feat(api): Add support for gpt-4o-transcribe-diarize on audio/transcriptions endpoint

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 135
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-11d308a9ef78ad01aa11c880a084a3982276800d7994db3f454aa515474977d7.yml
-openapi_spec_hash: 0a4bbb5aa0ae532a072bd6b3854e70b1
-config_hash: f0940d0906846178759ef7128e4cb98e
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-104cced8f4c7436a76eea02e26307828166405ccfb296faffb008b72772c11a7.yml
+openapi_spec_hash: fdc03ed84a65a31b80da909255e53924
+config_hash: 03b48e9b8c7231a902403210dbd7dfa0

api.md

@@ -156,11 +156,14 @@ Types:
 Types:
 
 - <code><a href="./src/resources/audio/transcriptions.ts">Transcription</a></code>
+- <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionDiarized</a></code>
+- <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionDiarizedSegment</a></code>
 - <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionInclude</a></code>
 - <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionSegment</a></code>
 - <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionStreamEvent</a></code>
 - <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionTextDeltaEvent</a></code>
 - <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionTextDoneEvent</a></code>
+- <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionTextSegmentEvent</a></code>
 - <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionVerbose</a></code>
 - <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionWord</a></code>
 - <code><a href="./src/resources/audio/transcriptions.ts">TranscriptionCreateResponse</a></code>

src/resources/audio/audio.ts

@@ -10,11 +10,14 @@ import {
   TranscriptionCreateParamsNonStreaming,
   TranscriptionCreateParamsStreaming,
   TranscriptionCreateResponse,
+  TranscriptionDiarized,
+  TranscriptionDiarizedSegment,
   TranscriptionInclude,
   TranscriptionSegment,
   TranscriptionStreamEvent,
   TranscriptionTextDeltaEvent,
   TranscriptionTextDoneEvent,
+  TranscriptionTextSegmentEvent,
   TranscriptionVerbose,
   TranscriptionWord,
   Transcriptions,
@@ -34,14 +37,20 @@ export class Audio extends APIResource {
   speech: SpeechAPI.Speech = new SpeechAPI.Speech(this._client);
 }
 
-export type AudioModel = 'whisper-1' | 'gpt-4o-transcribe' | 'gpt-4o-mini-transcribe';
+export type AudioModel =
+  | 'whisper-1'
+  | 'gpt-4o-transcribe'
+  | 'gpt-4o-mini-transcribe'
+  | 'gpt-4o-transcribe-diarize';
 
 /**
  * The format of the output, in one of these options: `json`, `text`, `srt`,
- * `verbose_json`, or `vtt`. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`,
- * the only supported format is `json`.
+ * `verbose_json`, `vtt`, or `diarized_json`. For `gpt-4o-transcribe` and
+ * `gpt-4o-mini-transcribe`, the only supported format is `json`. For
+ * `gpt-4o-transcribe-diarize`, the supported formats are `json`, `text`, and
+ * `diarized_json`, with `diarized_json` required to receive speaker annotations.
  */
-export type AudioResponseFormat = 'json' | 'text' | 'srt' | 'verbose_json' | 'vtt';
+export type AudioResponseFormat = 'json' | 'text' | 'srt' | 'verbose_json' | 'vtt' | 'diarized_json';
 
 Audio.Transcriptions = Transcriptions;
 Audio.Translations = Translations;
@@ -53,11 +62,14 @@ export declare namespace Audio {
   export {
     Transcriptions as Transcriptions,
     type Transcription as Transcription,
+    type TranscriptionDiarized as TranscriptionDiarized,
+    type TranscriptionDiarizedSegment as TranscriptionDiarizedSegment,
     type TranscriptionInclude as TranscriptionInclude,
     type TranscriptionSegment as TranscriptionSegment,
     type TranscriptionStreamEvent as TranscriptionStreamEvent,
     type TranscriptionTextDeltaEvent as TranscriptionTextDeltaEvent,
     type TranscriptionTextDoneEvent as TranscriptionTextDoneEvent,
+    type TranscriptionTextSegmentEvent as TranscriptionTextSegmentEvent,
     type TranscriptionVerbose as TranscriptionVerbose,
     type TranscriptionWord as TranscriptionWord,
     type TranscriptionCreateResponse as TranscriptionCreateResponse,

src/resources/audio/index.ts

@@ -5,11 +5,14 @@ export { Speech, type SpeechModel, type SpeechCreateParams } from './speech';
 export {
   Transcriptions,
   type Transcription,
+  type TranscriptionDiarized,
+  type TranscriptionDiarizedSegment,
   type TranscriptionInclude,
   type TranscriptionSegment,
   type TranscriptionStreamEvent,
   type TranscriptionTextDeltaEvent,
   type TranscriptionTextDoneEvent,
+  type TranscriptionTextSegmentEvent,
   type TranscriptionVerbose,
   type TranscriptionWord,
   type TranscriptionCreateResponse,