feat(api): slugs for new audio models; make all model params accept strings

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 137
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-235aa1c75c6cc178b97d074a4671343469f458c4a306ef7beb4e45ab252aa589.yml
-openapi_spec_hash: 6e615d34cf8c6bc76e0c6933fc8569af
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-75926226b642ebb2cb415694da9dff35e8ab40145ac1b791cefb82a83809db4d.yml
+openapi_spec_hash: 6a0e391b0ba5747b6b4a3e5fe21de4da
 config_hash: c028ce402ef5f71da947c3f15bf6046d

src/openai/resources/audio/speech.py

@@ -72,7 +72,7 @@ def create(
 
           model:
               One of the available [TTS models](https://platform.openai.com/docs/models#tts):
-              `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
+              `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`.
 
           voice: The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
               `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, and
@@ -168,7 +168,7 @@ async def create(
 
           model:
               One of the available [TTS models](https://platform.openai.com/docs/models#tts):
-              `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
+              `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`.
 
           voice: The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
               `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, and

src/openai/resources/audio/transcriptions.py

@@ -91,8 +91,9 @@ def create(
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, and `whisper-1` (which is powered by our open source
-              Whisper V2 model).
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           chunking_strategy: Controls how the audio is cut into chunks. When set to `"auto"`, the server
               first normalizes loudness and then uses voice activity detection (VAD) to choose
@@ -102,8 +103,9 @@ def create(
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           language: The language of the input audio. Supplying the input language in
               [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`)
@@ -239,8 +241,9 @@ def create(
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           stream: If set to true, the model response data will be streamed to the client as it is
               generated using
@@ -261,9 +264,9 @@ def create(
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for
@@ -346,8 +349,9 @@ def create(
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           stream: If set to true, the model response data will be streamed to the client as it is
               generated using
@@ -368,9 +372,9 @@ def create(
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for
@@ -535,8 +539,9 @@ async def create(
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           chunking_strategy: Controls how the audio is cut into chunks. When set to `"auto"`, the server
               first normalizes loudness and then uses voice activity detection (VAD) to choose
@@ -548,9 +553,9 @@ async def create(
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for
@@ -679,8 +684,9 @@ async def create(
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           stream: If set to true, the model response data will be streamed to the client as it is
               generated using
@@ -701,9 +707,9 @@ async def create(
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for
@@ -786,8 +792,9 @@ async def create(
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           stream: If set to true, the model response data will be streamed to the client as it is
               generated using
@@ -808,9 +815,9 @@ async def create(
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for

src/openai/resources/realtime/calls.py

@@ -125,8 +125,10 @@ def accept(
                 "gpt-4o-mini-realtime-preview-2024-12-17",
                 "gpt-realtime-mini",
                 "gpt-realtime-mini-2025-10-06",
+                "gpt-realtime-mini-2025-12-15",
                 "gpt-audio-mini",
                 "gpt-audio-mini-2025-10-06",
+                "gpt-audio-mini-2025-12-15",
             ],
         ]
         | Omit = omit,
@@ -450,8 +452,10 @@ async def accept(
                 "gpt-4o-mini-realtime-preview-2024-12-17",
                 "gpt-realtime-mini",
                 "gpt-realtime-mini-2025-10-06",
+                "gpt-realtime-mini-2025-12-15",
                 "gpt-audio-mini",
                 "gpt-audio-mini-2025-10-06",
+                "gpt-audio-mini-2025-12-15",
             ],
         ]
         | Omit = omit,

src/openai/resources/videos.py

@@ -10,7 +10,6 @@
 from .. import _legacy_response
 from ..types import (
     VideoSize,
-    VideoModel,
     VideoSeconds,
     video_list_params,
     video_remix_params,
@@ -34,8 +33,8 @@
 from .._base_client import AsyncPaginator, make_request_options
 from .._utils._utils import is_given
 from ..types.video_size import VideoSize
-from ..types.video_model import VideoModel
 from ..types.video_seconds import VideoSeconds
+from ..types.video_model_param import VideoModelParam
 from ..types.video_delete_response import VideoDeleteResponse
 
