sarvamai 0.1.11a1__py3-none-any.whl → 0.1.11a3__py3-none-any.whl

sarvamai/__init__.py

@@ -3,7 +3,6 @@
 # isort: skip_file
 
 from .types import (
-    AudioCodec,
     AudioData,
     AudioMessage,
     AudioOutput,
@@ -25,6 +24,7 @@ from .types import (
     ConfigureConnection,
     ConfigureConnectionData,
     ConfigureConnectionDataOutputAudioBitrate,
+    ConfigureConnectionDataOutputAudioCodec,
     ConfigureConnectionDataSpeaker,
     ConfigureConnectionDataTargetLanguageCode,
     CreateChatCompletionResponse,
@@ -43,7 +43,6 @@ from .types import (
     FilesUploadResponse,
     FinishReason,
     FlushSignal,
-    Format,
     JobState,
     JobStatusV1,
     LanguageIdentificationResponse,
@@ -63,6 +62,7 @@ from .types import (
     SpeechToTextResponseData,
     SpeechToTextStreamingResponse,
     SpeechToTextTranscriptionData,
+    SpeechToTextTranslateJobParameters,
     SpeechToTextTranslateLanguage,
     SpeechToTextTranslateModel,
     SpeechToTextTranslateResponse,
@@ -77,6 +77,7 @@ from .types import (
     TaskState,
     TextToSpeechLanguage,
     TextToSpeechModel,
+    TextToSpeechOutputAudioCodec,
     TextToSpeechResponse,
     TextToSpeechSpeaker,
     TimestampsModel,
@@ -105,6 +106,7 @@ from . import (
     speech_to_text,
     speech_to_text_job,
     speech_to_text_streaming,
+    speech_to_text_translate_job,
     speech_to_text_translate_streaming,
     text,
     text_to_speech,
@@ -157,6 +159,7 @@ from .requests import (
     SpeechToTextResponseParams,
     SpeechToTextStreamingResponseParams,
     SpeechToTextTranscriptionDataParams,
+    SpeechToTextTranslateJobParametersParams,
     SpeechToTextTranslateResponseDataParams,
     SpeechToTextTranslateResponseParams,
     SpeechToTextTranslateStreamingResponseParams,
@@ -185,7 +188,6 @@ from .version import __version__
 
 __all__ = [
     "AsyncSarvamAI",
-    "AudioCodec",
     "AudioData",
     "AudioDataParams",
     "AudioMessage",
@@ -226,6 +228,7 @@ __all__ = [
     "ConfigureConnection",
     "ConfigureConnectionData",
     "ConfigureConnectionDataOutputAudioBitrate",
+    "ConfigureConnectionDataOutputAudioCodec",
     "ConfigureConnectionDataParams",
     "ConfigureConnectionDataSpeaker",
     "ConfigureConnectionDataTargetLanguageCode",
@@ -261,7 +264,6 @@ __all__ = [
     "FlushSignal",
     "FlushSignalParams",
     "ForbiddenError",
-    "Format",
     "InternalServerError",
     "JobState",
     "JobStatusV1",
@@ -299,6 +301,8 @@ __all__ = [
     "SpeechToTextStreamingVadSignals",
     "SpeechToTextTranscriptionData",
     "SpeechToTextTranscriptionDataParams",
+    "SpeechToTextTranslateJobParameters",
+    "SpeechToTextTranslateJobParametersParams",
     "SpeechToTextTranslateLanguage",
     "SpeechToTextTranslateModel",
     "SpeechToTextTranslateResponse",
@@ -323,6 +327,7 @@ __all__ = [
     "TaskState",
     "TextToSpeechLanguage",
     "TextToSpeechModel",
+    "TextToSpeechOutputAudioCodec",
     "TextToSpeechResponse",
     "TextToSpeechResponseParams",
     "TextToSpeechSpeaker",
@@ -349,6 +354,7 @@ __all__ = [
     "speech_to_text",
     "speech_to_text_job",
     "speech_to_text_streaming",
+    "speech_to_text_translate_job",
     "speech_to_text_translate_streaming",
     "text",
     "text_to_speech",

