sarvamai 0.1.8rc5__py3-none-any.whl → 0.1.8rc7__py3-none-any.whl

sarvamai/__init__.py

@@ -18,6 +18,11 @@ from .types import (
     Choice,
     CompletionUsage,
     ConfigMessage,
+    ConfigureConnection,
+    ConfigureConnectionData,
+    ConfigureConnectionDataOutputAudioBitrate,
+    ConfigureConnectionDataSpeaker,
+    ConfigureConnectionDataTargetLanguageCode,
     CreateChatCompletionResponse,
     DiarizedEntry,
     DiarizedTranscript,
@@ -31,11 +36,6 @@ from .types import (
     FinishReason,
     FlushSignal,
     Format,
-    InitializeConnection,
-    InitializeConnectionData,
-    InitializeConnectionDataOutputAudioBitrate,
-    InitializeConnectionDataSpeaker,
-    InitializeConnectionDataTargetLanguageCode,
     LanguageIdentificationResponse,
     NumeralsFormat,
     PingSignal,
@@ -112,6 +112,8 @@ from .requests import (
     ChoiceParams,
     CompletionUsageParams,
     ConfigMessageParams,
+    ConfigureConnectionDataParams,
+    ConfigureConnectionParams,
     CreateChatCompletionResponseParams,
     DiarizedEntryParams,
     DiarizedTranscriptParams,
@@ -122,8 +124,6 @@ from .requests import (
     ErrorResponseParams,
     EventsDataParams,
     FlushSignalParams,
-    InitializeConnectionDataParams,
-    InitializeConnectionParams,
     LanguageIdentificationResponseParams,
     PingSignalParams,
     SendTextDataParams,
@@ -154,7 +154,6 @@ from .speech_to_text_translate_streaming import (
     SpeechToTextTranslateStreamingModel,
     SpeechToTextTranslateStreamingVadSignals,
 )
-from .text_to_speech_streaming import TextToSpeechStreamingModel
 from .version import __version__
 
 __all__ = [
@@ -190,6 +189,13 @@ __all__ = [
     "CompletionUsageParams",
     "ConfigMessage",
     "ConfigMessageParams",
+    "ConfigureConnection",
+    "ConfigureConnectionData",
+    "ConfigureConnectionDataOutputAudioBitrate",
+    "ConfigureConnectionDataParams",
+    "ConfigureConnectionDataSpeaker",
+    "ConfigureConnectionDataTargetLanguageCode",
+    "ConfigureConnectionParams",
     "CreateChatCompletionResponse",
     "CreateChatCompletionResponseParams",
     "DiarizedEntry",
@@ -214,13 +220,6 @@ __all__ = [
     "FlushSignalParams",
     "ForbiddenError",
     "Format",
-    "InitializeConnection",
-    "InitializeConnectionData",
-    "InitializeConnectionDataOutputAudioBitrate",
-    "InitializeConnectionDataParams",
-    "InitializeConnectionDataSpeaker",
-    "InitializeConnectionDataTargetLanguageCode",
-    "InitializeConnectionParams",
     "InternalServerError",
     "LanguageIdentificationResponse",
     "LanguageIdentificationResponseParams",
@@ -274,7 +273,6 @@ __all__ = [
     "TextToSpeechResponse",
     "TextToSpeechResponseParams",
     "TextToSpeechSpeaker",
-    "TextToSpeechStreamingModel",
     "TimestampsModel",
     "TimestampsModelParams",
     "TooManyRequestsError",

