sarvamai 0.1.9a2__py3-none-any.whl → 0.1.11__py3-none-any.whl

sarvamai/text_to_speech/client.py

@@ -7,6 +7,7 @@ from ..core.request_options import RequestOptions
 from ..types.speech_sample_rate import SpeechSampleRate
 from ..types.text_to_speech_language import TextToSpeechLanguage
 from ..types.text_to_speech_model import TextToSpeechModel
+from ..types.text_to_speech_output_audio_codec import TextToSpeechOutputAudioCodec
 from ..types.text_to_speech_response import TextToSpeechResponse
 from ..types.text_to_speech_speaker import TextToSpeechSpeaker
 from .raw_client import AsyncRawTextToSpeechClient, RawTextToSpeechClient
@@ -42,6 +43,7 @@ class TextToSpeechClient:
         speech_sample_rate: typing.Optional[SpeechSampleRate] = OMIT,
         enable_preprocessing: typing.Optional[bool] = OMIT,
         model: typing.Optional[TextToSpeechModel] = OMIT,
+        output_audio_codec: typing.Optional[TextToSpeechOutputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> TextToSpeechResponse:
         """
@@ -85,6 +87,9 @@ class TextToSpeechClient:
         model : typing.Optional[TextToSpeechModel]
             Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
 
+        output_audio_codec : typing.Optional[TextToSpeechOutputAudioCodec]
+            Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -115,6 +120,7 @@ class TextToSpeechClient:
             speech_sample_rate=speech_sample_rate,
             enable_preprocessing=enable_preprocessing,
             model=model,
+            output_audio_codec=output_audio_codec,
             request_options=request_options,
         )
         return _response.data
@@ -147,6 +153,7 @@ class AsyncTextToSpeechClient:
         speech_sample_rate: typing.Optional[SpeechSampleRate] = OMIT,
         enable_preprocessing: typing.Optional[bool] = OMIT,
         model: typing.Optional[TextToSpeechModel] = OMIT,
+        output_audio_codec: typing.Optional[TextToSpeechOutputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> TextToSpeechResponse:
         """
@@ -190,6 +197,9 @@ class AsyncTextToSpeechClient:
         model : typing.Optional[TextToSpeechModel]
             Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
 
+        output_audio_codec : typing.Optional[TextToSpeechOutputAudioCodec]
+            Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -228,6 +238,7 @@ class AsyncTextToSpeechClient:
             speech_sample_rate=speech_sample_rate,
             enable_preprocessing=enable_preprocessing,
             model=model,
+            output_audio_codec=output_audio_codec,
             request_options=request_options,
         )
         return _response.data

sarvamai/text_to_speech/raw_client.py

@@ -16,6 +16,7 @@ from ..errors.unprocessable_entity_error import UnprocessableEntityError
 from ..types.speech_sample_rate import SpeechSampleRate
 from ..types.text_to_speech_language import TextToSpeechLanguage
 from ..types.text_to_speech_model import TextToSpeechModel
+from ..types.text_to_speech_output_audio_codec import TextToSpeechOutputAudioCodec
 from ..types.text_to_speech_response import TextToSpeechResponse
 from ..types.text_to_speech_speaker import TextToSpeechSpeaker
 
@@ -39,6 +40,7 @@ class RawTextToSpeechClient:
         speech_sample_rate: typing.Optional[SpeechSampleRate] = OMIT,
         enable_preprocessing: typing.Optional[bool] = OMIT,
         model: typing.Optional[TextToSpeechModel] = OMIT,
+        output_audio_codec: typing.Optional[TextToSpeechOutputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[TextToSpeechResponse]:
         """
@@ -82,6 +84,9 @@ class RawTextToSpeechClient:
         model : typing.Optional[TextToSpeechModel]
             Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
 
+        output_audio_codec : typing.Optional[TextToSpeechOutputAudioCodec]
+            Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -104,6 +109,7 @@ class RawTextToSpeechClient:
                 "speech_sample_rate": speech_sample_rate,
                 "enable_preprocessing": enable_preprocessing,
                 "model": model,
+                "output_audio_codec": output_audio_codec,
             },
             headers={
                 "content-type": "application/json",
@@ -198,6 +204,7 @@ class AsyncRawTextToSpeechClient:
         speech_sample_rate: typing.Optional[SpeechSampleRate] = OMIT,
         enable_preprocessing: typing.Optional[bool] = OMIT,
         model: typing.Optional[TextToSpeechModel] = OMIT,
+        output_audio_codec: typing.Optional[TextToSpeechOutputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[TextToSpeechResponse]:
         """
@@ -241,6 +248,9 @@ class AsyncRawTextToSpeechClient:
         model : typing.Optional[TextToSpeechModel]
             Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
 
