sarvamai 0.1.7a0__py3-none-any.whl → 0.1.8a0__py3-none-any.whl

sarvamai/__init__.py

@@ -5,9 +5,8 @@
 from .types import (
     AudioData,
     AudioMessage,
-    BaseJobParameters,
-    BulkJobCallback,
-    BulkJobInitResponseV1,
+    AudioOutput,
+    AudioOutputData,
     ChatCompletionRequestAssistantMessage,
     ChatCompletionRequestMessage,
     ChatCompletionRequestMessage_Assistant,
@@ -17,6 +16,7 @@ from .types import (
     ChatCompletionRequestUserMessage,
     ChatCompletionResponseMessage,
     Choice,
+    CloseConnection,
     CompletionUsage,
     ConfigMessage,
     CreateChatCompletionResponse,
@@ -26,23 +26,27 @@ from .types import (
     ErrorData,
     ErrorDetails,
     ErrorMessage,
+    ErrorResponse,
+    ErrorResponseData,
     EventsData,
-    FileSignedUrlDetails,
-    FilesDownloadResponse,
-    FilesRequest,
-    FilesUploadResponse,
     FinishReason,
     Format,
-    JobState,
-    JobStatusV1,
+    InitializeConnection,
+    InitializeConnectionData,
+    InitializeConnectionDataModel,
+    InitializeConnectionDataOutputAudioBitrate,
+    InitializeConnectionDataSpeaker,
+    InitializeConnectionDataTargetLanguageCode,
     LanguageIdentificationResponse,
     NumeralsFormat,
+    PingSignal,
     ReasoningEffort,
     ResponseType,
     Role,
     SarvamModelIds,
+    SendText,
+    SendTextData,
     SpeechSampleRate,
-    SpeechToTextJobParameters,
     SpeechToTextLanguage,
     SpeechToTextModel,
     SpeechToTextResponse,
@@ -57,10 +61,6 @@ from .types import (
     SpeechToTextTranslateTranscriptionData,
     SpokenFormNumeralsFormat,
     StopConfiguration,
-    StorageContainerType,
-    TaskDetailV1,
-    TaskFileDetails,
-    TaskState,
     TextToSpeechLanguage,
     TextToSpeechModel,
     TextToSpeechResponse,
@@ -89,20 +89,19 @@ from .errors import (
 from . import (
     chat,
     speech_to_text,
-    speech_to_text_job,
     speech_to_text_streaming,
     speech_to_text_translate_streaming,
     text,
     text_to_speech,
+    text_to_speech_streaming,
 )
 from .client import AsyncSarvamAI, SarvamAI
 from .environment import SarvamAIEnvironment
 from .requests import (
     AudioDataParams,
     AudioMessageParams,
-    BaseJobParametersParams,
-    BulkJobCallbackParams,
-    BulkJobInitResponseV1Params,
+    AudioOutputDataParams,
+    AudioOutputParams,
     ChatCompletionRequestAssistantMessageParams,
     ChatCompletionRequestMessageParams,
     ChatCompletionRequestMessage_AssistantParams,
@@ -112,6 +111,7 @@ from .requests import (
     ChatCompletionRequestUserMessageParams,
     ChatCompletionResponseMessageParams,
     ChoiceParams,
+    CloseConnectionParams,
     CompletionUsageParams,
     ConfigMessageParams,
     CreateChatCompletionResponseParams,
@@ -120,14 +120,15 @@ from .requests import (
     ErrorDataParams,
     ErrorDetailsParams,
     ErrorMessageParams,
+    ErrorResponseDataParams,
+    ErrorResponseParams,
     EventsDataParams,
-    FileSignedUrlDetailsParams,
-    FilesDownloadResponseParams,
-    FilesRequestParams,
-    FilesUploadResponseParams,
-    JobStatusV1Params,
+    InitializeConnectionDataParams,
+    InitializeConnectionParams,
     LanguageIdentificationResponseParams,
-    SpeechToTextJobParametersParams,
+    PingSignalParams,
+    SendTextDataParams,
+    SendTextParams,
     SpeechToTextResponseDataParams,
