sarvamai 0.1.10__py3-none-any.whl → 0.1.11__py3-none-any.whl

sarvamai/__init__.py

@@ -3,11 +3,13 @@
 # isort: skip_file
 
 from .types import (
-    AudioCodec,
     AudioData,
     AudioMessage,
     AudioOutput,
     AudioOutputData,
+    BaseJobParameters,
+    BulkJobCallback,
+    BulkJobInitResponseV1,
     ChatCompletionRequestAssistantMessage,
     ChatCompletionRequestMessage,
     ChatCompletionRequestMessage_Assistant,
@@ -22,6 +24,7 @@ from .types import (
     ConfigureConnection,
     ConfigureConnectionData,
     ConfigureConnectionDataOutputAudioBitrate,
+    ConfigureConnectionDataOutputAudioCodec,
     ConfigureConnectionDataSpeaker,
     ConfigureConnectionDataTargetLanguageCode,
     CreateChatCompletionResponse,
@@ -34,9 +37,14 @@ from .types import (
     ErrorResponse,
     ErrorResponseData,
     EventsData,
+    FileSignedUrlDetails,
+    FilesDownloadResponse,
+    FilesRequest,
+    FilesUploadResponse,
     FinishReason,
     FlushSignal,
-    Format,
+    JobState,
+    JobStatusV1,
     LanguageIdentificationResponse,
     NumeralsFormat,
     PingSignal,
@@ -47,12 +55,14 @@ from .types import (
     SendText,
     SendTextData,
     SpeechSampleRate,
+    SpeechToTextJobParameters,
     SpeechToTextLanguage,
     SpeechToTextModel,
     SpeechToTextResponse,
     SpeechToTextResponseData,
     SpeechToTextStreamingResponse,
     SpeechToTextTranscriptionData,
+    SpeechToTextTranslateJobParameters,
     SpeechToTextTranslateLanguage,
     SpeechToTextTranslateModel,
     SpeechToTextTranslateResponse,
@@ -61,8 +71,13 @@ from .types import (
     SpeechToTextTranslateTranscriptionData,
     SpokenFormNumeralsFormat,
     StopConfiguration,
+    StorageContainerType,
+    TaskDetailV1,
+    TaskFileDetails,
+    TaskState,
     TextToSpeechLanguage,
     TextToSpeechModel,
+    TextToSpeechOutputAudioCodec,
     TextToSpeechResponse,
     TextToSpeechSpeaker,
     TimestampsModel,
@@ -89,7 +104,9 @@ from .errors import (
 from . import (
     chat,
     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,
@@ -102,6 +119,9 @@ from .requests import (
     AudioMessageParams,
     AudioOutputDataParams,
     AudioOutputParams,
+    BaseJobParametersParams,
+    BulkJobCallbackParams,
+    BulkJobInitResponseV1Params,
     ChatCompletionRequestAssistantMessageParams,
     ChatCompletionRequestMessageParams,
     ChatCompletionRequestMessage_AssistantParams,
@@ -124,20 +144,29 @@ from .requests import (
     ErrorResponseDataParams,
     ErrorResponseParams,
     EventsDataParams,
+    FileSignedUrlDetailsParams,
+    FilesDownloadResponseParams,
+    FilesRequestParams,
+    FilesUploadResponseParams,
     FlushSignalParams,
+    JobStatusV1Params,
     LanguageIdentificationResponseParams,
     PingSignalParams,
     SendTextDataParams,
     SendTextParams,
+    SpeechToTextJobParametersParams,
     SpeechToTextResponseDataParams,
     SpeechToTextResponseParams,
     SpeechToTextStreamingResponseParams,
     SpeechToTextTranscriptionDataParams,
+    SpeechToTextTranslateJobParametersParams,
     SpeechToTextTranslateResponseDataParams,
     SpeechToTextTranslateResponseParams,
     SpeechToTextTranslateStreamingResponseParams,
     SpeechToTextTranslateTranscriptionDataParams,
     StopConfigurationParams,
+    TaskDetailV1Params,
+    TaskFileDetailsParams,
     TextToSpeechResponseParams,
     TimestampsModelParams,
     TranscriptionMetricsParams,
@@ -159,7 +188,6 @@ from .version import __version__
 
