chore: 添加虚拟环境到仓库

- 添加 backend_service/venv 虚拟环境
- 包含所有Python依赖包
- 注意：虚拟环境约393MB，包含12655个文件

backend_service/venv/lib/python3.13/site-packages/openai/resources/audio/__init__.py

@@ -0,0 +1,61 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .audio import (
+    Audio,
+    AsyncAudio,
+    AudioWithRawResponse,
+    AsyncAudioWithRawResponse,
+    AudioWithStreamingResponse,
+    AsyncAudioWithStreamingResponse,
+)
+from .speech import (
+    Speech,
+    AsyncSpeech,
+    SpeechWithRawResponse,
+    AsyncSpeechWithRawResponse,
+    SpeechWithStreamingResponse,
+    AsyncSpeechWithStreamingResponse,
+)
+from .translations import (
+    Translations,
+    AsyncTranslations,
+    TranslationsWithRawResponse,
+    AsyncTranslationsWithRawResponse,
+    TranslationsWithStreamingResponse,
+    AsyncTranslationsWithStreamingResponse,
+)
+from .transcriptions import (
+    Transcriptions,
+    AsyncTranscriptions,
+    TranscriptionsWithRawResponse,
+    AsyncTranscriptionsWithRawResponse,
+    TranscriptionsWithStreamingResponse,
+    AsyncTranscriptionsWithStreamingResponse,
+)
+
+__all__ = [
+    "Transcriptions",
+    "AsyncTranscriptions",
+    "TranscriptionsWithRawResponse",
+    "AsyncTranscriptionsWithRawResponse",
+    "TranscriptionsWithStreamingResponse",
+    "AsyncTranscriptionsWithStreamingResponse",
+    "Translations",
+    "AsyncTranslations",
+    "TranslationsWithRawResponse",
+    "AsyncTranslationsWithRawResponse",
+    "TranslationsWithStreamingResponse",
+    "AsyncTranslationsWithStreamingResponse",
+    "Speech",
+    "AsyncSpeech",
+    "SpeechWithRawResponse",
+    "AsyncSpeechWithRawResponse",
+    "SpeechWithStreamingResponse",
+    "AsyncSpeechWithStreamingResponse",
+    "Audio",
+    "AsyncAudio",
+    "AudioWithRawResponse",
+    "AsyncAudioWithRawResponse",
+    "AudioWithStreamingResponse",
+    "AsyncAudioWithStreamingResponse",
+]

backend_service/venv/lib/python3.13/site-packages/openai/resources/audio/audio.py

@@ -0,0 +1,166 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .speech import (
+    Speech,
+    AsyncSpeech,
+    SpeechWithRawResponse,
+    AsyncSpeechWithRawResponse,
+    SpeechWithStreamingResponse,
+    AsyncSpeechWithStreamingResponse,
+)
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from .translations import (
+    Translations,
+    AsyncTranslations,
+    TranslationsWithRawResponse,
+    AsyncTranslationsWithRawResponse,
+    TranslationsWithStreamingResponse,
+    AsyncTranslationsWithStreamingResponse,
+)
+from .transcriptions import (
+    Transcriptions,
+    AsyncTranscriptions,
+    TranscriptionsWithRawResponse,
+    AsyncTranscriptionsWithRawResponse,
+    TranscriptionsWithStreamingResponse,
+    AsyncTranscriptionsWithStreamingResponse,
+)
+
+__all__ = ["Audio", "AsyncAudio"]
+
+
+class Audio(SyncAPIResource):
+    @cached_property
+    def transcriptions(self) -> Transcriptions:
+        return Transcriptions(self._client)
+
+    @cached_property
+    def translations(self) -> Translations:
+        return Translations(self._client)
+
+    @cached_property
+    def speech(self) -> Speech:
+        return Speech(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AudioWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return AudioWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AudioWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return AudioWithStreamingResponse(self)
+
+
+class AsyncAudio(AsyncAPIResource):
+    @cached_property
+    def transcriptions(self) -> AsyncTranscriptions:
+        return AsyncTranscriptions(self._client)
+
+    @cached_property
+    def translations(self) -> AsyncTranslations:
+        return AsyncTranslations(self._client)
+
+    @cached_property
+    def speech(self) -> AsyncSpeech:
+        return AsyncSpeech(self._client)
+
+    @cached_property
+    def with_raw_response(self) -> AsyncAudioWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncAudioWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncAudioWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return AsyncAudioWithStreamingResponse(self)
+
+
+class AudioWithRawResponse:
+    def __init__(self, audio: Audio) -> None:
+        self._audio = audio
+
+    @cached_property
+    def transcriptions(self) -> TranscriptionsWithRawResponse:
+        return TranscriptionsWithRawResponse(self._audio.transcriptions)
+
+    @cached_property
+    def translations(self) -> TranslationsWithRawResponse:
+        return TranslationsWithRawResponse(self._audio.translations)
+
+    @cached_property
+    def speech(self) -> SpeechWithRawResponse:
+        return SpeechWithRawResponse(self._audio.speech)
+
+
+class AsyncAudioWithRawResponse:
+    def __init__(self, audio: AsyncAudio) -> None:
+        self._audio = audio
+
+    @cached_property
+    def transcriptions(self) -> AsyncTranscriptionsWithRawResponse:
+        return AsyncTranscriptionsWithRawResponse(self._audio.transcriptions)
+
+    @cached_property
+    def translations(self) -> AsyncTranslationsWithRawResponse:
+        return AsyncTranslationsWithRawResponse(self._audio.translations)
+
+    @cached_property
+    def speech(self) -> AsyncSpeechWithRawResponse:
+        return AsyncSpeechWithRawResponse(self._audio.speech)
+
+
+class AudioWithStreamingResponse:
+    def __init__(self, audio: Audio) -> None:
+        self._audio = audio
+
+    @cached_property
+    def transcriptions(self) -> TranscriptionsWithStreamingResponse:
+        return TranscriptionsWithStreamingResponse(self._audio.transcriptions)
+
+    @cached_property
+    def translations(self) -> TranslationsWithStreamingResponse:
+        return TranslationsWithStreamingResponse(self._audio.translations)
+
+    @cached_property
+    def speech(self) -> SpeechWithStreamingResponse:
+        return SpeechWithStreamingResponse(self._audio.speech)
+
+
+class AsyncAudioWithStreamingResponse:
+    def __init__(self, audio: AsyncAudio) -> None:
+        self._audio = audio
+
+    @cached_property
+    def transcriptions(self) -> AsyncTranscriptionsWithStreamingResponse:
+        return AsyncTranscriptionsWithStreamingResponse(self._audio.transcriptions)
+
+    @cached_property
+    def translations(self) -> AsyncTranslationsWithStreamingResponse:
+        return AsyncTranslationsWithStreamingResponse(self._audio.translations)
+
+    @cached_property
+    def speech(self) -> AsyncSpeechWithStreamingResponse:
+        return AsyncSpeechWithStreamingResponse(self._audio.speech)

backend_service/venv/lib/python3.13/site-packages/openai/resources/audio/speech.py

@@ -0,0 +1,255 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union
+from typing_extensions import Literal
+
+import httpx
+
+from ... import _legacy_response
+from ..._types import Body, Omit, Query, Headers, NotGiven, omit, not_given
+from ..._utils import maybe_transform, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import (
+    StreamedBinaryAPIResponse,
+    AsyncStreamedBinaryAPIResponse,
+    to_custom_streamed_response_wrapper,
+    async_to_custom_streamed_response_wrapper,
+)
+from ...types.audio import speech_create_params
+from ..._base_client import make_request_options
+from ...types.audio.speech_model import SpeechModel
+
+__all__ = ["Speech", "AsyncSpeech"]
+
+
+class Speech(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> SpeechWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return SpeechWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> SpeechWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return SpeechWithStreamingResponse(self)
+
+    def create(
+        self,
+        *,
+        input: str,
+        model: Union[str, SpeechModel],
+        voice: Union[
+            str, Literal["alloy", "ash", "ballad", "coral", "echo", "sage", "shimmer", "verse", "marin", "cedar"]
+        ],
+        instructions: str | Omit = omit,
+        response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"] | Omit = omit,
+        speed: float | Omit = omit,
+        stream_format: Literal["sse", "audio"] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> _legacy_response.HttpxBinaryResponseContent:
+        """
+        Generates audio from the input text.
+
+        Args:
+          input: The text to generate audio for. The maximum length is 4096 characters.