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/0.1.8rc5",
+            "User-Agent": "sarvamai/0.1.8rc7",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.8rc5",
+            "X-Fern-SDK-Version": "0.1.8rc7",
         }
         headers["api-subscription-key"] = self.api_subscription_key
         return headers

sarvamai/requests/__init__.py

@@ -19,6 +19,8 @@ from .chat_completion_response_message import ChatCompletionResponseMessageParam
 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
@@ -29,8 +31,6 @@ from .error_response import ErrorResponseParams
 from .error_response_data import ErrorResponseDataParams
 from .events_data import EventsDataParams
 from .flush_signal import FlushSignalParams
-from .initialize_connection import InitializeConnectionParams
-from .initialize_connection_data import InitializeConnectionDataParams
 from .language_identification_response import LanguageIdentificationResponseParams
 from .ping_signal import PingSignalParams
 from .send_text import SendTextParams
@@ -66,6 +66,8 @@ __all__ = [
     "ChoiceParams",
     "CompletionUsageParams",
     "ConfigMessageParams",
+    "ConfigureConnectionDataParams",
+    "ConfigureConnectionParams",
     "CreateChatCompletionResponseParams",
     "DiarizedEntryParams",
     "DiarizedTranscriptParams",
@@ -76,8 +78,6 @@ __all__ = [
     "ErrorResponseParams",
     "EventsDataParams",
     "FlushSignalParams",
-    "InitializeConnectionDataParams",
-    "InitializeConnectionParams",
     "LanguageIdentificationResponseParams",
     "PingSignalParams",
     "SendTextDataParams",

sarvamai/requests/configure_connection.py

@@ -0,0 +1,18 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from .configure_connection_data import ConfigureConnectionDataParams
+
+
+class ConfigureConnectionParams(typing_extensions.TypedDict):
+    """
+    Configuration message required as the first message after establishing the WebSocket connection.
+    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.
+    """
+
+    type: typing.Literal["config"]
+    data: ConfigureConnectionDataParams

sarvamai/requests/configure_connection_data.py

@@ -0,0 +1,83 @@
+# 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_speaker import ConfigureConnectionDataSpeaker
+from ..types.configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
+
+
+class ConfigureConnectionDataParams(typing_extensions.TypedDict):
+    target_language_code: ConfigureConnectionDataTargetLanguageCode
+    """
+    The language of the text is 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
+    
+    **Note:** Speaker selection must match the chosen model version.
+    """
+
+    pitch: typing_extensions.NotRequired[float]
+    """
+    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.
+    """
+
+    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.
+    """
+
+    loudness: typing_extensions.NotRequired[float]
+    """
+    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.
+    """
+
+    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.
+    """
+
+    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.
+    """
+
+    output_audio_codec: typing_extensions.NotRequired[typing.Literal["mp3"]]
+    """
+    Audio codec (currently supports MP3 only, optimized for real-time playback)
+    """
+
+    output_audio_bitrate: typing_extensions.NotRequired[ConfigureConnectionDataOutputAudioBitrate]
+    """
+    Audio bitrate (choose from 5 supported bitrate options)
+    """
+
+    min_buffer_size: typing_extensions.NotRequired[int]
+    """
+    Minimum character length that triggers buffer flushing for TTS model processing
+    """
+
+    max_chunk_length: typing_extensions.NotRequired[int]
+    """
+    Maximum length for sentence splitting (adjust based on content length)
+    """

sarvamai/requests/flush_signal.py

@@ -6,4 +6,9 @@ import typing_extensions
 
 
 class FlushSignalParams(typing_extensions.TypedDict):
+    """
+    Forces the text buffer to process immediately, regardless of the min_buffer_size threshold.
+    Use this when you need to process remaining text that hasn't reached the minimum buffer size.
+    """
+
     type: typing.Literal["flush"]

sarvamai/requests/ping_signal.py

@@ -6,4 +6,9 @@ import typing_extensions
 
 
 class PingSignalParams(typing_extensions.TypedDict):
+    """
+    Send ping signal to keep the WebSocket connection alive. The connection automatically
+    closes after one minute of inactivity.
+    """
+
     type: typing.Literal["ping"]

sarvamai/text_to_speech_streaming/__init__.py

@@ -2,6 +2,3 @@
 
 # isort: skip_file
 
-from .types import TextToSpeechStreamingModel
-
-__all__ = ["TextToSpeechStreamingModel"]