     SpeechToTextResponseParams,
     SpeechToTextStreamingResponseParams,
@@ -137,8 +138,6 @@ from .requests import (
     SpeechToTextTranslateStreamingResponseParams,
     SpeechToTextTranslateTranscriptionDataParams,
     StopConfigurationParams,
-    TaskDetailV1Params,
-    TaskFileDetailsParams,
     TextToSpeechResponseParams,
     TimestampsModelParams,
     TranscriptionMetricsParams,
@@ -164,13 +163,11 @@ __all__ = [
     "AudioDataParams",
     "AudioMessage",
     "AudioMessageParams",
+    "AudioOutput",
+    "AudioOutputData",
+    "AudioOutputDataParams",
+    "AudioOutputParams",
     "BadRequestError",
-    "BaseJobParameters",
-    "BaseJobParametersParams",
-    "BulkJobCallback",
-    "BulkJobCallbackParams",
-    "BulkJobInitResponseV1",
-    "BulkJobInitResponseV1Params",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestAssistantMessageParams",
     "ChatCompletionRequestMessage",
@@ -189,6 +186,8 @@ __all__ = [
     "ChatCompletionResponseMessageParams",
     "Choice",
     "ChoiceParams",
+    "CloseConnection",
+    "CloseConnectionParams",
     "CompletionUsage",
     "CompletionUsageParams",
     "ConfigMessage",
@@ -206,36 +205,41 @@ __all__ = [
     "ErrorDetailsParams",
     "ErrorMessage",
     "ErrorMessageParams",
+    "ErrorResponse",
+    "ErrorResponseData",
+    "ErrorResponseDataParams",
+    "ErrorResponseParams",
     "EventsData",
     "EventsDataParams",
-    "FileSignedUrlDetails",
-    "FileSignedUrlDetailsParams",
-    "FilesDownloadResponse",
-    "FilesDownloadResponseParams",
-    "FilesRequest",
-    "FilesRequestParams",
-    "FilesUploadResponse",
-    "FilesUploadResponseParams",
     "FinishReason",
     "ForbiddenError",
     "Format",
+    "InitializeConnection",
+    "InitializeConnectionData",
+    "InitializeConnectionDataModel",
+    "InitializeConnectionDataOutputAudioBitrate",
+    "InitializeConnectionDataParams",
+    "InitializeConnectionDataSpeaker",
+    "InitializeConnectionDataTargetLanguageCode",
+    "InitializeConnectionParams",
     "InternalServerError",
-    "JobState",
-    "JobStatusV1",
-    "JobStatusV1Params",
     "LanguageIdentificationResponse",
     "LanguageIdentificationResponseParams",
     "NumeralsFormat",
+    "PingSignal",
+    "PingSignalParams",
     "ReasoningEffort",
     "ResponseType",
     "Role",
     "SarvamAI",
     "SarvamAIEnvironment",
     "SarvamModelIds",
+    "SendText",
+    "SendTextData",
+    "SendTextDataParams",
+    "SendTextParams",
     "ServiceUnavailableError",
     "SpeechSampleRate",
-    "SpeechToTextJobParameters",
-    "SpeechToTextJobParametersParams",
     "SpeechToTextLanguage",
     "SpeechToTextModel",
     "SpeechToTextResponse",
@@ -266,12 +270,6 @@ __all__ = [
     "SpokenFormNumeralsFormat",
     "StopConfiguration",
     "StopConfigurationParams",
-    "StorageContainerType",
-    "TaskDetailV1",
-    "TaskDetailV1Params",
-    "TaskFileDetails",
-    "TaskFileDetailsParams",
-    "TaskState",
     "TextToSpeechLanguage",
     "TextToSpeechModel",
     "TextToSpeechResponse",
@@ -298,9 +296,9 @@ __all__ = [
     "__version__",
     "chat",
     "speech_to_text",
-    "speech_to_text_job",
     "speech_to_text_streaming",
     "speech_to_text_translate_streaming",
     "text",
     "text_to_speech",
+    "text_to_speech_streaming",
 ]