 __all__ = [
     "AsyncSarvamAI",
-    "AudioCodec",
     "AudioData",
     "AudioDataParams",
     "AudioMessage",
@@ -169,6 +197,12 @@ __all__ = [
     "AudioOutputDataParams",
     "AudioOutputParams",
     "BadRequestError",
+    "BaseJobParameters",
+    "BaseJobParametersParams",
+    "BulkJobCallback",
+    "BulkJobCallbackParams",
+    "BulkJobInitResponseV1",
+    "BulkJobInitResponseV1Params",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestAssistantMessageParams",
     "ChatCompletionRequestMessage",
@@ -194,6 +228,7 @@ __all__ = [
     "ConfigureConnection",
     "ConfigureConnectionData",
     "ConfigureConnectionDataOutputAudioBitrate",
+    "ConfigureConnectionDataOutputAudioCodec",
     "ConfigureConnectionDataParams",
     "ConfigureConnectionDataSpeaker",
     "ConfigureConnectionDataTargetLanguageCode",
@@ -217,12 +252,22 @@ __all__ = [
     "ErrorResponseParams",
     "EventsData",
     "EventsDataParams",
+    "FileSignedUrlDetails",
+    "FileSignedUrlDetailsParams",
+    "FilesDownloadResponse",
+    "FilesDownloadResponseParams",
+    "FilesRequest",
+    "FilesRequestParams",
+    "FilesUploadResponse",
+    "FilesUploadResponseParams",
     "FinishReason",
     "FlushSignal",
     "FlushSignalParams",
     "ForbiddenError",
-    "Format",
     "InternalServerError",
+    "JobState",
+    "JobStatusV1",
+    "JobStatusV1Params",
     "LanguageIdentificationResponse",
     "LanguageIdentificationResponseParams",
     "NumeralsFormat",
@@ -240,6 +285,8 @@ __all__ = [
     "SendTextParams",
     "ServiceUnavailableError",
     "SpeechSampleRate",
+    "SpeechToTextJobParameters",
+    "SpeechToTextJobParametersParams",
     "SpeechToTextLanguage",
     "SpeechToTextModel",
     "SpeechToTextResponse",
@@ -254,6 +301,8 @@ __all__ = [
     "SpeechToTextStreamingVadSignals",
     "SpeechToTextTranscriptionData",
     "SpeechToTextTranscriptionDataParams",
+    "SpeechToTextTranslateJobParameters",
+    "SpeechToTextTranslateJobParametersParams",
     "SpeechToTextTranslateLanguage",
     "SpeechToTextTranslateModel",
     "SpeechToTextTranslateResponse",
@@ -270,8 +319,15 @@ __all__ = [
     "SpokenFormNumeralsFormat",
     "StopConfiguration",
     "StopConfigurationParams",
+    "StorageContainerType",
+    "TaskDetailV1",
+    "TaskDetailV1Params",
+    "TaskFileDetails",
+    "TaskFileDetailsParams",
+    "TaskState",
     "TextToSpeechLanguage",
     "TextToSpeechModel",
+    "TextToSpeechOutputAudioCodec",
     "TextToSpeechResponse",
     "TextToSpeechResponseParams",
     "TextToSpeechSpeaker",
@@ -296,7 +352,9 @@ __all__ = [
     "__version__",
     "chat",
     "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

@@ -9,7 +9,9 @@ from .core.api_error import ApiError
 from .core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 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,
@@ -88,6 +90,8 @@ class SarvamAI:
         self.speech_to_text = SpeechToTextClient(client_wrapper=self._client_wrapper)
         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
@@ -164,6 +168,8 @@ class AsyncSarvamAI:
         self.speech_to_text = AsyncSpeechToTextClient(client_wrapper=self._client_wrapper)
         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/0.1.10",
+            "User-Agent": "sarvamai/0.1.11",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.10",
+            "X-Fern-SDK-Version": "0.1.11",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

sarvamai/errors/service_unavailable_error.py

@@ -3,9 +3,8 @@
 import typing
 
 from ..core.api_error import ApiError
-from ..types.error_message import ErrorMessage
 
 
 class ServiceUnavailableError(ApiError):
-    def __init__(self, body: ErrorMessage, headers: typing.Optional[typing.Dict[str, str]] = None):
+    def __init__(self, body: typing.Optional[typing.Any], headers: typing.Optional[typing.Dict[str, str]] = None):
         super().__init__(status_code=503, headers=headers, body=body)