sarvamai/text_to_speech_streaming/client.py

@@ -11,7 +11,6 @@ from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from .raw_client import AsyncRawTextToSpeechStreamingClient, RawTextToSpeechStreamingClient
 from .socket_client import AsyncTextToSpeechStreamingSocketClient, TextToSpeechStreamingSocketClient
-from .types.text_to_speech_streaming_model import TextToSpeechStreamingModel
 
 
 class TextToSpeechStreamingClient:
@@ -33,7 +32,7 @@ class TextToSpeechStreamingClient:
     def connect(
         self,
         *,
-        model: typing.Optional[TextToSpeechStreamingModel] = None,
+        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[TextToSpeechStreamingSocketClient]:
@@ -43,7 +42,7 @@ class TextToSpeechStreamingClient:
 
         Parameters
         ----------
-        model : typing.Optional[TextToSpeechStreamingModel]
+        model : typing.Optional[typing.Literal["bulbul:v2"]]
             Text to speech model to use
 
         api_subscription_key : typing.Optional[str]
@@ -103,7 +102,7 @@ class AsyncTextToSpeechStreamingClient:
     async def connect(
         self,
         *,
-        model: typing.Optional[TextToSpeechStreamingModel] = None,
+        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncTextToSpeechStreamingSocketClient]:
@@ -113,7 +112,7 @@ class AsyncTextToSpeechStreamingClient:
 
         Parameters
         ----------
-        model : typing.Optional[TextToSpeechStreamingModel]
+        model : typing.Optional[typing.Literal["bulbul:v2"]]
             Text to speech model to use
 
         api_subscription_key : typing.Optional[str]

sarvamai/text_to_speech_streaming/raw_client.py

@@ -10,7 +10,6 @@ from ..core.api_error import ApiError
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from .socket_client import AsyncTextToSpeechStreamingSocketClient, TextToSpeechStreamingSocketClient
-from .types.text_to_speech_streaming_model import TextToSpeechStreamingModel
 
 
 class RawTextToSpeechStreamingClient:
@@ -21,7 +20,7 @@ class RawTextToSpeechStreamingClient:
     def connect(
         self,
         *,
-        model: typing.Optional[TextToSpeechStreamingModel] = None,
+        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[TextToSpeechStreamingSocketClient]:
@@ -31,7 +30,7 @@ class RawTextToSpeechStreamingClient:
 
         Parameters
         ----------
-        model : typing.Optional[TextToSpeechStreamingModel]
+        model : typing.Optional[typing.Literal["bulbul:v2"]]
             Text to speech model to use
 
         api_subscription_key : typing.Optional[str]
@@ -80,7 +79,7 @@ class AsyncRawTextToSpeechStreamingClient:
     async def connect(
         self,
         *,
-        model: typing.Optional[TextToSpeechStreamingModel] = None,
+        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncTextToSpeechStreamingSocketClient]:
@@ -90,7 +89,7 @@ class AsyncRawTextToSpeechStreamingClient:
 
         Parameters
         ----------
-        model : typing.Optional[TextToSpeechStreamingModel]
+        model : typing.Optional[typing.Literal["bulbul:v2"]]
             Text to speech model to use
 
         api_subscription_key : typing.Optional[str]

sarvamai/text_to_speech_streaming/socket_client.py

@@ -10,8 +10,8 @@ from ..core.pydantic_utilities import parse_obj_as
 from ..types.audio_output import AudioOutput
 from ..types.flush_signal import FlushSignal
 from ..types.error_response import ErrorResponse
-from ..types.initialize_connection import InitializeConnection
-from ..types.initialize_connection_data import InitializeConnectionData
+from ..types.configure_connection import ConfigureConnection
+from ..types.configure_connection_data import ConfigureConnectionData
 from ..types.ping_signal import PingSignal
 from ..types.send_text import SendText
 from ..types.send_text_data import SendTextData
@@ -54,10 +54,10 @@ class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
         finally:
             self._emit(EventType.CLOSE, None)
 