sarvamai/client.py

@@ -9,7 +9,6 @@ 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_streaming.client import (
     AsyncSpeechToTextTranslateStreamingClient,
@@ -17,6 +16,7 @@ from .speech_to_text_translate_streaming.client import (
 )
 from .text.client import AsyncTextClient, TextClient
 from .text_to_speech.client import AsyncTextToSpeechClient, TextToSpeechClient
+from .text_to_speech_streaming.client import AsyncTextToSpeechStreamingClient, TextToSpeechStreamingClient
 
 
 class SarvamAI:
@@ -83,11 +83,11 @@ 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_streaming = SpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = SpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper
         )
+        self.text_to_speech_streaming = TextToSpeechStreamingClient(client_wrapper=self._client_wrapper)
 
 
 class AsyncSarvamAI:
@@ -154,8 +154,8 @@ 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_streaming = AsyncSpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = AsyncSpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper
         )
+        self.text_to_speech_streaming = AsyncTextToSpeechStreamingClient(client_wrapper=self._client_wrapper)

sarvamai/core/client_wrapper.py

@@ -17,10 +17,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.7a0",
+            "User-Agent": "sarvamai/0.1.8a0",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.7a0",
+            "X-Fern-SDK-Version": "0.1.8a0",
         }
         headers["api-subscription-key"] = self.api_subscription_key
         return headers

sarvamai/errors/service_unavailable_error.py

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

sarvamai/requests/__init__.py

@@ -4,9 +4,8 @@
 
 from .audio_data import AudioDataParams
 from .audio_message import AudioMessageParams
-from .base_job_parameters import BaseJobParametersParams
-from .bulk_job_callback import BulkJobCallbackParams
-from .bulk_job_init_response_v_1 import BulkJobInitResponseV1Params
+from .audio_output import AudioOutputParams
+from .audio_output_data import AudioOutputDataParams
 from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessageParams
 from .chat_completion_request_message import (
     ChatCompletionRequestMessageParams,
@@ -18,6 +17,7 @@ from .chat_completion_request_system_message import ChatCompletionRequestSystemM
 from .chat_completion_request_user_message import ChatCompletionRequestUserMessageParams
 from .chat_completion_response_message import ChatCompletionResponseMessageParams
 from .choice import ChoiceParams
+from .close_connection import CloseConnectionParams
 from .completion_usage import CompletionUsageParams
 from .config_message import ConfigMessageParams
 from .create_chat_completion_response import CreateChatCompletionResponseParams
@@ -26,14 +26,15 @@ from .diarized_transcript import DiarizedTranscriptParams
 from .error_data import ErrorDataParams
 from .error_details import ErrorDetailsParams
 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 .job_status_v_1 import JobStatusV1Params
+from .initialize_connection import InitializeConnectionParams
+from .initialize_connection_data import InitializeConnectionDataParams
 from .language_identification_response import LanguageIdentificationResponseParams
-from .speech_to_text_job_parameters import SpeechToTextJobParametersParams
+from .ping_signal import PingSignalParams
+from .send_text import SendTextParams
+from .send_text_data import SendTextDataParams
 from .speech_to_text_response import SpeechToTextResponseParams
 from .speech_to_text_response_data import SpeechToTextResponseDataParams
 from .speech_to_text_streaming_response import SpeechToTextStreamingResponseParams
@@ -43,8 +44,6 @@ from .speech_to_text_translate_response_data import SpeechToTextTranslateRespons
 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
@@ -54,9 +53,8 @@ from .transliteration_response import TransliterationResponseParams
 __all__ = [
     "AudioDataParams",
     "AudioMessageParams",
-    "BaseJobParametersParams",
-    "BulkJobCallbackParams",
-    "BulkJobInitResponseV1Params",
+    "AudioOutputDataParams",
+    "AudioOutputParams",
     "ChatCompletionRequestAssistantMessageParams",
     "ChatCompletionRequestMessageParams",
     "ChatCompletionRequestMessage_AssistantParams",
@@ -66,6 +64,7 @@ __all__ = [
     "ChatCompletionRequestUserMessageParams",
     "ChatCompletionResponseMessageParams",
     "ChoiceParams",
+    "CloseConnectionParams",
     "CompletionUsageParams",
     "ConfigMessageParams",
     "CreateChatCompletionResponseParams",
@@ -74,14 +73,15 @@ __all__ = [
     "ErrorDataParams",
     "ErrorDetailsParams",
     "ErrorMessageParams",
+    "ErrorResponseDataParams",
+    "ErrorResponseParams",
     "EventsDataParams",
-    "FileSignedUrlDetailsParams",
-    "FilesDownloadResponseParams",
-    "FilesRequestParams",
-    "FilesUploadResponseParams",
-    "JobStatusV1Params",
+    "InitializeConnectionDataParams",
+    "InitializeConnectionParams",
     "LanguageIdentificationResponseParams",
-    "SpeechToTextJobParametersParams",
+    "PingSignalParams",
+    "SendTextDataParams",
+    "SendTextParams",
     "SpeechToTextResponseDataParams",
     "SpeechToTextResponseParams",
     "SpeechToTextStreamingResponseParams",
@@ -91,8 +91,6 @@ __all__ = [
     "SpeechToTextTranslateStreamingResponseParams",
     "SpeechToTextTranslateTranscriptionDataParams",
     "StopConfigurationParams",
-    "TaskDetailV1Params",
-    "TaskFileDetailsParams",
     "TextToSpeechResponseParams",
     "TimestampsModelParams",
     "TranscriptionMetricsParams",

