Merge pull request #1552 from openai/release-please--branches--master--changes--next--components--openai

release: 5.7.0

Author: kwhinnery-openai

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "5.6.0"
+  ".": "5.7.0"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 111
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-f411a68f272b8be0ab0c266043da33228687b9b2d76896724e3cef797de9563d.yml
-openapi_spec_hash: 89bf866ea95ecfb3d76c8833237047d6
-config_hash: dc5515e257676a27cb1ace1784aa92b3
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-ef4ecb19eb61e24c49d77fef769ee243e5279bc0bdbaee8d0f8dba4da8722559.yml
+openapi_spec_hash: 1b8a9767c9f04e6865b06c41948cdc24
+config_hash: fd2af1d5eff0995bb7dc02ac9a34851d

CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 5.7.0 (2025-06-23)
+
+Full Changelog: [v5.6.0...v5.7.0](https://github.com/openai/openai-node/compare/v5.6.0...v5.7.0)
+
+### Features
+
+* **api:** update api shapes for usage and code interpreter ([f2100e8](https://github.com/openai/openai-node/commit/f2100e89334753e7f580f7f20f48b43eb8ba2fe3))
+
 ## 5.6.0 (2025-06-20)
 
 Full Changelog: [v5.5.1...v5.6.0](https://github.com/openai/openai-node/compare/v5.5.1...v5.6.0)

api.md

@@ -259,7 +259,7 @@ Types:
 Methods:
 
 - <code title="post /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions">client.fineTuning.checkpoints.permissions.<a href="./src/resources/fine-tuning/checkpoints/permissions.ts">create</a>(fineTunedModelCheckpoint, { ...params }) -> PermissionCreateResponsesPage</code>
-- <code title="get /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions">client.fineTuning.checkpoints.permissions.<a href="./src/resources/fine-tuning/checkpoints/permissions.ts">retrieve</a>(fineTunedModelCheckpoint, { ...params }) -> PermissionRetrieveResponsesPage</code>
+- <code title="get /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions">client.fineTuning.checkpoints.permissions.<a href="./src/resources/fine-tuning/checkpoints/permissions.ts">retrieve</a>(fineTunedModelCheckpoint, { ...params }) -> PermissionRetrieveResponse</code>
 - <code title="delete /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id}">client.fineTuning.checkpoints.permissions.<a href="./src/resources/fine-tuning/checkpoints/permissions.ts">delete</a>(permissionID, { ...params }) -> PermissionDeleteResponse</code>
 
 ## Alpha

jsr.json

@@ -1,6 +1,6 @@
 {
   "name": "@openai/openai",
-  "version": "5.6.0",
+  "version": "5.7.0",
   "exports": {
     ".": "./index.ts",
     "./helpers/zod": "./helpers/zod.ts",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "openai",
-  "version": "5.6.0",
+  "version": "5.7.0",
   "description": "The official TypeScript library for the OpenAI API",
   "author": "OpenAI <[email protected]>",
   "types": "dist/index.d.ts",

src/resources/audio/speech.ts

@@ -79,9 +79,15 @@ export interface SpeechCreateParams {
 
   /**
    * The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is
-   * the default. Does not work with `gpt-4o-mini-tts`.
+   * the default.
    */
   speed?: number;
+
+  /**
+   * The format to stream the audio in. Supported formats are `sse` and `audio`.
+   * `sse` is not supported for `tts-1` or `tts-1-hd`.
+   */
+  stream_format?: 'sse' | 'audio';
 }
 
 export declare namespace Speech {

src/resources/audio/transcriptions.ts

@@ -78,6 +78,11 @@ export interface Transcription {
    * to the `include` array.
    */
   logprobs?: Array<Transcription.Logprob>;
+
+  /**
+   * Token usage statistics for the request.
+   */
+  usage?: Transcription.Tokens | Transcription.Duration;
 }
 
 export namespace Transcription {
@@ -97,6 +102,68 @@ export namespace Transcription {
      */
     logprob?: number;
   }
+
+  /**
+   * Usage statistics for models billed by token usage.
+   */
+  export interface Tokens {
+    /**
+     * Number of input tokens billed for this request.
+     */
+    input_tokens: number;
+
+    /**
+     * Number of output tokens generated.
+     */
+    output_tokens: number;
+
+    /**
+     * Total number of tokens used (input + output).
+     */
+    total_tokens: number;
+
+    /**
+     * The type of the usage object. Always `tokens` for this variant.
+     */
+    type: 'tokens';
+
+    /**
+     * Details about the input tokens billed for this request.
+     */
+    input_token_details?: Tokens.InputTokenDetails;
+  }
+
+  export namespace Tokens {
+    /**
+     * Details about the input tokens billed for this request.
+     */
+    export interface InputTokenDetails {
+      /**
+       * Number of audio tokens billed for this request.
+       */
+      audio_tokens?: number;
+
+      /**
+       * Number of text tokens billed for this request.
+       */
+      text_tokens?: number;
+    }
+  }
+
+  /**
+   * Usage statistics for models billed by audio input duration.
+   */
+  export interface Duration {
+    /**
+     * Duration of the input audio in seconds.
+     */
+    duration: number;
+
+    /**
+     * The type of the usage object. Always `duration` for this variant.
+     */
+    type: 'duration';
+  }
 }
 
 export type TranscriptionInclude = 'logprobs';
@@ -232,6 +299,11 @@ export interface TranscriptionTextDoneEvent {
    * with the `include[]` parameter set to `logprobs`.
    */
   logprobs?: Array<TranscriptionTextDoneEvent.Logprob>;
+
+  /**
+   * Usage statistics for models billed by token usage.
+   */
+  usage?: TranscriptionTextDoneEvent.Usage;
 }
 