-    async def initialize_connection(
+    async def configure(
         self,
         target_language_code: str,
-        speaker: str,
+        speaker: str = "anushka",
         pitch: float = 0.0,
         pace: float = 1.0,
         loudness: float = 1.0,
@@ -69,21 +69,35 @@ class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
         max_chunk_length: int = 150,
     ) -> None:
         """
-        Initialize the TTS connection with configuration parameters.
+        Configuration message required as the first message after establishing the WebSocket connection.
+        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.
 
-        :param target_language_code: Target language code (e.g., 'hi-IN')
-        :param speaker: Voice speaker name (e.g., 'meera', 'arvind')
-        :param pitch: Voice pitch adjustment (-1.0 to 1.0, default: 0.0)
-        :param pace: Speech pace (0.3 to 3.0, default: 1.0)
-        :param loudness: Voice loudness (0.1 to 3.0, default: 1.0)
-        :param speech_sample_rate: Audio sample rate, default: 22050
-        :param enable_preprocessing: Enable text preprocessing, default: False
-        :param output_audio_codec: Audio codec, default: 'mp3'
-        :param output_audio_bitrate: Audio bitrate, default: '128k'
-        :param min_buffer_size: Minimum buffer size, default: 50
-        :param max_chunk_length: Maximum chunk length, default: 150
-        """
-        data = InitializeConnectionData(
+        :param target_language_code: The language of the text is BCP-47 format
+        :param speaker: The speaker voice to be used for the output audio. Default: Anushka.
+            Model Compatibility (bulbul:v2): Female: Anushka, Manisha, Vidya, Arya;
+            Male: Abhilash, Karun, Hitesh
+        :param pitch: 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.
+        :param pace: 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.
+        :param loudness: 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.
+        :param speech_sample_rate: Specifies the sample rate of the output audio. Supported values are
+            8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+        :param enable_preprocessing: 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.
+        :param output_audio_codec: Audio codec (currently supports MP3 only, optimized for real-time playback)
+        :param output_audio_bitrate: Audio bitrate (choose from 5 supported bitrate options)
+        :param min_buffer_size: Minimum character length that triggers buffer flushing for TTS model processing
+        :param max_chunk_length: Maximum length for sentence splitting (adjust based on content length)
+        """
+        data = ConfigureConnectionData(
             target_language_code=target_language_code,
             speaker=speaker,
             pitch=pitch,
@@ -96,14 +110,16 @@ class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
             min_buffer_size=min_buffer_size,
             max_chunk_length=max_chunk_length,
         )
-        message = InitializeConnection(data=data)
+        message = ConfigureConnection(data=data)
         await self._send_model(message)
 
     async def convert(self, text: str) -> None:
         """
-        Send text to be converted to speech.
+        Send text to be converted to speech. Text length should be 1-2500 characters.
+        Recommended: <500 characters for optimal streaming performance.
+        Real-time endpoints perform better with longer character counts.
 
-        :param text: Text to be synthesized (1-2500 characters)
+        :param text: Text to be synthesized (1-2500 characters, recommended <500)
         """
         data = SendTextData(text=text)
         message = SendText(data=data)
@@ -111,15 +127,16 @@ class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
 
     async def flush(self) -> None:
         """
-        Signal to flush the buffer and finalize audio output.
-        This indicates the end of text input.
+        Forces the text buffer to process immediately, regardless of the min_buffer_size threshold.
+        Use this when you need to process remaining text that hasn't reached the minimum buffer size.
         """
         message = FlushSignal()
         await self._send_model(message)
 
     async def ping(self) -> None:
         """
-        Send ping signal to keep the WebSocket connection alive.
+        Send ping signal to keep the WebSocket connection alive. The connection automatically
+        closes after one minute of inactivity.
         """
         message = PingSignal()
         await self._send_model(message)
@@ -182,10 +199,10 @@ class TextToSpeechStreamingSocketClient(EventEmitterMixin):
         finally:
             self._emit(EventType.CLOSE, None)
 