sarvamai/requests/audio_output.py

@@ -0,0 +1,11 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from .audio_output_data import AudioOutputDataParams
+
+
+class AudioOutputParams(typing_extensions.TypedDict):
+    type: typing.Literal["audio"]
+    data: AudioOutputDataParams

sarvamai/requests/audio_output_data.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class AudioOutputDataParams(typing_extensions.TypedDict):
+    content_type: str
+    """
+    MIME type of the audio content (e.g., 'audio/mp3', 'audio/wav')
+    """
+
+    audio: str
+    """
+    Base64-encoded audio data ready for playback or download
+    """

sarvamai/requests/{files_request.py → close_connection.py}

@@ -5,6 +5,5 @@ import typing
 import typing_extensions
 
 
-class FilesRequestParams(typing_extensions.TypedDict):
-    job_id: str
-    files: typing.Sequence[str]
+class CloseConnectionParams(typing_extensions.TypedDict):
+    type: typing.Literal["flush"]

sarvamai/requests/error_response.py

@@ -0,0 +1,11 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from .error_response_data import ErrorResponseDataParams
+
+
+class ErrorResponseParams(typing_extensions.TypedDict):
+    type: typing.Literal["error"]
+    data: ErrorResponseDataParams

sarvamai/requests/error_response_data.py

@@ -0,0 +1,18 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+
+
+class ErrorResponseDataParams(typing_extensions.TypedDict):
+    message: str
+    code: typing_extensions.NotRequired[int]
+    """
+    Optional error code for programmatic error handling
+    """
+
+    details: typing_extensions.NotRequired[typing.Dict[str, typing.Optional[typing.Any]]]
+    """
+    Additional error details and context information
+    """

sarvamai/requests/initialize_connection.py

@@ -0,0 +1,11 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from .initialize_connection_data import InitializeConnectionDataParams
+
+
+class InitializeConnectionParams(typing_extensions.TypedDict):
+    type: typing.Literal["config"]
+    data: InitializeConnectionDataParams

