core.RequestOptions): Core.APIPromise<Translation>;
+  create(
+    body: TranslationCreateParams,
+    options?: Core.RequestOptions,
+  ): Core.APIPromise<TranslationCreateResponse | string> {
     return this._client.post('/audio/translations', Core.multipartFormRequestOptions({ body, ...options }));
   }
 }
@@ -18,7 +35,33 @@ export interface Translation {
   text: string;
 }
 
-export interface TranslationCreateParams {
+export interface TranslationVerbose {
+  /**
+   * The duration of the input audio.
+   */
+  duration: string;
+
+  /**
+   * The language of the output translation (always `english`).
+   */
+  language: string;
+
+  /**
+   * The translated text.
+   */
+  text: string;
+
+  /**
+   * Segments of the translated text and their corresponding details.
+   */
+  segments?: Array<TranscriptionsAPI.TranscriptionSegment>;
+}
+
+export type TranslationCreateResponse = Translation | TranslationVerbose;
+
+export interface TranslationCreateParams<
+  ResponseFormat extends AudioAPI.AudioResponseFormat | undefined = AudioAPI.AudioResponseFormat | undefined,
+> {
   /**
    * The audio file object (not file name) translate, in one of these formats: flac,
    * mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
@@ -43,7 +86,7 @@ export interface TranslationCreateParams {
    * The format of the output, in one of these options: `json`, `text`, `srt`,
    * `verbose_json`, or `vtt`.
    */
-  response_format?: AudioAPI.AudioResponseFormat;
+  response_format?: ResponseFormat;
 
   /**
    * The sampling temperature, between 0 and 1. Higher values like 0.8 will make the
@@ -57,5 +100,11 @@ export interface TranslationCreateParams {
 
 export namespace Translations {
   export import Translation = TranslationsAPI.Translation;
-  export import TranslationCreateParams = TranslationsAPI.TranslationCreateParams;
+  export import TranslationVerbose = TranslationsAPI.TranslationVerbose;
+  export import TranslationCreateResponse = TranslationsAPI.TranslationCreateResponse;
+  export type TranslationCreateParams<
+    ResponseFormat extends AudioAPI.AudioResponseFormat | undefined =
+      | AudioAPI.AudioResponseFormat
+      | undefined,
+  > = TranslationsAPI.TranslationCreateParams<ResponseFormat>;
 }

package/src/resources/chat/chat.ts

@@ -16,6 +16,7 @@ export type ChatModel =
   | 'gpt-4o'
   | 'gpt-4o-2024-08-06'
   | 'gpt-4o-2024-05-13'
+  | 'gpt-4o-realtime-preview-2024-10-01'
   | 'chatgpt-4o-latest'
   | 'gpt-4o-mini'
   | 'gpt-4o-mini-2024-07-18'

package/src/resources/chat/completions.ts

@@ -727,8 +727,12 @@ export type ChatCompletionCreateParams =
 
 export interface ChatCompletionCreateParamsBase {
   /**
-   * A list of messages comprising the conversation so far.
-   * [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).
+   * A list of messages comprising the conversation so far. Depending on the
+   * [model](https://platform.openai.com/docs/models) you use, different message
+   * types (modalities) are supported, like
+   * [text](https://platform.openai.com/docs/guides/text-generation),
+   * [images](https://platform.openai.com/docs/guides/vision), and
+   * [audio](https://platform.openai.com/docs/guides/audio).
    */
   messages: Array<ChatCompletionMessageParam>;
 
@@ -806,6 +810,12 @@ export interface ChatCompletionCreateParamsBase {
    */
   max_tokens?: number | null;
 
+  /**
+   * Developer-defined tags and values used for filtering completions in the
+   * [dashboard](https://platform.openai.com/completions).
+   */
+  metadata?: Record<string, string> | null;
+
   /**
    * How many chat completion choices to generate for each input message. Note that
    * you will be charged based on the number of generated tokens across all of the
@@ -889,6 +899,12 @@ export interface ChatCompletionCreateParamsBase {
    */
   stop?: string | null | Array<string>;
 
+  /**
+   * Whether or not to store the output of this completion request for traffic
+   * logging in the [dashboard](https://platform.openai.com/completions).
+   */
+  store?: boolean | null;
+
   /**
    * If set, partial message deltas will be sent, like in ChatGPT. Tokens will be
    * sent as data-only

package/src/resources/completions.ts

@@ -125,6 +125,11 @@ export interface CompletionUsage {
    * Breakdown of tokens used in a completion.
    */
   completion_tokens_details?: CompletionUsage.CompletionTokensDetails;
+
+  /**
+   * Breakdown of tokens used in the prompt.
+   */
+  prompt_tokens_details?: CompletionUsage.PromptTokensDetails;
 }
 
 export namespace CompletionUsage {
@@ -132,11 +137,31 @@ export namespace CompletionUsage {
    * Breakdown of tokens used in a completion.
    */
   export interface CompletionTokensDetails {
+    /**
+     * Audio input tokens generated by the model.
+     */
+    audio_tokens?: number;
+
     /**
      * Tokens generated by the model for reasoning.
      */
     reasoning_tokens?: number;
   }
+
+  /**
+   * Breakdown of tokens used in the prompt.
+   */
+  export interface PromptTokensDetails {
+    /**
+     * Audio input tokens present in the prompt.
+     */
+    audio_tokens?: number;
+
+    /**
+     * Cached tokens present in the prompt.
+     */
+    cached_tokens?: number;
+  }
 }
 
 export type CompletionCreateParams = CompletionCreateParamsNonStreaming | CompletionCreateParamsStreaming;

package/src/version.ts

@@ -1 +1 @@
-export const VERSION = '4.65.0'; // x-release-please-version
+export const VERSION = '4.67.0'; // x-release-please-version

package/version.d.ts

@@ -1,2 +1,2 @@
-export declare const VERSION = "4.65.0";
+export declare const VERSION = "4.67.0";
 //# sourceMappingURL=version.d.ts.map

package/version.js

@@ -1,5 +1,5 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.VERSION = void 0;
-exports.VERSION = '4.65.0'; // x-release-please-version
+exports.VERSION = '4.67.0'; // x-release-please-version
 //# sourceMappingURL=version.js.map

package/version.mjs

@@ -1,2 +1,2 @@
-export const VERSION = '4.65.0'; // x-release-please-version
+export const VERSION = '4.67.0'; // x-release-please-version
 //# sourceMappingURL=version.mjs.map