sarvamai/requests/__init__.py

@@ -6,6 +6,9 @@ from .audio_data import AudioDataParams
 from .audio_message import AudioMessageParams
 from .audio_output import AudioOutputParams
 from .audio_output_data import AudioOutputDataParams
+from .base_job_parameters import BaseJobParametersParams
+from .bulk_job_callback import BulkJobCallbackParams
+from .bulk_job_init_response_v_1 import BulkJobInitResponseV1Params
 from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessageParams
 from .chat_completion_request_message import (
     ChatCompletionRequestMessageParams,
@@ -30,20 +33,29 @@ from .error_message import ErrorMessageParams
 from .error_response import ErrorResponseParams
 from .error_response_data import ErrorResponseDataParams
 from .events_data import EventsDataParams
+from .file_signed_url_details import FileSignedUrlDetailsParams
+from .files_download_response import FilesDownloadResponseParams
+from .files_request import FilesRequestParams
+from .files_upload_response import FilesUploadResponseParams
 from .flush_signal import FlushSignalParams
+from .job_status_v_1 import JobStatusV1Params
 from .language_identification_response import LanguageIdentificationResponseParams
 from .ping_signal import PingSignalParams
 from .send_text import SendTextParams
 from .send_text_data import SendTextDataParams
+from .speech_to_text_job_parameters import SpeechToTextJobParametersParams
 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
 from .speech_to_text_translate_transcription_data import SpeechToTextTranslateTranscriptionDataParams
 from .stop_configuration import StopConfigurationParams
+from .task_detail_v_1 import TaskDetailV1Params
+from .task_file_details import TaskFileDetailsParams
 from .text_to_speech_response import TextToSpeechResponseParams
 from .timestamps_model import TimestampsModelParams
 from .transcription_metrics import TranscriptionMetricsParams
@@ -55,6 +67,9 @@ __all__ = [
     "AudioMessageParams",
     "AudioOutputDataParams",
     "AudioOutputParams",
+    "BaseJobParametersParams",
+    "BulkJobCallbackParams",
+    "BulkJobInitResponseV1Params",
     "ChatCompletionRequestAssistantMessageParams",
     "ChatCompletionRequestMessageParams",
     "ChatCompletionRequestMessage_AssistantParams",
@@ -77,20 +92,29 @@ __all__ = [
     "ErrorResponseDataParams",
     "ErrorResponseParams",
     "EventsDataParams",
+    "FileSignedUrlDetailsParams",
+    "FilesDownloadResponseParams",
+    "FilesRequestParams",
+    "FilesUploadResponseParams",
     "FlushSignalParams",
+    "JobStatusV1Params",
     "LanguageIdentificationResponseParams",
     "PingSignalParams",
     "SendTextDataParams",
     "SendTextParams",
+    "SpeechToTextJobParametersParams",
     "SpeechToTextResponseDataParams",
     "SpeechToTextResponseParams",
     "SpeechToTextStreamingResponseParams",
     "SpeechToTextTranscriptionDataParams",
+    "SpeechToTextTranslateJobParametersParams",
     "SpeechToTextTranslateResponseDataParams",
     "SpeechToTextTranslateResponseParams",
     "SpeechToTextTranslateStreamingResponseParams",
     "SpeechToTextTranslateTranscriptionDataParams",
     "StopConfigurationParams",
+    "TaskDetailV1Params",
+    "TaskFileDetailsParams",
     "TextToSpeechResponseParams",
     "TimestampsModelParams",
     "TranscriptionMetricsParams",

sarvamai/requests/base_job_parameters.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class BaseJobParametersParams(typing_extensions.TypedDict):
+    pass

sarvamai/requests/bulk_job_callback.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class BulkJobCallbackParams(typing_extensions.TypedDict):
+    url: str
+    """
+    Webhook url to call upon job completion
+    """
+
+    auth_token: typing_extensions.NotRequired[str]
+    """
+    Authorization token required for the callback Url
+    """

sarvamai/requests/bulk_job_init_response_v_1.py

@@ -0,0 +1,27 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.job_state import JobState
+from ..types.storage_container_type import StorageContainerType
+from .base_job_parameters import BaseJobParametersParams
+from .bulk_job_callback import BulkJobCallbackParams
+
+
+class BulkJobInitResponseV1Params(typing_extensions.TypedDict):
+    job_id: str
+    """
+    Job UUID.
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage Container Type
+    """
+
+    job_parameters: BaseJobParametersParams
+    job_state: JobState
+    owner_id: str
+    callback: typing_extensions.NotRequired[BulkJobCallbackParams]
+    """
+    Parameters for callback URL
+    """