sarvamai/client.py

@@ -11,6 +11,7 @@ from .environment import SarvamAIEnvironment
 from .speech_to_text.client import AsyncSpeechToTextClient, SpeechToTextClient
 from .speech_to_text_job.client import AsyncSpeechToTextJobClient, SpeechToTextJobClient
 from .speech_to_text_streaming.client import AsyncSpeechToTextStreamingClient, SpeechToTextStreamingClient
+from .speech_to_text_translate_job.client import AsyncSpeechToTextTranslateJobClient, SpeechToTextTranslateJobClient
 from .speech_to_text_translate_streaming.client import (
     AsyncSpeechToTextTranslateStreamingClient,
     SpeechToTextTranslateStreamingClient,
@@ -90,6 +91,7 @@ class SarvamAI:
         self.text_to_speech = TextToSpeechClient(client_wrapper=self._client_wrapper)
         self.chat = ChatClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_job = SpeechToTextJobClient(client_wrapper=self._client_wrapper)
+        self.speech_to_text_translate_job = SpeechToTextTranslateJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_streaming = SpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = SpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper
@@ -167,6 +169,7 @@ class AsyncSarvamAI:
         self.text_to_speech = AsyncTextToSpeechClient(client_wrapper=self._client_wrapper)
         self.chat = AsyncChatClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_job = AsyncSpeechToTextJobClient(client_wrapper=self._client_wrapper)
+        self.speech_to_text_translate_job = AsyncSpeechToTextTranslateJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_streaming = AsyncSpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = AsyncSpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper

sarvamai/core/client_wrapper.py

@@ -23,10 +23,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.11a1",
+            "User-Agent": "sarvamai/0.1.11a3",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.11a1",
+            "X-Fern-SDK-Version": "0.1.11a3",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

sarvamai/requests/__init__.py

@@ -48,6 +48,7 @@ from .speech_to_text_response import SpeechToTextResponseParams
 from .speech_to_text_response_data import SpeechToTextResponseDataParams
 from .speech_to_text_streaming_response import SpeechToTextStreamingResponseParams
 from .speech_to_text_transcription_data import SpeechToTextTranscriptionDataParams
+from .speech_to_text_translate_job_parameters import SpeechToTextTranslateJobParametersParams
 from .speech_to_text_translate_response import SpeechToTextTranslateResponseParams
 from .speech_to_text_translate_response_data import SpeechToTextTranslateResponseDataParams
 from .speech_to_text_translate_streaming_response import SpeechToTextTranslateStreamingResponseParams
@@ -106,6 +107,7 @@ __all__ = [
     "SpeechToTextResponseParams",
     "SpeechToTextStreamingResponseParams",
     "SpeechToTextTranscriptionDataParams",
+    "SpeechToTextTranslateJobParametersParams",
     "SpeechToTextTranslateResponseDataParams",
     "SpeechToTextTranslateResponseParams",
     "SpeechToTextTranslateStreamingResponseParams",

sarvamai/requests/configure_connection_data.py

@@ -1,9 +1,8 @@
 # This file was auto-generated by Fern from our API Definition.
 
-import typing
-
 import typing_extensions
 from ..types.configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
+from ..types.configure_connection_data_output_audio_codec import ConfigureConnectionDataOutputAudioCodec
 from ..types.configure_connection_data_speaker import ConfigureConnectionDataSpeaker
 from ..types.configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
 
@@ -62,7 +61,7 @@ class ConfigureConnectionDataParams(typing_extensions.TypedDict):
     of mixed-language text. Default is false.
     """
 
-    output_audio_codec: typing_extensions.NotRequired[typing.Literal["mp3"]]
+    output_audio_codec: typing_extensions.NotRequired[ConfigureConnectionDataOutputAudioCodec]
     """
     Audio codec (currently supports MP3 only, optimized for real-time playback)
     """

sarvamai/requests/speech_to_text_translate_job_parameters.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.speech_to_text_translate_model import SpeechToTextTranslateModel
+
+
+class SpeechToTextTranslateJobParametersParams(typing_extensions.TypedDict):
+    prompt: typing_extensions.NotRequired[str]
+    """
+    Prompt to assist the transcription
+    """
+
+    model: typing_extensions.NotRequired[SpeechToTextTranslateModel]
+    """
+    Model to be used for converting speech to text in target language
+    """
+
+    with_diarization: typing_extensions.NotRequired[bool]
+    """
+    Enables speaker diarization, which identifies and separates different speakers in the audio.
+     When set to true, the API will provide speaker-specific segments in the response.
+     Note: This parameter is currently in Beta mode.
+    """
+
+    num_speakers: typing_extensions.NotRequired[int]
+    """
+    Number of speakers to be detected in the audio. This is used when with_diarization is set to true.
+    """