-    def initialize_connection(
+    def configure(
         self,
         target_language_code: str,
-        speaker: str,
+        speaker: str = "anushka",
         pitch: float = 0.0,
         pace: float = 1.0,
         loudness: float = 1.0,
@@ -197,21 +214,35 @@ class TextToSpeechStreamingSocketClient(EventEmitterMixin):
         max_chunk_length: int = 150,
     ) -> None:
         """
-        Initialize the TTS connection with configuration parameters.
+        Configuration message required as the first message after establishing the WebSocket connection.
+        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.
 
-        :param target_language_code: Target language code (e.g., 'hi-IN')
-        :param speaker: Voice speaker name (e.g., 'meera', 'arvind')
-        :param pitch: Voice pitch adjustment (-1.0 to 1.0, default: 0.0)
-        :param pace: Speech pace (0.3 to 3.0, default: 1.0)
-        :param loudness: Voice loudness (0.1 to 3.0, default: 1.0)
-        :param speech_sample_rate: Audio sample rate, default: 22050
-        :param enable_preprocessing: Enable text preprocessing, default: False
-        :param output_audio_codec: Audio codec, default: 'mp3'
-        :param output_audio_bitrate: Audio bitrate, default: '128k'
-        :param min_buffer_size: Minimum buffer size, default: 50
-        :param max_chunk_length: Maximum chunk length, default: 150
-        """
-        data = InitializeConnectionData(
+        :param target_language_code: The language of the text is BCP-47 format
+        :param speaker: The speaker voice to be used for the output audio. Default: Anushka.
+            Model Compatibility (bulbul:v2): Female: Anushka, Manisha, Vidya, Arya;
+            Male: Abhilash, Karun, Hitesh
+        :param pitch: 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.
+        :param pace: 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.
+        :param loudness: 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.
+        :param speech_sample_rate: Specifies the sample rate of the output audio. Supported values are
+            8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+        :param enable_preprocessing: 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.
+        :param output_audio_codec: Audio codec (currently supports MP3 only, optimized for real-time playback)
+        :param output_audio_bitrate: Audio bitrate (choose from 5 supported bitrate options)
+        :param min_buffer_size: Minimum character length that triggers buffer flushing for TTS model processing
+        :param max_chunk_length: Maximum length for sentence splitting (adjust based on content length)
+        """
+        data = ConfigureConnectionData(
             target_language_code=target_language_code,
             speaker=speaker,
             pitch=pitch,
@@ -224,14 +255,16 @@ class TextToSpeechStreamingSocketClient(EventEmitterMixin):
             min_buffer_size=min_buffer_size,
             max_chunk_length=max_chunk_length,
         )
-        message = InitializeConnection(data=data)
+        message = ConfigureConnection(data=data)
         self._send_model(message)
 
     def convert(self, text: str) -> None:
         """
-        Send text to be converted to speech.
+        Send text to be converted to speech. Text length should be 1-2500 characters.
+        Recommended: <500 characters for optimal streaming performance.
+        Real-time endpoints perform better with longer character counts.
 
-        :param text: Text to be synthesized (1-2500 characters)
+        :param text: Text to be synthesized (1-2500 characters, recommended <500)
         """
         data = SendTextData(text=text)
         message = SendText(data=data)
@@ -239,15 +272,16 @@ class TextToSpeechStreamingSocketClient(EventEmitterMixin):
 
     def flush(self) -> None:
         """
-        Signal to flush the buffer and finalize audio output.
-        This indicates the end of text input.
+        Forces the text buffer to process immediately, regardless of the min_buffer_size threshold.
+        Use this when you need to process remaining text that hasn't reached the minimum buffer size.
         """
         message = FlushSignal()
         self._send_model(message)
 
