fix(client): correct types for transcriptions / translations (#1757)

Author: stainless-app[bot]

Diff for: .stats.yml

@@ -1,2 +1,2 @@
 configured_endpoints: 68
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-17ddd746c775ca4d4fbe64e5621ac30756ef09c061ff6313190b6ec162222d4c.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-71e58a77027c67e003fdd1b1ac8ac11557d8bfabc7666d1a827c6b1ca8ab98b5.yml

Diff for: api.md

@@ -121,24 +121,30 @@ from openai.types import AudioModel, AudioResponseFormat
 Types:
 
 ```python
-from openai.types.audio import Transcription
+from openai.types.audio import (
+    Transcription,
+    TranscriptionSegment,
+    TranscriptionVerbose,
+    TranscriptionWord,
+    TranscriptionCreateResponse,
+)
 ```
 
 Methods:
 
-- <code title="post /audio/transcriptions">client.audio.transcriptions.<a href="./src/openai/resources/audio/transcriptions.py">create</a>(\*\*<a href="src/openai/types/audio/transcription_create_params.py">params</a>) -> <a href="./src/openai/types/audio/transcription.py">Transcription</a></code>
+- <code title="post /audio/transcriptions">client.audio.transcriptions.<a href="./src/openai/resources/audio/transcriptions.py">create</a>(\*\*<a href="src/openai/types/audio/transcription_create_params.py">params</a>) -> <a href="./src/openai/types/audio/transcription_create_response.py">TranscriptionCreateResponse</a></code>
 
 ## Translations
 
 Types:
 
 ```python
-from openai.types.audio import Translation
+from openai.types.audio import Translation, TranslationVerbose, TranslationCreateResponse
 ```
 
 Methods:
 
-- <code title="post /audio/translations">client.audio.translations.<a href="./src/openai/resources/audio/translations.py">create</a>(\*\*<a href="src/openai/types/audio/translation_create_params.py">params</a>) -> <a href="./src/openai/types/audio/translation.py">Translation</a></code>
+- <code title="post /audio/translations">client.audio.translations.<a href="./src/openai/resources/audio/translations.py">create</a>(\*\*<a href="src/openai/types/audio/translation_create_params.py">params</a>) -> <a href="./src/openai/types/audio/translation_create_response.py">TranslationCreateResponse</a></code>
 
 ## Speech
 

Diff for: src/openai/resources/audio/transcriptions.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from typing import List, Union, Mapping, cast
+from typing import Any, List, Union, Mapping, cast
 from typing_extensions import Literal
 
 import httpx
@@ -22,8 +22,8 @@
 from ...types.audio import transcription_create_params
 from ..._base_client import make_request_options
 from ...types.audio_model import AudioModel
-from ...types.audio.transcription import Transcription
 from ...types.audio_response_format import AudioResponseFormat
+from ...types.audio.transcription_create_response import TranscriptionCreateResponse
 
 __all__ = ["Transcriptions", "AsyncTranscriptions"]
 
@@ -64,7 +64,7 @@ def create(
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
-    ) -> Transcription:
+    ) -> TranscriptionCreateResponse:
         """
         Transcribes audio into the input language.
 
@@ -124,14 +124,19 @@ def create(
         # sent to the server will contain a `boundary` parameter, e.g.
         # multipart/form-data; boundary=---abc--
         extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
-        return self._post(
-            "/audio/transcriptions",
-            body=maybe_transform(body, transcription_create_params.TranscriptionCreateParams),
-            files=files,
-            options=make_request_options(
-                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+        return cast(
+            TranscriptionCreateResponse,
+            self._post(
+                "/audio/transcriptions",
+                body=maybe_transform(body, transcription_create_params.TranscriptionCreateParams),
+                files=files,
+                options=make_request_options(
+                    extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+                ),
+                cast_to=cast(
+                    Any, TranscriptionCreateResponse
+                ),  # Union types cannot be passed in as arguments in the type system
             ),
-            cast_to=Transcription,
         )
 
 
@@ -171,7 +176,7 @@ async def create(
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
-    ) -> Transcription:
+    ) -> TranscriptionCreateResponse:
         """
         Transcribes audio into the input language.
 