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/file_signed_url_details.py

@@ -0,0 +1,10 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+
+
+class FileSignedUrlDetailsParams(typing_extensions.TypedDict):
+    file_url: str
+    file_metadata: typing_extensions.NotRequired[typing.Dict[str, typing.Optional[typing.Any]]]

sarvamai/requests/files_download_response.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.job_state import JobState
+from ..types.storage_container_type import StorageContainerType
+from .file_signed_url_details import FileSignedUrlDetailsParams
+
+
+class FilesDownloadResponseParams(typing_extensions.TypedDict):
+    job_id: str
+    job_state: JobState
+    download_urls: typing.Dict[str, FileSignedUrlDetailsParams]
+    storage_container_type: StorageContainerType

sarvamai/requests/files_request.py

@@ -0,0 +1,10 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+
+
+class FilesRequestParams(typing_extensions.TypedDict):
+    job_id: str
+    files: typing.Sequence[str]

sarvamai/requests/files_upload_response.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.job_state import JobState
+from ..types.storage_container_type import StorageContainerType
+from .file_signed_url_details import FileSignedUrlDetailsParams
+
+
+class FilesUploadResponseParams(typing_extensions.TypedDict):
+    job_id: str
+    job_state: JobState
+    upload_urls: typing.Dict[str, FileSignedUrlDetailsParams]
+    storage_container_type: StorageContainerType

sarvamai/requests/job_status_v_1.py

@@ -0,0 +1,70 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.job_state import JobState
+from ..types.storage_container_type import StorageContainerType
+from .task_detail_v_1 import TaskDetailV1Params
+
+
+class JobStatusV1Params(typing_extensions.TypedDict):
+    job_state: JobState
+    """
+    Job State
+    """
+
+    created_at: str
+    """
+    Created At
+    """
+
+    updated_at: str
+    """
+    Updated At
+    """
+
+    job_id: str
+    """
+    Job Id
+    """
+
+    total_files: typing_extensions.NotRequired[int]
+    """
+    Total Files
+    """
+
+    successful_files_count: typing_extensions.NotRequired[int]
+    """
+    Success Count
+    """
+
+    failed_files_count: typing_extensions.NotRequired[int]
+    """
+    Failed Count
+    """
+
+    owner_id: str
+    """
+    Owner of the job
+    """
+
+    storage_container_type: StorageContainerType
+    """
+    Storage Container Type
+    """
+
+    error_message: typing_extensions.NotRequired[str]
+    """
+    Error Message
+    """
+
+    job_details: typing_extensions.NotRequired[typing.Sequence[TaskDetailV1Params]]
+    """
+    Job details at file level.
+    """
+
+    num_internal_retries: typing_extensions.NotRequired[int]
+    """
+    Number of internal retries
+    """

sarvamai/requests/speech_to_text_job_parameters.py

@@ -0,0 +1,32 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.speech_to_text_model import SpeechToTextModel
+from ..types.speech_to_text_translate_language import SpeechToTextTranslateLanguage
+
+
+class SpeechToTextJobParametersParams(typing_extensions.TypedDict):
+    language_code: typing_extensions.NotRequired[SpeechToTextTranslateLanguage]
+    """
+    Language code
+    """
+
+    model: typing_extensions.NotRequired[SpeechToTextModel]
+    """
+    Model to be used for speech to text
+    """
+
+    with_timestamps: typing_extensions.NotRequired[bool]
+    """
+    Whether to include timestamps in the response
+    """
+
+    with_diarization: typing_extensions.NotRequired[bool]
+    """
+    Enables speaker diarization, which identifies and separates different speakers in the audio. 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 true.
+    """

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/requests/task_detail_v_1.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.task_state import TaskState
+from .task_file_details import TaskFileDetailsParams
+
+
+class TaskDetailV1Params(typing_extensions.TypedDict):
+    inputs: typing_extensions.NotRequired[typing.Sequence[TaskFileDetailsParams]]
+    outputs: typing_extensions.NotRequired[typing.Sequence[TaskFileDetailsParams]]
+    state: typing_extensions.NotRequired[TaskState]
+    error_message: typing_extensions.NotRequired[str]
+    exception_name: typing_extensions.NotRequired[str]

sarvamai/requests/task_file_details.py

@@ -0,0 +1,8 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class TaskFileDetailsParams(typing_extensions.TypedDict):
+    file_name: str
+    file_id: str