sarvamai/requests/initialize_connection_data.py

@@ -0,0 +1,24 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.initialize_connection_data_model import InitializeConnectionDataModel
+from ..types.initialize_connection_data_output_audio_bitrate import InitializeConnectionDataOutputAudioBitrate
+from ..types.initialize_connection_data_speaker import InitializeConnectionDataSpeaker
+from ..types.initialize_connection_data_target_language_code import InitializeConnectionDataTargetLanguageCode
+
+
+class InitializeConnectionDataParams(typing_extensions.TypedDict):
+    target_language_code: InitializeConnectionDataTargetLanguageCode
+    speaker: InitializeConnectionDataSpeaker
+    pitch: typing_extensions.NotRequired[float]
+    pace: typing_extensions.NotRequired[float]
+    loudness: typing_extensions.NotRequired[float]
+    speech_sample_rate: typing_extensions.NotRequired[int]
+    enable_preprocessing: typing_extensions.NotRequired[bool]
+    model: InitializeConnectionDataModel
+    output_audio_codec: typing_extensions.NotRequired[typing.Literal["mp3"]]
+    output_audio_bitrate: typing_extensions.NotRequired[InitializeConnectionDataOutputAudioBitrate]
+    min_buffer_size: typing_extensions.NotRequired[int]
+    max_chunk_length: typing_extensions.NotRequired[int]

sarvamai/requests/ping_signal.py

@@ -0,0 +1,9 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+
+
+class PingSignalParams(typing_extensions.TypedDict):
+    type: typing.Literal["ping"]

sarvamai/requests/send_text.py

@@ -0,0 +1,11 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from .send_text_data import SendTextDataParams
+
+
+class SendTextParams(typing_extensions.TypedDict):
+    type: typing.Literal["text"]
+    data: SendTextDataParams

sarvamai/requests/{base_job_parameters.py → send_text_data.py}

@@ -3,5 +3,5 @@
 import typing_extensions
 
 
-class BaseJobParametersParams(typing_extensions.TypedDict):
-    pass
+class SendTextDataParams(typing_extensions.TypedDict):
+    text: str

sarvamai/speech_to_text/raw_client.py

@@ -15,6 +15,7 @@ from ..errors.internal_server_error import InternalServerError
 from ..errors.service_unavailable_error import ServiceUnavailableError
 from ..errors.too_many_requests_error import TooManyRequestsError
 from ..errors.unprocessable_entity_error import UnprocessableEntityError
+from ..types.error_message import ErrorMessage
 from ..types.speech_to_text_language import SpeechToTextLanguage
 from ..types.speech_to_text_model import SpeechToTextModel
 from ..types.speech_to_text_response import SpeechToTextResponse
@@ -160,9 +161,9 @@ class RawSpeechToTextClient:
                 raise ServiceUnavailableError(
                     headers=dict(_response.headers),
                     body=typing.cast(
-                        typing.Optional[typing.Any],
+                        ErrorMessage,
                         parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
+                            type_=ErrorMessage,  # type: ignore
                             object_=_response.json(),
                         ),
                     ),
@@ -298,9 +299,9 @@ class RawSpeechToTextClient:
                 raise ServiceUnavailableError(
                     headers=dict(_response.headers),
                     body=typing.cast(
-                        typing.Optional[typing.Any],
+                        ErrorMessage,
                         parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
+                            type_=ErrorMessage,  # type: ignore
                             object_=_response.json(),
                         ),
                     ),
@@ -446,9 +447,9 @@ class AsyncRawSpeechToTextClient:
                 raise ServiceUnavailableError(
                     headers=dict(_response.headers),
                     body=typing.cast(
-                        typing.Optional[typing.Any],
+                        ErrorMessage,
                         parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
+                            type_=ErrorMessage,  # type: ignore
                             object_=_response.json(),
                         ),
                     ),
@@ -584,9 +585,9 @@ class AsyncRawSpeechToTextClient:
                 raise ServiceUnavailableError(
                     headers=dict(_response.headers),
                     body=typing.cast(
-                        typing.Optional[typing.Any],
+                        ErrorMessage,
                         parse_obj_as(
-                            type_=typing.Optional[typing.Any],  # type: ignore
+                            type_=ErrorMessage,  # type: ignore
                             object_=_response.json(),
                         ),
                     ),