sarvamai 0.1.23a3__py3-none-any.whl → 0.1.23a4__py3-none-any.whl

sarvamai/errors/__init__.py

@@ -2,46 +2,12 @@
 
 # isort: skip_file
 
-import typing
-from importlib import import_module
-
-if typing.TYPE_CHECKING:
-    from .bad_request_error import BadRequestError
-    from .forbidden_error import ForbiddenError
-    from .internal_server_error import InternalServerError
-    from .service_unavailable_error import ServiceUnavailableError
-    from .too_many_requests_error import TooManyRequestsError
-    from .unprocessable_entity_error import UnprocessableEntityError
-_dynamic_imports: typing.Dict[str, str] = {
-    "BadRequestError": ".bad_request_error",
-    "ForbiddenError": ".forbidden_error",
-    "InternalServerError": ".internal_server_error",
-    "ServiceUnavailableError": ".service_unavailable_error",
-    "TooManyRequestsError": ".too_many_requests_error",
-    "UnprocessableEntityError": ".unprocessable_entity_error",
-}
-
-
-def __getattr__(attr_name: str) -> typing.Any:
-    module_name = _dynamic_imports.get(attr_name)
-    if module_name is None:
-        raise AttributeError(f"No {attr_name} found in _dynamic_imports for module name -> {__name__}")
-    try:
-        module = import_module(module_name, __package__)
-        if module_name == f".{attr_name}":
-            return module
-        else:
-            return getattr(module, attr_name)
-    except ImportError as e:
-        raise ImportError(f"Failed to import {attr_name} from {module_name}: {e}") from e
-    except AttributeError as e:
-        raise AttributeError(f"Failed to get {attr_name} from {module_name}: {e}") from e
-
-
-def __dir__():
-    lazy_attrs = list(_dynamic_imports.keys())
-    return sorted(lazy_attrs)
-
+from .bad_request_error import BadRequestError
+from .forbidden_error import ForbiddenError
+from .internal_server_error import InternalServerError
+from .service_unavailable_error import ServiceUnavailableError
+from .too_many_requests_error import TooManyRequestsError
+from .unprocessable_entity_error import UnprocessableEntityError
 
 __all__ = [
     "BadRequestError",

sarvamai/errors/bad_request_error.py

@@ -6,5 +6,5 @@ from ..core.api_error import ApiError
 
 
 class BadRequestError(ApiError):
-    def __init__(self, body: typing.Any, 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=400, headers=headers, body=body)

sarvamai/errors/forbidden_error.py

@@ -6,5 +6,5 @@ from ..core.api_error import ApiError
 
 
 class ForbiddenError(ApiError):
-    def __init__(self, body: typing.Any, 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=403, headers=headers, body=body)

sarvamai/errors/internal_server_error.py

@@ -6,5 +6,5 @@ from ..core.api_error import ApiError
 
 
 class InternalServerError(ApiError):
-    def __init__(self, body: typing.Any, 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=500, headers=headers, body=body)

sarvamai/errors/service_unavailable_error.py

@@ -6,5 +6,5 @@ from ..core.api_error import ApiError
 
 
 class ServiceUnavailableError(ApiError):
-    def __init__(self, body: typing.Any, 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/errors/too_many_requests_error.py

@@ -6,5 +6,5 @@ from ..core.api_error import ApiError
 
 
 class TooManyRequestsError(ApiError):
-    def __init__(self, body: typing.Any, 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=429, headers=headers, body=body)

sarvamai/errors/unprocessable_entity_error.py

@@ -6,5 +6,5 @@ from ..core.api_error import ApiError
 
 
 class UnprocessableEntityError(ApiError):
-    def __init__(self, body: typing.Any, 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=422, headers=headers, body=body)