 export namespace TranscriptionTextDoneEvent {
@@ -251,6 +323,53 @@ export namespace TranscriptionTextDoneEvent {
      */
     logprob?: number;
   }
+
+  /**
+   * Usage statistics for models billed by token usage.
+   */
+  export interface Usage {
+    /**
+     * Number of input tokens billed for this request.
+     */
+    input_tokens: number;
+
+    /**
+     * Number of output tokens generated.
+     */
+    output_tokens: number;
+
+    /**
+     * Total number of tokens used (input + output).
+     */
+    total_tokens: number;
+
+    /**
+     * The type of the usage object. Always `tokens` for this variant.
+     */
+    type: 'tokens';
+
+    /**
+     * Details about the input tokens billed for this request.
+     */
+    input_token_details?: Usage.InputTokenDetails;
+  }
+
+  export namespace Usage {
+    /**
+     * Details about the input tokens billed for this request.
+     */
+    export interface InputTokenDetails {
+      /**
+       * Number of audio tokens billed for this request.
+       */
+      audio_tokens?: number;
+
+      /**
+       * Number of text tokens billed for this request.
+       */
+      text_tokens?: number;
+    }
+  }
 }
 
 /**
@@ -278,12 +397,34 @@ export interface TranscriptionVerbose {
    */
   segments?: Array<TranscriptionSegment>;
 
+  /**
+   * Usage statistics for models billed by audio input duration.
+   */
+  usage?: TranscriptionVerbose.Usage;
+
   /**
    * Extracted words and their corresponding timestamps.
    */
   words?: Array<TranscriptionWord>;
 }
 
+export namespace TranscriptionVerbose {
+  /**
+   * Usage statistics for models billed by audio input duration.
+   */
+  export interface Usage {
+    /**
+     * Duration of the input audio in seconds.
+     */
+    duration: number;
+
+    /**
+     * The type of the usage object. Always `duration` for this variant.
+     */
+    type: 'duration';
+  }
+}
+
 export interface TranscriptionWord {
   /**
    * End time of the word in seconds.

src/resources/beta/realtime/realtime.ts

@@ -279,9 +279,9 @@ export interface ConversationItemDeletedEvent {
  * the Response events.
  *
  * Realtime API models accept audio natively, and thus input transcription is a
- * separate process run on a separate ASR (Automatic Speech Recognition) model,
- * currently always `whisper-1`. Thus the transcript may diverge somewhat from the
- * model's interpretation, and should be treated as a rough guide.
+ * separate process run on a separate ASR (Automatic Speech Recognition) model. The
+ * transcript may diverge somewhat from the model's interpretation, and should be
+ * treated as a rough guide.
  */
 export interface ConversationItemInputAudioTranscriptionCompletedEvent {
   /**
@@ -2248,19 +2248,19 @@ export namespace SessionUpdateEvent {
       /**
        * Configuration for the ephemeral token expiration.
        */
-      expires_at?: ClientSecret.ExpiresAt;
+      expires_after?: ClientSecret.ExpiresAfter;
     }
 
     export namespace ClientSecret {
       /**
        * Configuration for the ephemeral token expiration.
        */
-      export interface ExpiresAt {
+      export interface ExpiresAfter {
         /**
          * The anchor point for the ephemeral token expiration. Only `created_at` is
          * currently supported.
          */
-        anchor?: 'created_at';
+        anchor: 'created_at';
 
         /**
          * The number of seconds from the anchor point to the expiration. Select a value

src/resources/beta/realtime/sessions.ts

@@ -356,8 +356,8 @@ export interface SessionCreateResponse {
    * Configuration for input audio transcription, defaults to off and can be set to
    * `null` to turn off once on. Input audio transcription is not native to the
    * model, since the model consumes audio directly. Transcription runs
-   * asynchronously through Whisper and should be treated as rough guidance rather
-   * than the representation understood by the model.
+   * asynchronously and should be treated as rough guidance rather than the
+   * representation understood by the model.
    */
   input_audio_transcription?: SessionCreateResponse.InputAudioTranscription;
 
@@ -476,13 +476,12 @@ export namespace SessionCreateResponse {
    * Configuration for input audio transcription, defaults to off and can be set to
    * `null` to turn off once on. Input audio transcription is not native to the
    * model, since the model consumes audio directly. Transcription runs
-   * asynchronously through Whisper and should be treated as rough guidance rather
-   * than the representation understood by the model.
+   * asynchronously and should be treated as rough guidance rather than the
+   * representation understood by the model.
    */
   export interface InputAudioTranscription {
     /**
-     * The model to use for transcription, `whisper-1` is the only currently supported
-     * model.
+     * The model to use for transcription.
      */
     model?: string;
   }
@@ -721,19 +720,19 @@ export namespace SessionCreateParams {
     /**
      * Configuration for the ephemeral token expiration.
      */
-    expires_at?: ClientSecret.ExpiresAt;
+    expires_after?: ClientSecret.ExpiresAfter;
   }
 
   export namespace ClientSecret {
     /**
      * Configuration for the ephemeral token expiration.
      */
-    export interface ExpiresAt {
+    export interface ExpiresAfter {
       /**
        * The anchor point for the ephemeral token expiration. Only `created_at` is
        * currently supported.
        */
-      anchor?: 'created_at';
+      anchor: 'created_at';
 
       /**
        * The number of seconds from the anchor point to the expiration. Select a value