     def ping(self) -> None:
         """
-        Send ping signal to keep the WebSocket connection alive.
+        Send ping signal to keep the WebSocket connection alive. The connection automatically
+        closes after one minute of inactivity.
         """
         message = PingSignal()
         self._send_model(message)

sarvamai/types/__init__.py

@@ -19,6 +19,11 @@ from .chat_completion_response_message import ChatCompletionResponseMessage
 from .choice import Choice
 from .completion_usage import CompletionUsage
 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_speaker import ConfigureConnectionDataSpeaker
+from .configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
 from .create_chat_completion_response import CreateChatCompletionResponse
 from .diarized_entry import DiarizedEntry
 from .diarized_transcript import DiarizedTranscript
@@ -32,11 +37,6 @@ from .events_data import EventsData
 from .finish_reason import FinishReason
 from .flush_signal import FlushSignal
 from .format import Format
-from .initialize_connection import InitializeConnection
-from .initialize_connection_data import InitializeConnectionData
-from .initialize_connection_data_output_audio_bitrate import InitializeConnectionDataOutputAudioBitrate
-from .initialize_connection_data_speaker import InitializeConnectionDataSpeaker
-from .initialize_connection_data_target_language_code import InitializeConnectionDataTargetLanguageCode
 from .language_identification_response import LanguageIdentificationResponse
 from .numerals_format import NumeralsFormat
 from .ping_signal import PingSignal
@@ -94,6 +94,11 @@ __all__ = [
     "Choice",
     "CompletionUsage",
     "ConfigMessage",
+    "ConfigureConnection",
+    "ConfigureConnectionData",
+    "ConfigureConnectionDataOutputAudioBitrate",
+    "ConfigureConnectionDataSpeaker",
+    "ConfigureConnectionDataTargetLanguageCode",
     "CreateChatCompletionResponse",
     "DiarizedEntry",
     "DiarizedTranscript",
@@ -107,11 +112,6 @@ __all__ = [
     "FinishReason",
     "FlushSignal",
     "Format",
-    "InitializeConnection",
-    "InitializeConnectionData",
-    "InitializeConnectionDataOutputAudioBitrate",
-    "InitializeConnectionDataSpeaker",
-    "InitializeConnectionDataTargetLanguageCode",
     "LanguageIdentificationResponse",
     "NumeralsFormat",
     "PingSignal",

sarvamai/types/configure_connection.py

@@ -0,0 +1,28 @@
+# 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 .configure_connection_data import ConfigureConnectionData
+
+
+class ConfigureConnection(UniversalBaseModel):
+    """
+    Configuration message required as the first message after establishing the WebSocket connection.
+    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.
+    """
+
+    type: typing.Literal["config"] = "config"
+    data: ConfigureConnectionData
+
+    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

@@ -0,0 +1,93 @@
+# 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 .configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
+from .configure_connection_data_speaker import ConfigureConnectionDataSpeaker
+from .configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
+
+
+class ConfigureConnectionData(UniversalBaseModel):
+    target_language_code: ConfigureConnectionDataTargetLanguageCode = pydantic.Field()
+    """
+    The language of the text is BCP-47 format
+    """
+
+    speaker: ConfigureConnectionDataSpeaker = pydantic.Field()
+    """
+    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
+    
+    **Note:** Speaker selection must match the chosen model version.
+    """
+
+    pitch: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    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.
+    """
+
+    pace: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    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.
+    """
+
+    loudness: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    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.
+    """
+
+    speech_sample_rate: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Specifies the sample rate of the output audio. Supported values are 
+    8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+    """
+
+    enable_preprocessing: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    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.
+    """
+
+    output_audio_codec: typing.Optional[typing.Literal["mp3"]] = pydantic.Field(default=None)
+    """
+    Audio codec (currently supports MP3 only, optimized for real-time playback)
+    """
+
+    output_audio_bitrate: typing.Optional[ConfigureConnectionDataOutputAudioBitrate] = pydantic.Field(default=None)
+    """
+    Audio bitrate (choose from 5 supported bitrate options)
+    """
+
+    min_buffer_size: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Minimum character length that triggers buffer flushing for TTS model processing
+    """
+
+    max_chunk_length: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Maximum length for sentence splitting (adjust based on content length)
+    """
+
+    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/{initialize_connection_data_output_audio_bitrate.py → configure_connection_data_output_audio_bitrate.py}