+
+          model:
+              One of the available [TTS models](https://platform.openai.com/docs/models#tts):
+              `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
+
+          voice: The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
+              `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, and
+              `verse`. Previews of the voices are available in the
+              [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
+
+          instructions: Control the voice of your generated audio with additional instructions. Does not
+              work with `tts-1` or `tts-1-hd`.
+
+          response_format: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`,
+              `wav`, and `pcm`.
+
+          speed: The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is
+              the default.
+
+          stream_format: The format to stream the audio in. Supported formats are `sse` and `audio`.
+              `sse` is not supported for `tts-1` or `tts-1-hd`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        extra_headers = {"Accept": "application/octet-stream", **(extra_headers or {})}
+        return self._post(
+            "/audio/speech",
+            body=maybe_transform(
+                {
+                    "input": input,
+                    "model": model,
+                    "voice": voice,
+                    "instructions": instructions,
+                    "response_format": response_format,
+                    "speed": speed,
+                    "stream_format": stream_format,
+                },
+                speech_create_params.SpeechCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=_legacy_response.HttpxBinaryResponseContent,
+        )
+
+
+class AsyncSpeech(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncSpeechWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncSpeechWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncSpeechWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return AsyncSpeechWithStreamingResponse(self)
+
+    async def create(
+        self,
+        *,
+        input: str,
+        model: Union[str, SpeechModel],
+        voice: Union[
+            str, Literal["alloy", "ash", "ballad", "coral", "echo", "sage", "shimmer", "verse", "marin", "cedar"]
+        ],
+        instructions: str | Omit = omit,
+        response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"] | Omit = omit,
+        speed: float | Omit = omit,
+        stream_format: Literal["sse", "audio"] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> _legacy_response.HttpxBinaryResponseContent:
+        """
+        Generates audio from the input text.
+
+        Args:
+          input: The text to generate audio for. The maximum length is 4096 characters.
+
+          model:
+              One of the available [TTS models](https://platform.openai.com/docs/models#tts):
+              `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
+
+          voice: The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
+              `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, and
+              `verse`. Previews of the voices are available in the
+              [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
+
+          instructions: Control the voice of your generated audio with additional instructions. Does not
+              work with `tts-1` or `tts-1-hd`.
+
+          response_format: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`,
+              `wav`, and `pcm`.
+
+          speed: The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is
+              the default.
+
+          stream_format: The format to stream the audio in. Supported formats are `sse` and `audio`.
+              `sse` is not supported for `tts-1` or `tts-1-hd`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        extra_headers = {"Accept": "application/octet-stream", **(extra_headers or {})}
+        return await self._post(
+            "/audio/speech",
+            body=await async_maybe_transform(
+                {
+                    "input": input,
+                    "model": model,
+                    "voice": voice,
+                    "instructions": instructions,
+                    "response_format": response_format,
+                    "speed": speed,
+                    "stream_format": stream_format,
+                },
+                speech_create_params.SpeechCreateParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=_legacy_response.HttpxBinaryResponseContent,
+        )
+
+
+class SpeechWithRawResponse:
+    def __init__(self, speech: Speech) -> None:
+        self._speech = speech
+
+        self.create = _legacy_response.to_raw_response_wrapper(
+            speech.create,
+        )
+
+
+class AsyncSpeechWithRawResponse:
+    def __init__(self, speech: AsyncSpeech) -> None:
+        self._speech = speech
+
+        self.create = _legacy_response.async_to_raw_response_wrapper(
+            speech.create,
+        )
+
+
+class SpeechWithStreamingResponse:
+    def __init__(self, speech: Speech) -> None:
+        self._speech = speech
+
+        self.create = to_custom_streamed_response_wrapper(
+            speech.create,
+            StreamedBinaryAPIResponse,
+        )
+
+
+class AsyncSpeechWithStreamingResponse:
+    def __init__(self, speech: AsyncSpeech) -> None:
+        self._speech = speech
+
+        self.create = async_to_custom_streamed_response_wrapper(
+            speech.create,
+            AsyncStreamedBinaryAPIResponse,
+        )

backend_service/venv/lib/python3.13/site-packages/openai/resources/audio/transcriptions.py

@@ -0,0 +1,980 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING, List, Union, Mapping, Optional, cast
+from typing_extensions import Literal, overload, assert_never
+
+import httpx
+
+from ... import _legacy_response
+from ..._types import (
+    Body,
+    Omit,
+    Query,
+    Headers,
+    NotGiven,
+    FileTypes,
+    SequenceNotStr,
+    omit,
+    not_given,
+)
+from ..._utils import extract_files, required_args, maybe_transform, deepcopy_minimal, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import to_streamed_response_wrapper, async_to_streamed_response_wrapper
+from ..._streaming import Stream, AsyncStream
+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_include import TranscriptionInclude
+from ...types.audio.transcription_verbose import TranscriptionVerbose
+from ...types.audio.transcription_diarized import TranscriptionDiarized
+from ...types.audio.transcription_stream_event import TranscriptionStreamEvent
+from ...types.audio.transcription_create_response import TranscriptionCreateResponse
+
+__all__ = ["Transcriptions", "AsyncTranscriptions"]
+
+log: logging.Logger = logging.getLogger("openai.audio.transcriptions")
+
+
+class Transcriptions(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> TranscriptionsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return TranscriptionsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> TranscriptionsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return TranscriptionsWithStreamingResponse(self)
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        response_format: Union[Literal["json"], Omit] = omit,
+        stream: Optional[Literal[False]] | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> Transcription:
+        """
+        Transcribes audio into the input language.