@@ -231,14 +236,19 @@ async def create(
         # sent to the server will contain a `boundary` parameter, e.g.
         # multipart/form-data; boundary=---abc--
         extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
-        return await self._post(
-            "/audio/transcriptions",
-            body=await async_maybe_transform(body, transcription_create_params.TranscriptionCreateParams),
-            files=files,
-            options=make_request_options(
-                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+        return cast(
+            TranscriptionCreateResponse,
+            await self._post(
+                "/audio/transcriptions",
+                body=await async_maybe_transform(body, transcription_create_params.TranscriptionCreateParams),
+                files=files,
+                options=make_request_options(
+                    extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+                ),
+                cast_to=cast(
+                    Any, TranscriptionCreateResponse
+                ),  # Union types cannot be passed in as arguments in the type system
             ),
-            cast_to=Transcription,
         )
 
 

Diff for: src/openai/resources/audio/translations.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from typing import Union, Mapping, cast
+from typing import Any, Union, Mapping, cast
 
 import httpx
 
@@ -21,8 +21,8 @@
 from ...types.audio import translation_create_params
 from ..._base_client import make_request_options
 from ...types.audio_model import AudioModel
-from ...types.audio.translation import Translation
 from ...types.audio_response_format import AudioResponseFormat
+from ...types.audio.translation_create_response import TranslationCreateResponse
 
 __all__ = ["Translations", "AsyncTranslations"]
 
@@ -61,7 +61,7 @@ def create(
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
-    ) -> Translation:
+    ) -> TranslationCreateResponse:
         """
         Translates audio into English.
 
@@ -108,14 +108,19 @@ def create(
         # sent to the server will contain a `boundary` parameter, e.g.
         # multipart/form-data; boundary=---abc--
         extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
-        return self._post(
-            "/audio/translations",
-            body=maybe_transform(body, translation_create_params.TranslationCreateParams),
-            files=files,
-            options=make_request_options(
-                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+        return cast(
+            TranslationCreateResponse,
+            self._post(
+                "/audio/translations",
+                body=maybe_transform(body, translation_create_params.TranslationCreateParams),
+                files=files,
+                options=make_request_options(
+                    extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+                ),
+                cast_to=cast(
+                    Any, TranslationCreateResponse
+                ),  # Union types cannot be passed in as arguments in the type system
             ),
-            cast_to=Translation,
         )
 
 
@@ -153,7 +158,7 @@ async def create(
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
-    ) -> Translation:
+    ) -> TranslationCreateResponse:
         """
         Translates audio into English.
 
@@ -200,14 +205,19 @@ async def create(
         # sent to the server will contain a `boundary` parameter, e.g.
         # multipart/form-data; boundary=---abc--
         extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
-        return await self._post(
-            "/audio/translations",
-            body=await async_maybe_transform(body, translation_create_params.TranslationCreateParams),
-            files=files,
-            options=make_request_options(
-                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+        return cast(
+            TranslationCreateResponse,
+            await self._post(
+                "/audio/translations",
+                body=await async_maybe_transform(body, translation_create_params.TranslationCreateParams),
+                files=files,
+                options=make_request_options(
+                    extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+                ),
+                cast_to=cast(
+                    Any, TranslationCreateResponse
+                ),  # Union types cannot be passed in as arguments in the type system
             ),
-            cast_to=Translation,
         )
 
 

Diff for: src/openai/types/audio/__init__.py

@@ -5,6 +5,12 @@
 from .translation import Translation as Translation
 from .speech_model import SpeechModel as SpeechModel
 from .transcription import Transcription as Transcription
+from .transcription_word import TranscriptionWord as TranscriptionWord
+from .translation_verbose import TranslationVerbose as TranslationVerbose
 from .speech_create_params import SpeechCreateParams as SpeechCreateParams
+from .transcription_segment import TranscriptionSegment as TranscriptionSegment
+from .transcription_verbose import TranscriptionVerbose as TranscriptionVerbose
 from .translation_create_params import TranslationCreateParams as TranslationCreateParams
 from .transcription_create_params import TranscriptionCreateParams as TranscriptionCreateParams
+from .translation_create_response import TranslationCreateResponse as TranslationCreateResponse
+from .transcription_create_response import TranscriptionCreateResponse as TranscriptionCreateResponse