sarvamai/requests/__init__.py

@@ -2,156 +2,68 @@
 
 # isort: skip_file
 
-import typing
-from importlib import import_module
-
-if typing.TYPE_CHECKING:
-    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,
-        ChatCompletionRequestMessage_AssistantParams,
-        ChatCompletionRequestMessage_SystemParams,
-        ChatCompletionRequestMessage_UserParams,
-    )
-    from .chat_completion_request_system_message import ChatCompletionRequestSystemMessageParams
-    from .chat_completion_request_user_message import ChatCompletionRequestUserMessageParams
-    from .chat_completion_response_message import ChatCompletionResponseMessageParams
-    from .choice import ChoiceParams
-    from .completion_usage import CompletionUsageParams
-    from .config_message import ConfigMessageParams
-    from .configure_connection import ConfigureConnectionParams
-    from .configure_connection_data import ConfigureConnectionDataParams
-    from .create_chat_completion_response import CreateChatCompletionResponseParams
-    from .diarized_entry import DiarizedEntryParams
-    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 .event_response import EventResponseParams
-    from .event_response_data import EventResponseDataParams
-    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_response import JobStatusV1ResponseParams
-    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 .stt_flush_signal import SttFlushSignalParams
-    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
-    from .translation_response import TranslationResponseParams
-    from .transliteration_response import TransliterationResponseParams
-_dynamic_imports: typing.Dict[str, str] = {
-    "AudioDataParams": ".audio_data",
-    "AudioMessageParams": ".audio_message",
-    "AudioOutputDataParams": ".audio_output_data",
-    "AudioOutputParams": ".audio_output",
-    "BaseJobParametersParams": ".base_job_parameters",
-    "BulkJobCallbackParams": ".bulk_job_callback",
-    "BulkJobInitResponseV1Params": ".bulk_job_init_response_v_1",
-    "ChatCompletionRequestAssistantMessageParams": ".chat_completion_request_assistant_message",
-    "ChatCompletionRequestMessageParams": ".chat_completion_request_message",
-    "ChatCompletionRequestMessage_AssistantParams": ".chat_completion_request_message",
-    "ChatCompletionRequestMessage_SystemParams": ".chat_completion_request_message",
-    "ChatCompletionRequestMessage_UserParams": ".chat_completion_request_message",
-    "ChatCompletionRequestSystemMessageParams": ".chat_completion_request_system_message",
-    "ChatCompletionRequestUserMessageParams": ".chat_completion_request_user_message",
-    "ChatCompletionResponseMessageParams": ".chat_completion_response_message",
-    "ChoiceParams": ".choice",
-    "CompletionUsageParams": ".completion_usage",
-    "ConfigMessageParams": ".config_message",
-    "ConfigureConnectionDataParams": ".configure_connection_data",
-    "ConfigureConnectionParams": ".configure_connection",
-    "CreateChatCompletionResponseParams": ".create_chat_completion_response",
-    "DiarizedEntryParams": ".diarized_entry",
-    "DiarizedTranscriptParams": ".diarized_transcript",
-    "ErrorDataParams": ".error_data",
-    "ErrorDetailsParams": ".error_details",
-    "ErrorMessageParams": ".error_message",
-    "ErrorResponseDataParams": ".error_response_data",
-    "ErrorResponseParams": ".error_response",
-    "EventResponseDataParams": ".event_response_data",
-    "EventResponseParams": ".event_response",
-    "EventsDataParams": ".events_data",
-    "FileSignedUrlDetailsParams": ".file_signed_url_details",
-    "FilesDownloadResponseParams": ".files_download_response",
-    "FilesRequestParams": ".files_request",
-    "FilesUploadResponseParams": ".files_upload_response",
-    "FlushSignalParams": ".flush_signal",
-    "JobStatusV1ResponseParams": ".job_status_v_1_response",
-    "LanguageIdentificationResponseParams": ".language_identification_response",
-    "PingSignalParams": ".ping_signal",
-    "SendTextDataParams": ".send_text_data",
-    "SendTextParams": ".send_text",
-    "SpeechToTextJobParametersParams": ".speech_to_text_job_parameters",
-    "SpeechToTextResponseDataParams": ".speech_to_text_response_data",
-    "SpeechToTextResponseParams": ".speech_to_text_response",
-    "SpeechToTextStreamingResponseParams": ".speech_to_text_streaming_response",
-    "SpeechToTextTranscriptionDataParams": ".speech_to_text_transcription_data",
-    "SpeechToTextTranslateJobParametersParams": ".speech_to_text_translate_job_parameters",
-    "SpeechToTextTranslateResponseDataParams": ".speech_to_text_translate_response_data",
-    "SpeechToTextTranslateResponseParams": ".speech_to_text_translate_response",
-    "SpeechToTextTranslateStreamingResponseParams": ".speech_to_text_translate_streaming_response",
-    "SpeechToTextTranslateTranscriptionDataParams": ".speech_to_text_translate_transcription_data",
-    "StopConfigurationParams": ".stop_configuration",
-    "SttFlushSignalParams": ".stt_flush_signal",
-    "TaskDetailV1Params": ".task_detail_v_1",
-    "TaskFileDetailsParams": ".task_file_details",
-    "TextToSpeechResponseParams": ".text_to_speech_response",
-    "TimestampsModelParams": ".timestamps_model",
-    "TranscriptionMetricsParams": ".transcription_metrics",
-    "TranslationResponseParams": ".translation_response",
-    "TransliterationResponseParams": ".transliteration_response",
-}
-
-
-def __getattr__(attr_name: str) -> typing.Any:
-    module_name = _dynamic_imports.get(attr_name)
-    if module_name is None:
-        raise AttributeError(f"No {attr_name} found in _dynamic_imports for module name -> {__name__}")
-    try:
-        module = import_module(module_name, __package__)
-        if module_name == f".{attr_name}":
-            return module
-        else:
-            return getattr(module, attr_name)
-    except ImportError as e:
-        raise ImportError(f"Failed to import {attr_name} from {module_name}: {e}") from e
-    except AttributeError as e:
-        raise AttributeError(f"Failed to get {attr_name} from {module_name}: {e}") from e
-
-
-def __dir__():
-    lazy_attrs = list(_dynamic_imports.keys())
-    return sorted(lazy_attrs)
-
+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,
+    ChatCompletionRequestMessage_AssistantParams,
+    ChatCompletionRequestMessage_SystemParams,
+    ChatCompletionRequestMessage_UserParams,
+)
+from .chat_completion_request_system_message import ChatCompletionRequestSystemMessageParams
+from .chat_completion_request_user_message import ChatCompletionRequestUserMessageParams
+from .chat_completion_response_message import ChatCompletionResponseMessageParams
+from .choice import ChoiceParams
+from .completion_usage import CompletionUsageParams
+from .config_message import ConfigMessageParams
+from .configure_connection import ConfigureConnectionParams
+from .configure_connection_data import ConfigureConnectionDataParams
+from .create_chat_completion_response import CreateChatCompletionResponseParams
+from .diarized_entry import DiarizedEntryParams
+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 .event_response import EventResponseParams
+from .event_response_data import EventResponseDataParams
+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_response import JobStatusV1ResponseParams
+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 .stt_flush_signal import SttFlushSignalParams
+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
+from .translation_response import TranslationResponseParams
+from .transliteration_response import TransliterationResponseParams
 