+
+        Args:
+          file:
+              The audio file object (not file name) to transcribe, in one of these formats:
+              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).
+
+          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
+              boundaries. `server_vad` object can be provided to tweak VAD detection
+              parameters manually. If unset, the audio is transcribed as a single block.
+
+          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`.
+
+          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`)
+              format will improve accuracy and latency.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+              should match the audio language.
+
+          response_format: 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`.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+              for more information.
+
+              Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+
+          temperature: 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.
+
+          timestamp_granularities: The timestamp granularities to populate for this transcription.
+              `response_format` must be set `verbose_json` to use timestamp granularities.
+              Either or both of these options are supported: `word`, or `segment`. Note: There
+              is no additional latency for segment timestamps, but generating word timestamps
+              incurs additional latency.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+        """
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        response_format: Literal["verbose_json"],
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> TranscriptionVerbose: ...
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        response_format: Literal["text", "srt", "vtt"],
+        include: List[TranscriptionInclude] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> str: ...
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        response_format: Literal["diarized_json"],
+        known_speaker_names: SequenceNotStr[str] | Omit = omit,
+        known_speaker_references: SequenceNotStr[str] | Omit = omit,
+        language: str | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> TranscriptionDiarized: ...
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        stream: Literal[True],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        known_speaker_names: SequenceNotStr[str] | Omit = omit,
+        known_speaker_references: SequenceNotStr[str] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        response_format: Union[AudioResponseFormat, Omit] = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> Stream[TranscriptionStreamEvent]:
+        """
+        Transcribes audio into the input language.
+
+        Args:
+          file:
+              The audio file object (not file name) to transcribe, in one of these formats:
+              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`.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+              for more information.
+
+              Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+
+          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
+              boundaries. `server_vad` object can be provided to tweak VAD detection
+              parameters manually. If unset, the audio is transcribed as a single block.
+              Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30
+              seconds.
+
+          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`.
+
+          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
+              example `customer` or `agent`). Up to 4 speakers are supported.
+
+          known_speaker_references: Optional list of audio samples (as
+              [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+              that contain known speaker references matching `known_speaker_names[]`. Each
+              sample must be between 2 and 10 seconds, and can use any of the same input audio
+              formats supported by `file`.
+
+          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`)
+              format will improve accuracy and latency.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+              should match the audio language. This field is not supported when using
+              `gpt-4o-transcribe-diarize`.
+
+          response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
+              `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.
+
+          temperature: 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.
+
+          timestamp_granularities: The timestamp granularities to populate for this transcription.
+              `response_format` must be set `verbose_json` to use timestamp granularities.
+              Either or both of these options are supported: `word`, or `segment`. Note: There
+              is no additional latency for segment timestamps, but generating word timestamps
+              incurs additional latency. This option is not available for
+              `gpt-4o-transcribe-diarize`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        stream: bool,
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        known_speaker_names: SequenceNotStr[str] | Omit = omit,
+        known_speaker_references: SequenceNotStr[str] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        response_format: Union[AudioResponseFormat, Omit] = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> TranscriptionCreateResponse | Stream[TranscriptionStreamEvent]:
+        """
+        Transcribes audio into the input language.
+
+        Args:
+          file:
+              The audio file object (not file name) to transcribe, in one of these formats:
+              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`.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+              for more information.