Diff for: src/openai/types/audio/transcription_create_response.py

@@ -0,0 +1,11 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Union
+from typing_extensions import TypeAlias
+
+from .transcription import Transcription
+from .transcription_verbose import TranscriptionVerbose
+
+__all__ = ["TranscriptionCreateResponse"]
+
+TranscriptionCreateResponse: TypeAlias = Union[Transcription, TranscriptionVerbose]

Diff for: src/openai/types/audio/transcription_segment.py

@@ -0,0 +1,49 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List
+
+from ..._models import BaseModel
+
+__all__ = ["TranscriptionSegment"]
+
+
+class TranscriptionSegment(BaseModel):
+    id: int
+    """Unique identifier of the segment."""
+
+    avg_logprob: float
+    """Average logprob of the segment.
+
+    If the value is lower than -1, consider the logprobs failed.
+    """
+
+    compression_ratio: float
+    """Compression ratio of the segment.
+
+    If the value is greater than 2.4, consider the compression failed.
+    """
+
+    end: float
+    """End time of the segment in seconds."""
+
+    no_speech_prob: float
+    """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.
+    """
+
+    seek: int
+    """Seek offset of the segment."""
+
+    start: float
+    """Start time of the segment in seconds."""
+
+    temperature: float
+    """Temperature parameter used for generating the segment."""
+
+    text: str
+    """Text content of the segment."""
+
+    tokens: List[int]
+    """Array of token IDs for the text content."""

Diff for: src/openai/types/audio/transcription_verbose.py

@@ -0,0 +1,26 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+
+from ..._models import BaseModel
+from .transcription_word import TranscriptionWord
+from .transcription_segment import TranscriptionSegment
+
+__all__ = ["TranscriptionVerbose"]
+
+
+class TranscriptionVerbose(BaseModel):
+    duration: str
+    """The duration of the input audio."""
+
+    language: str
+    """The language of the input audio."""
+
+    text: str
+    """The transcribed text."""
+
+    segments: Optional[List[TranscriptionSegment]] = None
+    """Segments of the transcribed text and their corresponding details."""
+
+    words: Optional[List[TranscriptionWord]] = None
+    """Extracted words and their corresponding timestamps."""

Diff for: src/openai/types/audio/transcription_word.py

@@ -0,0 +1,18 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+
+
+from ..._models import BaseModel
+
+__all__ = ["TranscriptionWord"]
+
+
+class TranscriptionWord(BaseModel):
+    end: float
+    """End time of the word in seconds."""
+
+    start: float
+    """Start time of the word in seconds."""
+
+    word: str
+    """The text content of the word."""

Diff for: src/openai/types/audio/translation_create_response.py

@@ -0,0 +1,11 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Union
+from typing_extensions import TypeAlias
+
+from .translation import Translation
+from .translation_verbose import TranslationVerbose
+
+__all__ = ["TranslationCreateResponse"]
+
+TranslationCreateResponse: TypeAlias = Union[Translation, TranslationVerbose]

Diff for: src/openai/types/audio/translation_verbose.py

@@ -0,0 +1,22 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List, Optional
+
+from ..._models import BaseModel
+from .transcription_segment import TranscriptionSegment
+
+__all__ = ["TranslationVerbose"]
+
+
+class TranslationVerbose(BaseModel):
+    duration: str
+    """The duration of the input audio."""
+
+    language: str
+    """The language of the output translation (always `english`)."""
+
+    text: str
+    """The translated text."""
+
+    segments: Optional[List[TranscriptionSegment]] = None
+    """Segments of the translated text and their corresponding details."""