+        output_audio_codec : typing.Optional[TextToSpeechOutputAudioCodec]
+            Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -263,6 +273,7 @@ class AsyncRawTextToSpeechClient:
                 "speech_sample_rate": speech_sample_rate,
                 "enable_preprocessing": enable_preprocessing,
                 "model": model,
+                "output_audio_codec": output_audio_codec,
             },
             headers={
                 "content-type": "application/json",

sarvamai/types/__init__.py

@@ -6,6 +6,9 @@ from .audio_data import AudioData
 from .audio_message import AudioMessage
 from .audio_output import AudioOutput
 from .audio_output_data import AudioOutputData
+from .base_job_parameters import BaseJobParameters
+from .bulk_job_callback import BulkJobCallback
+from .bulk_job_init_response_v_1 import BulkJobInitResponseV1
 from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessage
 from .chat_completion_request_message import (
     ChatCompletionRequestMessage,
@@ -22,6 +25,7 @@ from .config_message import ConfigMessage
 from .configure_connection import ConfigureConnection
 from .configure_connection_data import ConfigureConnectionData
 from .configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
+from .configure_connection_data_output_audio_codec import ConfigureConnectionDataOutputAudioCodec
 from .configure_connection_data_speaker import ConfigureConnectionDataSpeaker
 from .configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
 from .create_chat_completion_response import CreateChatCompletionResponse
@@ -34,9 +38,14 @@ from .error_message import ErrorMessage
 from .error_response import ErrorResponse
 from .error_response_data import ErrorResponseData
 from .events_data import EventsData
+from .file_signed_url_details import FileSignedUrlDetails
+from .files_download_response import FilesDownloadResponse
+from .files_request import FilesRequest
+from .files_upload_response import FilesUploadResponse
 from .finish_reason import FinishReason
 from .flush_signal import FlushSignal
-from .format import Format
+from .job_state import JobState
+from .job_status_v_1 import JobStatusV1
 from .language_identification_response import LanguageIdentificationResponse
 from .numerals_format import NumeralsFormat
 from .ping_signal import PingSignal
@@ -47,12 +56,14 @@ from .sarvam_model_ids import SarvamModelIds
 from .send_text import SendText
 from .send_text_data import SendTextData
 from .speech_sample_rate import SpeechSampleRate
+from .speech_to_text_job_parameters import SpeechToTextJobParameters
 from .speech_to_text_language import SpeechToTextLanguage
 from .speech_to_text_model import SpeechToTextModel
 from .speech_to_text_response import SpeechToTextResponse
 from .speech_to_text_response_data import SpeechToTextResponseData
 from .speech_to_text_streaming_response import SpeechToTextStreamingResponse
 from .speech_to_text_transcription_data import SpeechToTextTranscriptionData
+from .speech_to_text_translate_job_parameters import SpeechToTextTranslateJobParameters
 from .speech_to_text_translate_language import SpeechToTextTranslateLanguage
 from .speech_to_text_translate_model import SpeechToTextTranslateModel
 from .speech_to_text_translate_response import SpeechToTextTranslateResponse
@@ -61,8 +72,13 @@ from .speech_to_text_translate_streaming_response import SpeechToTextTranslateSt
 from .speech_to_text_translate_transcription_data import SpeechToTextTranslateTranscriptionData
 from .spoken_form_numerals_format import SpokenFormNumeralsFormat
 from .stop_configuration import StopConfiguration
+from .storage_container_type import StorageContainerType
+from .task_detail_v_1 import TaskDetailV1
+from .task_file_details import TaskFileDetails
+from .task_state import TaskState
 from .text_to_speech_language import TextToSpeechLanguage
 from .text_to_speech_model import TextToSpeechModel
+from .text_to_speech_output_audio_codec import TextToSpeechOutputAudioCodec
 from .text_to_speech_response import TextToSpeechResponse
 from .text_to_speech_speaker import TextToSpeechSpeaker
 from .timestamps_model import TimestampsModel
@@ -83,6 +99,9 @@ __all__ = [
     "AudioMessage",
     "AudioOutput",
     "AudioOutputData",
+    "BaseJobParameters",
+    "BulkJobCallback",
+    "BulkJobInitResponseV1",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestMessage",
     "ChatCompletionRequestMessage_Assistant",
@@ -97,6 +116,7 @@ __all__ = [
     "ConfigureConnection",
     "ConfigureConnectionData",
     "ConfigureConnectionDataOutputAudioBitrate",
+    "ConfigureConnectionDataOutputAudioCodec",
     "ConfigureConnectionDataSpeaker",
     "ConfigureConnectionDataTargetLanguageCode",
     "CreateChatCompletionResponse",
@@ -109,9 +129,14 @@ __all__ = [
     "ErrorResponse",
     "ErrorResponseData",
     "EventsData",
+    "FileSignedUrlDetails",
+    "FilesDownloadResponse",
+    "FilesRequest",
+    "FilesUploadResponse",
     "FinishReason",
     "FlushSignal",
-    "Format",
+    "JobState",
+    "JobStatusV1",
     "LanguageIdentificationResponse",
     "NumeralsFormat",
     "PingSignal",
@@ -122,12 +147,14 @@ __all__ = [
     "SendText",
     "SendTextData",
     "SpeechSampleRate",
+    "SpeechToTextJobParameters",
     "SpeechToTextLanguage",
     "SpeechToTextModel",
     "SpeechToTextResponse",
     "SpeechToTextResponseData",
     "SpeechToTextStreamingResponse",
     "SpeechToTextTranscriptionData",
+    "SpeechToTextTranslateJobParameters",
     "SpeechToTextTranslateLanguage",
     "SpeechToTextTranslateModel",
     "SpeechToTextTranslateResponse",
@@ -136,8 +163,13 @@ __all__ = [
     "SpeechToTextTranslateTranscriptionData",
     "SpokenFormNumeralsFormat",
     "StopConfiguration",
+    "StorageContainerType",
+    "TaskDetailV1",
+    "TaskFileDetails",
+    "TaskState",
     "TextToSpeechLanguage",
     "TextToSpeechModel",
+    "TextToSpeechOutputAudioCodec",
     "TextToSpeechResponse",
     "TextToSpeechSpeaker",
     "TimestampsModel",