+
+              Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+
+          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
+              boundaries. `server_vad` object can be provided to tweak VAD detection
+              parameters manually. If unset, the audio is transcribed as a single block.
+              Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30
+              seconds.
+
+          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`.
+
+          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
+              example `customer` or `agent`). Up to 4 speakers are supported.
+
+          known_speaker_references: Optional list of audio samples (as
+              [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+              that contain known speaker references matching `known_speaker_names[]`. Each
+              sample must be between 2 and 10 seconds, and can use any of the same input audio
+              formats supported by `file`.
+
+          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`)
+              format will improve accuracy and latency.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+              should match the audio language. This field is not supported when using
+              `gpt-4o-transcribe-diarize`.
+
+          response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
+              `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.
+
+          temperature: 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.
+
+          timestamp_granularities: The timestamp granularities to populate for this transcription.
+              `response_format` must be set `verbose_json` to use timestamp granularities.
+              Either or both of these options are supported: `word`, or `segment`. Note: There
+              is no additional latency for segment timestamps, but generating word timestamps
+              incurs additional latency. This option is not available for
+              `gpt-4o-transcribe-diarize`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @required_args(["file", "model"], ["file", "model", "stream"])
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        known_speaker_names: SequenceNotStr[str] | Omit = omit,
+        known_speaker_references: SequenceNotStr[str] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        response_format: Union[AudioResponseFormat, Omit] = omit,
+        stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> str | Transcription | TranscriptionDiarized | TranscriptionVerbose | Stream[TranscriptionStreamEvent]:
+        body = deepcopy_minimal(
+            {
+                "file": file,
+                "model": model,
+                "chunking_strategy": chunking_strategy,
+                "include": include,
+                "known_speaker_names": known_speaker_names,
+                "known_speaker_references": known_speaker_references,
+                "language": language,
+                "prompt": prompt,
+                "response_format": response_format,
+                "stream": stream,
+                "temperature": temperature,
+                "timestamp_granularities": timestamp_granularities,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # 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(  # type: ignore[return-value]
+            "/audio/transcriptions",
+            body=maybe_transform(
+                body,
+                transcription_create_params.TranscriptionCreateParamsStreaming
+                if stream
+                else transcription_create_params.TranscriptionCreateParamsNonStreaming,
+            ),
+            files=files,
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=_get_response_format_type(response_format),
+            stream=stream or False,
+            stream_cls=Stream[TranscriptionStreamEvent],
+        )
+
+
+class AsyncTranscriptions(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncTranscriptionsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncTranscriptionsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncTranscriptionsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return AsyncTranscriptionsWithStreamingResponse(self)
+
+    @overload
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        known_speaker_names: SequenceNotStr[str] | Omit = omit,
+        known_speaker_references: SequenceNotStr[str] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        response_format: Union[Literal["json"], Omit] = omit,
+        stream: Optional[Literal[False]] | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> TranscriptionCreateResponse:
+        """
+        Transcribes audio into the input language.
+
+        Args:
+          file:
+              The audio file object (not file name) to transcribe, in one of these formats:
+              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`.
+
+          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
+              boundaries. `server_vad` object can be provided to tweak VAD detection
+              parameters manually. If unset, the audio is transcribed as a single block.
+              Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30
+              seconds.
+
+          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`.
+
+          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
+              example `customer` or `agent`). Up to 4 speakers are supported.
+
+          known_speaker_references: Optional list of audio samples (as
+              [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+              that contain known speaker references matching `known_speaker_names[]`. Each
+              sample must be between 2 and 10 seconds, and can use any of the same input audio
+              formats supported by `file`.
+
+          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`)
+              format will improve accuracy and latency.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+              should match the audio language. This field is not supported when using
+              `gpt-4o-transcribe-diarize`.
+
+          response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
+              `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.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+              for more information.
+
+              Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+
+          temperature: 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.
+
+          timestamp_granularities: The timestamp granularities to populate for this transcription.
+              `response_format` must be set `verbose_json` to use timestamp granularities.