sarvamai/speech_to_text_translate_job/__init__.py

@@ -0,0 +1,4 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+

sarvamai/speech_to_text_translate_job/client.py

@@ -0,0 +1,494 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from ..core.request_options import RequestOptions
+from ..requests.bulk_job_callback import BulkJobCallbackParams
+from ..requests.speech_to_text_translate_job_parameters import SpeechToTextTranslateJobParametersParams
+from ..types.bulk_job_init_response_v_1 import BulkJobInitResponseV1
+from ..types.files_download_response import FilesDownloadResponse
+from ..types.files_upload_response import FilesUploadResponse
+from ..types.job_status_v_1 import JobStatusV1
+from .raw_client import AsyncRawSpeechToTextTranslateJobClient, RawSpeechToTextTranslateJobClient
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+class SpeechToTextTranslateJobClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._raw_client = RawSpeechToTextTranslateJobClient(client_wrapper=client_wrapper)
+
+    @property
+    def with_raw_response(self) -> RawSpeechToTextTranslateJobClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        RawSpeechToTextTranslateJobClient
+        """
+        return self._raw_client
+
+    def initialise(
+        self,
+        *,
+        job_parameters: SpeechToTextTranslateJobParametersParams,
+        ptu_id: typing.Optional[int] = None,
+        callback: typing.Optional[BulkJobCallbackParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> BulkJobInitResponseV1:
+        """
+        Get a job uuid, and storage folder details for speech to text tranlsate bulk job v1
+
+        Parameters
+        ----------
+        job_parameters : SpeechToTextTranslateJobParametersParams
+            Job Parameters for the bulk job
+
+        ptu_id : typing.Optional[int]
+
+        callback : typing.Optional[BulkJobCallbackParams]
+            Parameters for callback URL
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        BulkJobInitResponseV1
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.speech_to_text_translate_job.initialise(
+            job_parameters={},
+        )
+        """
+        _response = self._raw_client.initialise(
+            job_parameters=job_parameters, ptu_id=ptu_id, callback=callback, request_options=request_options
+        )
+        return _response.data
+
+    def get_status(self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None) -> JobStatusV1:
+        """
+        Get the status of a speech to text translate bulk job V1
+
+        Parameters
+        ----------
+        job_id : str
+            The unique identifier of the job
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        JobStatusV1
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.speech_to_text_translate_job.get_status(
+            job_id="job_id",
+        )
+        """
+        _response = self._raw_client.get_status(job_id, request_options=request_options)
+        return _response.data
+
+    def start(
+        self,
+        job_id: str,
+        *,
+        ptu_id: typing.Optional[int] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> JobStatusV1:
+        """
+        Start a speech to text translate bulk job V1
+
+        Parameters
+        ----------
+        job_id : str
+            The unique identifier of the job
+
+        ptu_id : typing.Optional[int]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        JobStatusV1
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.speech_to_text_translate_job.start(
+            job_id="job_id",
+        )
+        """
+        _response = self._raw_client.start(job_id, ptu_id=ptu_id, request_options=request_options)
+        return _response.data
+
+    def get_upload_links(
+        self,
+        *,
+        job_id: str,
+        files: typing.Sequence[str],
+        ptu_id: typing.Optional[int] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> FilesUploadResponse:
+        """
+        Start a speech to text bulk job V1
+
+        Parameters
+        ----------
+        job_id : str
+
+        files : typing.Sequence[str]
+
+        ptu_id : typing.Optional[int]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        FilesUploadResponse
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.speech_to_text_translate_job.get_upload_links(
+            job_id="job_id",
+            files=["files"],
+        )
+        """
+        _response = self._raw_client.get_upload_links(
+            job_id=job_id, files=files, ptu_id=ptu_id, request_options=request_options
+        )
+        return _response.data
+
+    def get_download_links(
+        self,
+        *,
+        job_id: str,
+        files: typing.Sequence[str],
+        ptu_id: typing.Optional[int] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> FilesDownloadResponse:
+        """
+        Start a speech to text bulk job V1
+
+        Parameters
+        ----------
+        job_id : str
+
+        files : typing.Sequence[str]
+
+        ptu_id : typing.Optional[int]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        FilesDownloadResponse
+            Successful Response
+
+        Examples
+        --------
+        from sarvamai import SarvamAI
+