sarvamai/types/base_job_parameters.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class BaseJobParameters(UniversalBaseModel):
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/bulk_job_callback.py

@@ -0,0 +1,27 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class BulkJobCallback(UniversalBaseModel):
+    url: str = pydantic.Field()
+    """
+    Webhook url to call upon job completion
+    """
+
+    auth_token: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Authorization token required for the callback Url
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/bulk_job_init_response_v_1.py

@@ -0,0 +1,39 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .base_job_parameters import BaseJobParameters
+from .bulk_job_callback import BulkJobCallback
+from .job_state import JobState
+from .storage_container_type import StorageContainerType
+
+
+class BulkJobInitResponseV1(UniversalBaseModel):
+    job_id: str = pydantic.Field()
+    """
+    Job UUID.
+    """
+
+    storage_container_type: StorageContainerType = pydantic.Field()
+    """
+    Storage Container Type
+    """
+
+    job_parameters: BaseJobParameters
+    job_state: JobState
+    owner_id: str
+    callback: typing.Optional[BulkJobCallback] = pydantic.Field(default=None)
+    """
+    Parameters for callback URL
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/configure_connection_data.py

@@ -5,6 +5,7 @@ import typing
 import pydantic
 from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
 from .configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
+from .configure_connection_data_output_audio_codec import ConfigureConnectionDataOutputAudioCodec
 from .configure_connection_data_speaker import ConfigureConnectionDataSpeaker
 from .configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
 
@@ -63,7 +64,7 @@ class ConfigureConnectionData(UniversalBaseModel):
     of mixed-language text. Default is false.
     """
 
-    output_audio_codec: typing.Optional[typing.Literal["mp3"]] = pydantic.Field(default=None)
+    output_audio_codec: typing.Optional[ConfigureConnectionDataOutputAudioCodec] = pydantic.Field(default=None)
     """
     Audio codec (currently supports MP3 only, optimized for real-time playback)
     """

sarvamai/types/configure_connection_data_output_audio_codec.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ConfigureConnectionDataOutputAudioCodec = typing.Union[
+    typing.Literal["linear16", "mulaw", "alaw", "opus", "flac", "aac", "wav"], typing.Any
+]

sarvamai/types/file_signed_url_details.py

@@ -0,0 +1,20 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class FileSignedUrlDetails(UniversalBaseModel):
+    file_url: str
+    file_metadata: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/files_download_response.py

@@ -0,0 +1,25 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .file_signed_url_details import FileSignedUrlDetails
+from .job_state import JobState
+from .storage_container_type import StorageContainerType
+
+
+class FilesDownloadResponse(UniversalBaseModel):
+    job_id: str
+    job_state: JobState
+    download_urls: typing.Dict[str, FileSignedUrlDetails]
+    storage_container_type: StorageContainerType
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/files_request.py

@@ -0,0 +1,20 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class FilesRequest(UniversalBaseModel):
+    job_id: str
+    files: typing.List[str]
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/files_upload_response.py