 __all__ = [
     "AudioDataParams",

sarvamai/requests/configure_connection.py

@@ -12,6 +12,10 @@ class ConfigureConnectionParams(typing_extensions.TypedDict):
     This initializes TTS parameters and can be updated at any time during the WebSocket lifecycle
     by sending a new config message. When a config update is sent, any text currently in the buffer
     will be automatically flushed and processed before applying the new configuration.
+
+    **Model-Specific Notes:**
+    - **bulbul:v2:** Supports pitch, loudness, pace (0.3-3.0). Default sample rate: 22050 Hz.
+    - **bulbul:v3-beta:** Does NOT support pitch/loudness. Pace range: 0.5-2.0. Supports temperature. Default sample rate: 24000 Hz.
     """
 
     type: typing.Literal["config"]

sarvamai/requests/configure_connection_data.py

@@ -1,6 +1,7 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing_extensions
+from ..types.configure_connection_data_model import ConfigureConnectionDataModel
 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
@@ -8,21 +9,25 @@ from ..types.configure_connection_data_target_language_code import ConfigureConn
 
 
 class ConfigureConnectionDataParams(typing_extensions.TypedDict):
+    model: typing_extensions.NotRequired[ConfigureConnectionDataModel]
+    """
+    Specifies the model to use for text-to-speech conversion.
+    - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
+    - **bulbul:v3-beta**: Advanced model with temperature control (no pitch/loudness)
+    """
+
     target_language_code: ConfigureConnectionDataTargetLanguageCode
     """
-    The language of the text is BCP-47 format
+    The language of the text in BCP-47 format
     """
 
     speaker: ConfigureConnectionDataSpeaker
     """
     The speaker voice to be used for the output audio.
     
-    **Default:** Anushka
-    
-    **Model Compatibility (Speakers compatible with respective model):**
-    - **bulbul:v2:**
-      - Female: Anushka, Manisha, Vidya, Arya
-      - Male: Abhilash, Karun, Hitesh
+    **Model Compatibility:**
+    - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
+    - **bulbul:v3-beta:** aditya (default), ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, shubh, ashutosh, advait, amelia, sophia
     
     **Note:** Speaker selection must match the chosen model version.
     """
@@ -32,13 +37,18 @@ class ConfigureConnectionDataParams(typing_extensions.TypedDict):
     Controls the pitch of the audio. Lower values result in a deeper voice, 
     while higher values make it sharper. The suitable range is between -0.75 
     and 0.75. Default is 0.0.
+    
+    **Note:** NOT supported for bulbul:v3-beta. Will be ignored if provided.
     """
 
     pace: typing_extensions.NotRequired[float]
     """
     Controls the speed of the audio. Lower values result in slower speech, 
-    while higher values make it faster. The suitable range is between 0.5 
-    and 2.0. Default is 1.0.
+    while higher values make it faster. Default is 1.0.
+    
+    **Model-specific ranges:**
+    - **bulbul:v2:** 0.3 to 3.0
+    - **bulbul:v3-beta:** 0.5 to 2.0
     """
 
     loudness: typing_extensions.NotRequired[float]
@@ -46,19 +56,38 @@ class ConfigureConnectionDataParams(typing_extensions.TypedDict):
     Controls the loudness of the audio. Lower values result in quieter audio, 
     while higher values make it louder. The suitable range is between 0.3 
     and 3.0. Default is 1.0.
+    
+    **Note:** NOT supported for bulbul:v3-beta. Will be ignored if provided.
+    """
+
+    temperature: typing_extensions.NotRequired[float]
+    """
+    Controls the randomness of the output. Lower values make the output more 
+    focused and deterministic, while higher values make it more random. 
+    The suitable range is between 0.01 and 1.0. Default is 0.6.
+    
+    **Note:** Only supported for bulbul:v3-beta. Will be ignored for bulbul:v2.
     """
 
     speech_sample_rate: typing_extensions.NotRequired[int]
     """
     Specifies the sample rate of the output audio. Supported values are 
-    8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+    8000, 16000, 22050, 24000 Hz.
+    
+    **Model-specific defaults:**
+    - **bulbul:v2:** 22050 Hz
+    - **bulbul:v3-beta:** 24000 Hz
     """
 
     enable_preprocessing: typing_extensions.NotRequired[bool]
     """
     Controls whether normalization of English words and numeric entities 
     (e.g., numbers, dates) is performed. Set to true for better handling 
-    of mixed-language text. Default is false.
+    of mixed-language text.
+    
+    **Model-specific defaults:**
+    - **bulbul:v2:** false (optional)
+    - **bulbul:v3-beta:** Always enabled (cannot be disabled)
     """
 
     output_audio_codec: typing_extensions.NotRequired[ConfigureConnectionDataOutputAudioCodec]

sarvamai/requests/error_response_data.py

@@ -12,7 +12,7 @@ class ErrorResponseDataParams(typing_extensions.TypedDict):
     Optional error code for programmatic error handling
     """
 
-    details: typing_extensions.NotRequired[typing.Dict[str, typing.Any]]
+    details: typing_extensions.NotRequired[typing.Dict[str, typing.Optional[typing.Any]]]
     """
     Additional error details and context information
     """

sarvamai/requests/file_signed_url_details.py

@@ -7,4 +7,4 @@ import typing_extensions
 
 class FileSignedUrlDetailsParams(typing_extensions.TypedDict):
     file_url: str
-    file_metadata: typing_extensions.NotRequired[typing.Dict[str, typing.Any]]
+    file_metadata: typing_extensions.NotRequired[typing.Dict[str, typing.Optional[typing.Any]]]

sarvamai/requests/speech_to_text_job_parameters.py

@@ -1,6 +1,7 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing_extensions
+from ..types.mode import Mode
 from ..types.speech_to_text_model import SpeechToTextModel
 from ..types.speech_to_text_translate_language import SpeechToTextTranslateLanguage
 