+              Either or both of these options are supported: `word`, or `segment`. Note: There
+              is no additional latency for segment timestamps, but generating word timestamps
+              incurs additional latency. This option is not available for
+              `gpt-4o-transcribe-diarize`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+        """
+
+    @overload
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        response_format: Literal["verbose_json"],
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> TranscriptionVerbose: ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        response_format: Literal["text", "srt", "vtt"],
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> str: ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        stream: Literal[True],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        known_speaker_names: SequenceNotStr[str] | Omit = omit,
+        known_speaker_references: SequenceNotStr[str] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        response_format: Union[AudioResponseFormat, Omit] = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> AsyncStream[TranscriptionStreamEvent]:
+        """
+        Transcribes audio into the input language.
+
+        Args:
+          file:
+              The audio file object (not file name) to transcribe, in one of these formats:
+              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`.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+              for more information.
+
+              Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+
+          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
+              boundaries. `server_vad` object can be provided to tweak VAD detection
+              parameters manually. If unset, the audio is transcribed as a single block.
+              Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30
+              seconds.
+
+          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`.
+
+          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
+              example `customer` or `agent`). Up to 4 speakers are supported.
+
+          known_speaker_references: Optional list of audio samples (as
+              [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+              that contain known speaker references matching `known_speaker_names[]`. Each
+              sample must be between 2 and 10 seconds, and can use any of the same input audio
+              formats supported by `file`.
+
+          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`)
+              format will improve accuracy and latency.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+              should match the audio language. This field is not supported when using
+              `gpt-4o-transcribe-diarize`.
+
+          response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
+              `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.
+
+          temperature: 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.
+
+          timestamp_granularities: The timestamp granularities to populate for this transcription.
+              `response_format` must be set `verbose_json` to use timestamp granularities.
+              Either or both of these options are supported: `word`, or `segment`. Note: There
+              is no additional latency for segment timestamps, but generating word timestamps
+              incurs additional latency. This option is not available for
+              `gpt-4o-transcribe-diarize`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        stream: bool,
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        known_speaker_names: SequenceNotStr[str] | Omit = omit,
+        known_speaker_references: SequenceNotStr[str] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        response_format: Union[AudioResponseFormat, Omit] = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> TranscriptionCreateResponse | AsyncStream[TranscriptionStreamEvent]:
+        """
+        Transcribes audio into the input language.
+
+        Args:
+          file:
+              The audio file object (not file name) to transcribe, in one of these formats:
+              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`.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using
+              [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+              See the
+              [Streaming section of the Speech-to-Text guide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
+              for more information.
+
+              Note: Streaming is not supported for the `whisper-1` model and will be ignored.
+
+          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
+              boundaries. `server_vad` object can be provided to tweak VAD detection
+              parameters manually. If unset, the audio is transcribed as a single block.
+              Required when using `gpt-4o-transcribe-diarize` for inputs longer than 30
+              seconds.
+
+          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`.
+
+          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
+              example `customer` or `agent`). Up to 4 speakers are supported.
+
+          known_speaker_references: Optional list of audio samples (as
+              [data URLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
+              that contain known speaker references matching `known_speaker_names[]`. Each
+              sample must be between 2 and 10 seconds, and can use any of the same input audio
+              formats supported by `file`.
+
+          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`)
+              format will improve accuracy and latency.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+              should match the audio language. This field is not supported when using
+              `gpt-4o-transcribe-diarize`.
+
+          response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
+              `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.
+
+          temperature: 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.
+
+          timestamp_granularities: The timestamp granularities to populate for this transcription.
+              `response_format` must be set `verbose_json` to use timestamp granularities.
+              Either or both of these options are supported: `word`, or `segment`. Note: There
+              is no additional latency for segment timestamps, but generating word timestamps
+              incurs additional latency. This option is not available for
+              `gpt-4o-transcribe-diarize`.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        ...