@@ -0,0 +1,25 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .file_signed_url_details import FileSignedUrlDetails
+from .job_state import JobState
+from .storage_container_type import StorageContainerType
+
+
+class FilesUploadResponse(UniversalBaseModel):
+    job_id: str
+    job_state: JobState
+    upload_urls: typing.Dict[str, FileSignedUrlDetails]
+    storage_container_type: StorageContainerType
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/job_state.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+JobState = typing.Union[typing.Literal["Accepted", "Pending", "Running", "Completed", "Failed"], typing.Any]

sarvamai/types/job_status_v_1.py

@@ -0,0 +1,80 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .job_state import JobState
+from .storage_container_type import StorageContainerType
+from .task_detail_v_1 import TaskDetailV1
+
+
+class JobStatusV1(UniversalBaseModel):
+    job_state: JobState = pydantic.Field()
+    """
+    Job State
+    """
+
+    created_at: str = pydantic.Field()
+    """
+    Created At
+    """
+
+    updated_at: str = pydantic.Field()
+    """
+    Updated At
+    """
+
+    job_id: str = pydantic.Field()
+    """
+    Job Id
+    """
+
+    total_files: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Total Files
+    """
+
+    successful_files_count: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Success Count
+    """
+
+    failed_files_count: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Failed Count
+    """
+
+    owner_id: str = pydantic.Field()
+    """
+    Owner of the job
+    """
+
+    storage_container_type: StorageContainerType = pydantic.Field()
+    """
+    Storage Container Type
+    """
+
+    error_message: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Error Message
+    """
+
+    job_details: typing.Optional[typing.List[TaskDetailV1]] = pydantic.Field(default=None)
+    """
+    Job details at file level.
+    """
+
+    num_internal_retries: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Number of internal retries
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/speech_to_text_job_parameters.py

@@ -0,0 +1,44 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .speech_to_text_model import SpeechToTextModel
+from .speech_to_text_translate_language import SpeechToTextTranslateLanguage
+
+
+class SpeechToTextJobParameters(UniversalBaseModel):
+    language_code: typing.Optional[SpeechToTextTranslateLanguage] = pydantic.Field(default=None)
+    """
+    Language code
+    """
+
+    model: typing.Optional[SpeechToTextModel] = pydantic.Field(default=None)
+    """
+    Model to be used for speech to text
+    """
+
+    with_timestamps: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Whether to include timestamps in the response
+    """
+
+    with_diarization: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Enables speaker diarization, which identifies and separates different speakers in the audio. In beta mode
+    """
+
+    num_speakers: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Number of speakers to be detected in the audio. This is used when with_diarization is true.
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/speech_to_text_model.py

@@ -2,4 +2,6 @@
 
 import typing
 
-SpeechToTextModel = typing.Union[typing.Literal["saarika:v2", "saarika:v2.5"], typing.Any]
+SpeechToTextModel = typing.Union[
+    typing.Literal["saarika:v1", "saarika:v2", "saarika:v2.5", "saarika:flash"], typing.Any
+]

sarvamai/types/speech_to_text_translate_job_parameters.py

@@ -0,0 +1,40 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .speech_to_text_translate_model import SpeechToTextTranslateModel
+
+
+class SpeechToTextTranslateJobParameters(UniversalBaseModel):
+    prompt: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Prompt to assist the transcription
+    """
+
+    model: typing.Optional[SpeechToTextTranslateModel] = pydantic.Field(default=None)
+    """
+    Model to be used for converting speech to text in target language
+    """
+
+    with_diarization: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    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.Optional[int] = pydantic.Field(default=None)
+    """
+    Number of speakers to be detected in the audio. This is used when with_diarization is set to true.
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/speech_to_text_translate_model.py

@@ -2,4 +2,6 @@
 
 import typing
 
-SpeechToTextTranslateModel = typing.Union[typing.Literal["saaras:v2", "saaras:v2.5"], typing.Any]
+SpeechToTextTranslateModel = typing.Union[
+    typing.Literal["saaras:v1", "saaras:v2", "saaras:v2.5", "saaras:flash"], typing.Any
+]

sarvamai/types/storage_container_type.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+StorageContainerType = typing.Union[typing.Literal["Azure", "Local", "Google", "Azure_V1"], typing.Any]

sarvamai/types/task_detail_v_1.py

@@ -0,0 +1,25 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .task_file_details import TaskFileDetails
+from .task_state import TaskState
+
+
+class TaskDetailV1(UniversalBaseModel):
+    inputs: typing.Optional[typing.List[TaskFileDetails]] = None
+    outputs: typing.Optional[typing.List[TaskFileDetails]] = None
+    state: typing.Optional[TaskState] = None
+    error_message: typing.Optional[str] = None
+    exception_name: typing.Optional[str] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow