diff --git a/openapi.yaml b/openapi.yaml
index 64ed15bd..e614890a 100644
--- a/openapi.yaml
+++ b/openapi.yaml
@@ -10900,16 +10900,7 @@ components:
                         An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the audio language.
                     type: string
                 response_format:
-                    description: |
-                        The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`.
-                    type: string
-                    enum:
-                        - json
-                        - text
-                        - srt
-                        - verbose_json
-                        - vtt
-                    default: json
+                    $ref: "#/components/schemas/AudioResponseFormat"
                 temperature:
                     description: |
                         The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.
@@ -11042,6 +11033,18 @@ components:
                 group: audio
                 example: *verbose_transcription_response_example
 
+        AudioResponseFormat:
+            description: |
+                The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`.
+            type: string
+            enum:
+                - json
+                - text
+                - srt
+                - verbose_json
+                - vtt
+            default: json
+
         CreateTranslationRequest:
             type: object
             additionalProperties: false
@@ -11066,10 +11069,7 @@ components:
                         An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in English.
                     type: string
                 response_format:
-                    description: |
-                        The format of the transcript output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`.
-                    type: string
-                    default: json
+                    $ref: "#/components/schemas/AudioResponseFormat"
                 temperature:
                     description: |
                         The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.