@@ -13,7 +14,15 @@ class SpeechToTextJobParametersParams(typing_extensions.TypedDict):
 
     model: typing_extensions.NotRequired[SpeechToTextModel]
     """
-    Model to be used for speech to text
+    Model to be used for speech to text.
+    - **saarika:v2.5** (default)
+    - **saarika:v3**: Advanced transcription model
+    - **saaras:v3**: Advanced model with multiple modes
+    """
+
+    mode: typing_extensions.NotRequired[Mode]
+    """
+    Mode of operation. Only applicable for saaras:v3 model.
     """
 
     with_timestamps: typing_extensions.NotRequired[bool]

sarvamai/requests/speech_to_text_transcription_data.py

@@ -17,12 +17,12 @@ class SpeechToTextTranscriptionDataParams(typing_extensions.TypedDict):
     Transcript of the provided speech in original language
     """
 
-    timestamps: typing_extensions.NotRequired[typing.Dict[str, typing.Any]]
+    timestamps: typing_extensions.NotRequired[typing.Dict[str, typing.Optional[typing.Any]]]
     """
     Timestamp information (if available)
     """
 
-    diarized_transcript: typing_extensions.NotRequired[typing.Dict[str, typing.Any]]
+    diarized_transcript: typing_extensions.NotRequired[typing.Dict[str, typing.Optional[typing.Any]]]
     """
     Diarized transcript of the provided speech
     """

sarvamai/speech_to_text/client.py

@@ -6,6 +6,7 @@ from .. import core
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from ..types.input_audio_codec import InputAudioCodec
+from ..types.mode import Mode
 from ..types.speech_to_text_language import SpeechToTextLanguage
 from ..types.speech_to_text_model import SpeechToTextModel
 from ..types.speech_to_text_response import SpeechToTextResponse
@@ -37,6 +38,7 @@ class SpeechToTextClient:
         *,
         file: core.File,
         model: typing.Optional[SpeechToTextModel] = OMIT,
+        mode: typing.Optional[Mode] = OMIT,
         language_code: typing.Optional[SpeechToTextLanguage] = OMIT,
         input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
@@ -63,7 +65,18 @@ class SpeechToTextClient:
 
         model : typing.Optional[SpeechToTextModel]
             Specifies the model to use for speech-to-text conversion.
-            Note:- Default model is `saarika:v2.5`
+            - **saarika:v2.5** (default): Standard transcription model
+            - **saarika:v3**: Advanced transcription model
+            - **saaras:v3**: Advanced model with multiple output modes
+
+        mode : typing.Optional[Mode]
+            Mode of operation. **Only applicable when using saaras:v3 model.**
+            - **transcribe** (default): Standard transcription
+            - **translate**: Translation to English
+            - **indic-en**: Indic to English translation
+            - **verbatim**: Exact transcription
+            - **translit**: Transliteration to Latin script
+            - **codemix**: Code-mixed output
 
         language_code : typing.Optional[SpeechToTextLanguage]
             Specifies the language of the input audio.
@@ -93,6 +106,7 @@ class SpeechToTextClient:
         _response = self._raw_client.transcribe(
             file=file,
             model=model,
+            mode=mode,
             language_code=language_code,
             input_audio_codec=input_audio_codec,
             request_options=request_options,
@@ -180,6 +194,7 @@ class AsyncSpeechToTextClient:
         *,
         file: core.File,
         model: typing.Optional[SpeechToTextModel] = OMIT,
+        mode: typing.Optional[Mode] = OMIT,
         language_code: typing.Optional[SpeechToTextLanguage] = OMIT,
         input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
@@ -206,7 +221,18 @@ class AsyncSpeechToTextClient:
 
         model : typing.Optional[SpeechToTextModel]
             Specifies the model to use for speech-to-text conversion.
-            Note:- Default model is `saarika:v2.5`
+            - **saarika:v2.5** (default): Standard transcription model
+            - **saarika:v3**: Advanced transcription model
+            - **saaras:v3**: Advanced model with multiple output modes
+
+        mode : typing.Optional[Mode]
+            Mode of operation. **Only applicable when using saaras:v3 model.**
+            - **transcribe** (default): Standard transcription
+            - **translate**: Translation to English
+            - **indic-en**: Indic to English translation
+            - **verbatim**: Exact transcription
+            - **translit**: Transliteration to Latin script
+            - **codemix**: Code-mixed output
 
         language_code : typing.Optional[SpeechToTextLanguage]
             Specifies the language of the input audio.
@@ -244,6 +270,7 @@ class AsyncSpeechToTextClient:
         _response = await self._raw_client.transcribe(
             file=file,
             model=model,
+            mode=mode,
             language_code=language_code,
             input_audio_codec=input_audio_codec,
             request_options=request_options,