+
+    @required_args(["file", "model"], ["file", "model", "stream"])
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        chunking_strategy: Optional[transcription_create_params.ChunkingStrategy] | Omit = omit,
+        include: List[TranscriptionInclude] | Omit = omit,
+        known_speaker_names: SequenceNotStr[str] | Omit = omit,
+        known_speaker_references: SequenceNotStr[str] | Omit = omit,
+        language: str | Omit = omit,
+        prompt: str | Omit = omit,
+        response_format: Union[AudioResponseFormat, Omit] = omit,
+        stream: Optional[Literal[False]] | Literal[True] | Omit = omit,
+        temperature: float | Omit = omit,
+        timestamp_granularities: List[Literal["word", "segment"]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> Transcription | TranscriptionVerbose | TranscriptionDiarized | str | AsyncStream[TranscriptionStreamEvent]:
+        body = deepcopy_minimal(
+            {
+                "file": file,
+                "model": model,
+                "chunking_strategy": chunking_strategy,
+                "include": include,
+                "known_speaker_names": known_speaker_names,
+                "known_speaker_references": known_speaker_references,
+                "language": language,
+                "prompt": prompt,
+                "response_format": response_format,
+                "stream": stream,
+                "temperature": temperature,
+                "timestamp_granularities": timestamp_granularities,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # 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.TranscriptionCreateParamsStreaming
+                if stream
+                else transcription_create_params.TranscriptionCreateParamsNonStreaming,
+            ),
+            files=files,
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=_get_response_format_type(response_format),
+            stream=stream or False,
+            stream_cls=AsyncStream[TranscriptionStreamEvent],
+        )
+
+
+class TranscriptionsWithRawResponse:
+    def __init__(self, transcriptions: Transcriptions) -> None:
+        self._transcriptions = transcriptions
+
+        self.create = _legacy_response.to_raw_response_wrapper(
+            transcriptions.create,
+        )
+
+
+class AsyncTranscriptionsWithRawResponse:
+    def __init__(self, transcriptions: AsyncTranscriptions) -> None:
+        self._transcriptions = transcriptions
+
+        self.create = _legacy_response.async_to_raw_response_wrapper(
+            transcriptions.create,
+        )
+
+
+class TranscriptionsWithStreamingResponse:
+    def __init__(self, transcriptions: Transcriptions) -> None:
+        self._transcriptions = transcriptions
+
+        self.create = to_streamed_response_wrapper(
+            transcriptions.create,
+        )
+
+
+class AsyncTranscriptionsWithStreamingResponse:
+    def __init__(self, transcriptions: AsyncTranscriptions) -> None:
+        self._transcriptions = transcriptions
+
+        self.create = async_to_streamed_response_wrapper(
+            transcriptions.create,
+        )
+
+
+def _get_response_format_type(
+    response_format: AudioResponseFormat | Omit,
+) -> type[Transcription | TranscriptionVerbose | TranscriptionDiarized | str]:
+    if isinstance(response_format, Omit) or response_format is None:  # pyright: ignore[reportUnnecessaryComparison]
+        return Transcription
+
+    if response_format == "json":
+        return Transcription
+    elif response_format == "verbose_json":
+        return TranscriptionVerbose
+    elif response_format == "diarized_json":
+        return TranscriptionDiarized
+    elif response_format == "srt" or response_format == "text" or response_format == "vtt":
+        return str
+    elif TYPE_CHECKING:  # type: ignore[unreachable]
+        assert_never(response_format)
+    else:
+        log.warn("Unexpected audio response format: %s", response_format)
+        return Transcription

backend_service/venv/lib/python3.13/site-packages/openai/resources/audio/translations.py

@@ -0,0 +1,367 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING, Union, Mapping, cast
+from typing_extensions import Literal, overload, assert_never
+
+import httpx
+
+from ... import _legacy_response
+from ..._types import Body, Omit, Query, Headers, NotGiven, FileTypes, omit, not_given
+from ..._utils import extract_files, maybe_transform, deepcopy_minimal, async_maybe_transform
+from ..._compat import cached_property
+from ..._resource import SyncAPIResource, AsyncAPIResource
+from ..._response import to_streamed_response_wrapper, async_to_streamed_response_wrapper
+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_verbose import TranslationVerbose
+
+__all__ = ["Translations", "AsyncTranslations"]
+
+log: logging.Logger = logging.getLogger("openai.audio.transcriptions")
+
+
+class Translations(SyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> TranslationsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return TranslationsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> TranslationsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return TranslationsWithStreamingResponse(self)
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        response_format: Union[Literal["json"], Omit] = omit,
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> Translation: ...
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        response_format: Literal["verbose_json"],
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> TranslationVerbose: ...
+
+    @overload
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        response_format: Literal["text", "srt", "vtt"],
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> str: ...
+
+    def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        prompt: str | Omit = omit,
+        response_format: Union[Literal["json", "text", "srt", "verbose_json", "vtt"], Omit] = omit,
+        temperature: float | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> Translation | TranslationVerbose | str:
+        """
+        Translates audio into English.
+
+        Args:
+          file: The audio file object (not file name) translate, in one of these formats: flac,
+              mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
+
+          model: ID of the model to use. Only `whisper-1` (which is powered by our open source
+              Whisper V2 model) is currently available.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+              should be in English.