+        client = SarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+        client.speech_to_text_translate_job.get_download_links(
+            job_id="job_id",
+            files=["files"],
+        )
+        """
+        _response = self._raw_client.get_download_links(
+            job_id=job_id, files=files, ptu_id=ptu_id, request_options=request_options
+        )
+        return _response.data
+
+
+class AsyncSpeechToTextTranslateJobClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._raw_client = AsyncRawSpeechToTextTranslateJobClient(client_wrapper=client_wrapper)
+
+    @property
+    def with_raw_response(self) -> AsyncRawSpeechToTextTranslateJobClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        AsyncRawSpeechToTextTranslateJobClient
+        """
+        return self._raw_client
+
+    async def initialise(
+        self,
+        *,
+        job_parameters: SpeechToTextTranslateJobParametersParams,
+        ptu_id: typing.Optional[int] = None,
+        callback: typing.Optional[BulkJobCallbackParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> BulkJobInitResponseV1:
+        """
+        Get a job uuid, and storage folder details for speech to text tranlsate bulk job v1
+
+        Parameters
+        ----------
+        job_parameters : SpeechToTextTranslateJobParametersParams
+            Job Parameters for the bulk job
+
+        ptu_id : typing.Optional[int]
+
+        callback : typing.Optional[BulkJobCallbackParams]
+            Parameters for callback URL
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        BulkJobInitResponseV1
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.speech_to_text_translate_job.initialise(
+                job_parameters={},
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.initialise(
+            job_parameters=job_parameters, ptu_id=ptu_id, callback=callback, request_options=request_options
+        )
+        return _response.data
+
+    async def get_status(self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None) -> JobStatusV1:
+        """
+        Get the status of a speech to text translate bulk job V1
+
+        Parameters
+        ----------
+        job_id : str
+            The unique identifier of the job
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        JobStatusV1
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.speech_to_text_translate_job.get_status(
+                job_id="job_id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.get_status(job_id, request_options=request_options)
+        return _response.data
+
+    async def start(
+        self,
+        job_id: str,
+        *,
+        ptu_id: typing.Optional[int] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> JobStatusV1:
+        """
+        Start a speech to text translate bulk job V1
+
+        Parameters
+        ----------
+        job_id : str
+            The unique identifier of the job
+
+        ptu_id : typing.Optional[int]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        JobStatusV1
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.speech_to_text_translate_job.start(
+                job_id="job_id",
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.start(job_id, ptu_id=ptu_id, request_options=request_options)
+        return _response.data
+
+    async def get_upload_links(
+        self,
+        *,
+        job_id: str,
+        files: typing.Sequence[str],
+        ptu_id: typing.Optional[int] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> FilesUploadResponse:
+        """
+        Start a speech to text bulk job V1
+
+        Parameters
+        ----------
+        job_id : str
+
+        files : typing.Sequence[str]
+
+        ptu_id : typing.Optional[int]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        FilesUploadResponse
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.speech_to_text_translate_job.get_upload_links(
+                job_id="job_id",
+                files=["files"],
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.get_upload_links(
+            job_id=job_id, files=files, ptu_id=ptu_id, request_options=request_options
+        )
+        return _response.data
+
+    async def get_download_links(
+        self,
+        *,
+        job_id: str,
+        files: typing.Sequence[str],
+        ptu_id: typing.Optional[int] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> FilesDownloadResponse:
+        """
+        Start a speech to text bulk job V1
+
+        Parameters
+        ----------
+        job_id : str
+
+        files : typing.Sequence[str]
+
+        ptu_id : typing.Optional[int]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        FilesDownloadResponse
+            Successful Response
+
+        Examples
+        --------
+        import asyncio
+
+        from sarvamai import AsyncSarvamAI
+
+        client = AsyncSarvamAI(
+            api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.speech_to_text_translate_job.get_download_links(
+                job_id="job_id",
+                files=["files"],
+            )
+
+
+        asyncio.run(main())
+        """
+        _response = await self._raw_client.get_download_links(
+            job_id=job_id, files=files, ptu_id=ptu_id, request_options=request_options
+        )
+        return _response.data