 __all__ = ["Videos", "AsyncVideos"]
@@ -66,7 +65,7 @@ def create(
         *,
         prompt: str,
         input_reference: FileTypes | Omit = omit,
-        model: VideoModel | Omit = omit,
+        model: VideoModelParam | Omit = omit,
         seconds: VideoSeconds | Omit = omit,
         size: VideoSize | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -130,7 +129,7 @@ def create_and_poll(
         *,
         prompt: str,
         input_reference: FileTypes | Omit = omit,
-        model: VideoModel | Omit = omit,
+        model: VideoModelParam | Omit = omit,
         seconds: VideoSeconds | Omit = omit,
         size: VideoSize | Omit = omit,
         poll_interval_ms: int | Omit = omit,
@@ -421,7 +420,7 @@ async def create(
         *,
         prompt: str,
         input_reference: FileTypes | Omit = omit,
-        model: VideoModel | Omit = omit,
+        model: VideoModelParam | Omit = omit,
         seconds: VideoSeconds | Omit = omit,
         size: VideoSize | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -485,7 +484,7 @@ async def create_and_poll(
         *,
         prompt: str,
         input_reference: FileTypes | Omit = omit,
-        model: VideoModel | Omit = omit,
+        model: VideoModelParam | Omit = omit,
         seconds: VideoSeconds | Omit = omit,
         size: VideoSize | Omit = omit,
         poll_interval_ms: int | Omit = omit,

src/openai/types/__init__.py

@@ -53,6 +53,7 @@
 from .completion_choice import CompletionChoice as CompletionChoice
 from .image_edit_params import ImageEditParams as ImageEditParams
 from .video_list_params import VideoListParams as VideoListParams
+from .video_model_param import VideoModelParam as VideoModelParam
 from .eval_create_params import EvalCreateParams as EvalCreateParams
 from .eval_list_response import EvalListResponse as EvalListResponse
 from .eval_update_params import EvalUpdateParams as EvalUpdateParams

src/openai/types/audio/speech_create_params.py

@@ -17,7 +17,7 @@ class SpeechCreateParams(TypedDict, total=False):
     model: Required[Union[str, SpeechModel]]
     """
     One of the available [TTS models](https://platform.openai.com/docs/models#tts):
-    `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
+    `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`.
     """
 
     voice: Required[

src/openai/types/audio/speech_model.py

@@ -4,4 +4,4 @@
 
 __all__ = ["SpeechModel"]
 
-SpeechModel: TypeAlias = Literal["tts-1", "tts-1-hd", "gpt-4o-mini-tts"]
+SpeechModel: TypeAlias = Literal["tts-1", "tts-1-hd", "gpt-4o-mini-tts", "gpt-4o-mini-tts-2025-12-15"]

src/openai/types/audio/transcription_create_params.py

@@ -29,9 +29,9 @@ class TranscriptionCreateParamsBase(TypedDict, total=False):
     model: Required[Union[str, AudioModel]]
     """ID of the model to use.
 
-    The options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `whisper-1`
-    (which is powered by our open source Whisper V2 model), and
-    `gpt-4o-transcribe-diarize`.
+    The options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`,
+    `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1` (which is powered by our open
+    source Whisper V2 model), and `gpt-4o-transcribe-diarize`.
     """
 
     chunking_strategy: Optional[ChunkingStrategy]
@@ -49,9 +49,9 @@ class TranscriptionCreateParamsBase(TypedDict, total=False):
     Additional information to include in the transcription response. `logprobs` will
     return the log probabilities of the tokens in the response to understand the
     model's confidence in the transcription. `logprobs` only works with
-    response_format set to `json` and only with the models `gpt-4o-transcribe` and
-    `gpt-4o-mini-transcribe`. This field is not supported when using
-    `gpt-4o-transcribe-diarize`.
+    response_format set to `json` and only with the models `gpt-4o-transcribe`,
+    `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+    not supported when using `gpt-4o-transcribe-diarize`.
     """
 
     known_speaker_names: SequenceNotStr[str]

src/openai/types/audio_model.py

@@ -4,4 +4,10 @@
 
 __all__ = ["AudioModel"]
 
-AudioModel: TypeAlias = Literal["whisper-1", "gpt-4o-transcribe", "gpt-4o-mini-transcribe", "gpt-4o-transcribe-diarize"]
+AudioModel: TypeAlias = Literal[
+    "whisper-1",
+    "gpt-4o-transcribe",
+    "gpt-4o-mini-transcribe",
+    "gpt-4o-mini-transcribe-2025-12-15",
+    "gpt-4o-transcribe-diarize",
+]