+
+          response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
+              `verbose_json`, or `vtt`.
+
+          temperature: 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.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        body = deepcopy_minimal(
+            {
+                "file": file,
+                "model": model,
+                "prompt": prompt,
+                "response_format": response_format,
+                "temperature": temperature,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # 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(  # type: ignore[return-value]
+            "/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=_get_response_format_type(response_format),
+        )
+
+
+class AsyncTranslations(AsyncAPIResource):
+    @cached_property
+    def with_raw_response(self) -> AsyncTranslationsWithRawResponse:
+        """
+        This property can be used as a prefix for any HTTP method call to return
+        the raw response object instead of the parsed content.
+
+        For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
+        """
+        return AsyncTranslationsWithRawResponse(self)
+
+    @cached_property
+    def with_streaming_response(self) -> AsyncTranslationsWithStreamingResponse:
+        """
+        An alternative to `.with_raw_response` that doesn't eagerly read the response body.
+
+        For more information, see https://www.github.com/openai/openai-python#with_streaming_response
+        """
+        return AsyncTranslationsWithStreamingResponse(self)
+
+    @overload
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        response_format: Union[Literal["json"], Omit] = omit,
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> Translation: ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        response_format: Literal["verbose_json"],
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> TranslationVerbose: ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        response_format: Literal["text", "srt", "vtt"],
+        prompt: str | Omit = omit,
+        temperature: float | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> str: ...
+
+    async def create(
+        self,
+        *,
+        file: FileTypes,
+        model: Union[str, AudioModel],
+        prompt: str | Omit = omit,
+        response_format: Union[AudioResponseFormat, Omit] = omit,
+        temperature: float | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> Translation | TranslationVerbose | str:
+        """
+        Translates audio into English.
+
+        Args:
+          file: The audio file object (not file name) translate, in one of these formats: flac,
+              mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
+
+          model: ID of the model to use. Only `whisper-1` (which is powered by our open source
+              Whisper V2 model) is currently available.
+
+          prompt: An optional text to guide the model's style or continue a previous audio
+              segment. The
+              [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+              should be in English.
+
+          response_format: The format of the output, in one of these options: `json`, `text`, `srt`,
+              `verbose_json`, or `vtt`.
+
+          temperature: 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.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        body = deepcopy_minimal(
+            {
+                "file": file,
+                "model": model,
+                "prompt": prompt,
+                "response_format": response_format,
+                "temperature": temperature,
+            }
+        )
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        # It should be noted that the actual Content-Type header that will be
+        # 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
+            ),
+            cast_to=_get_response_format_type(response_format),
+        )
+
+
+class TranslationsWithRawResponse:
+    def __init__(self, translations: Translations) -> None:
+        self._translations = translations
+
+        self.create = _legacy_response.to_raw_response_wrapper(
+            translations.create,
+        )
+
+
+class AsyncTranslationsWithRawResponse:
+    def __init__(self, translations: AsyncTranslations) -> None:
+        self._translations = translations
+
+        self.create = _legacy_response.async_to_raw_response_wrapper(
+            translations.create,
+        )
+
+
+class TranslationsWithStreamingResponse:
+    def __init__(self, translations: Translations) -> None:
+        self._translations = translations
+
+        self.create = to_streamed_response_wrapper(
+            translations.create,
+        )
+
+
+class AsyncTranslationsWithStreamingResponse:
+    def __init__(self, translations: AsyncTranslations) -> None:
+        self._translations = translations
+
+        self.create = async_to_streamed_response_wrapper(
+            translations.create,
+        )
+
+
+def _get_response_format_type(
+    response_format: AudioResponseFormat | Omit,
+) -> type[Translation | TranslationVerbose | str]:
+    if isinstance(response_format, Omit) or response_format is None:  # pyright: ignore[reportUnnecessaryComparison]
+        return Translation
+
+    if response_format == "json":
+        return Translation
+    elif response_format == "verbose_json":
+        return TranslationVerbose
+    elif response_format == "srt" or response_format == "text" or response_format == "vtt":
+        return str
+    elif TYPE_CHECKING and response_format != "diarized_json":  # type: ignore[unreachable]
+        assert_never(response_format)
+    else:
+        log.warning("Unexpected audio response format: %s", response_format)
+        return Translation