@@ -2,6 +2,6 @@
 
 import typing
 
-InitializeConnectionDataOutputAudioBitrate = typing.Union[
+ConfigureConnectionDataOutputAudioBitrate = typing.Union[
     typing.Literal["32k", "64k", "96k", "128k", "192k"], typing.Any
 ]

sarvamai/types/configure_connection_data_speaker.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ConfigureConnectionDataSpeaker = typing.Union[
+    typing.Literal["anushka", "abhilash", "manisha", "vidya", "arya", "karun", "hitesh"], typing.Any
+]

sarvamai/types/{initialize_connection_data_target_language_code.py → configure_connection_data_target_language_code.py}

@@ -2,7 +2,7 @@
 
 import typing
 
-InitializeConnectionDataTargetLanguageCode = typing.Union[
+ConfigureConnectionDataTargetLanguageCode = typing.Union[
     typing.Literal["bn-IN", "en-IN", "gu-IN", "hi-IN", "kn-IN", "ml-IN", "mr-IN", "od-IN", "pa-IN", "ta-IN", "te-IN"],
     typing.Any,
 ]

sarvamai/types/flush_signal.py

@@ -7,6 +7,11 @@ from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
 
 
 class FlushSignal(UniversalBaseModel):
+    """
+    Forces the text buffer to process immediately, regardless of the min_buffer_size threshold.
+    Use this when you need to process remaining text that hasn't reached the minimum buffer size.
+    """
+
     type: typing.Literal["flush"] = "flush"
 
     if IS_PYDANTIC_V2:

sarvamai/types/ping_signal.py

@@ -7,6 +7,11 @@ from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
 
 
 class PingSignal(UniversalBaseModel):
+    """
+    Send ping signal to keep the WebSocket connection alive. The connection automatically
+    closes after one minute of inactivity.
+    """
+
     type: typing.Literal["ping"] = "ping"
 
     if IS_PYDANTIC_V2:

{sarvamai-0.1.8rc5.dist-info → sarvamai-0.1.8rc7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.8rc5
+Version: 0.1.8rc7
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.8rc5.dist-info → sarvamai-0.1.8rc7.dist-info}/RECORD

@@ -1,11 +1,11 @@
-sarvamai/__init__.py,sha256=1T6EojO84La_t1nZ0AphCawAVhYQAlgMk8A7ZC0FH4M,8937
+sarvamai/__init__.py,sha256=xkQNmsHue7UaEN7PgNfH2ExBGBdyszDgg5omMkSnZMM,8824
 sarvamai/chat/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
 sarvamai/chat/client.py,sha256=xOSj83Gr6Q7eY2qUeATiuXYQqBqWqSCQlIEopK5fKus,11022
 sarvamai/chat/raw_client.py,sha256=A2kRuZcVWlJhyYCD7YKgqNkZEp3cYa1731KhRkhirU0,17885
 sarvamai/client.py,sha256=aI1sw5LVGMjgukgZLDlUmA17ecK1yGsQxH-W_JiCrco,7177
 sarvamai/core/__init__.py,sha256=YE2CtXeASe1RAbaI39twKWYKCuT4tW5is9HWHhJjR_g,1653
 sarvamai/core/api_error.py,sha256=44vPoTyWN59gonCIZMdzw7M1uspygiLnr3GNFOoVL2Q,614
-sarvamai/core/client_wrapper.py,sha256=ucQFDVPXC5Z3Tn-1T8MlxyL0QrswihfNYW1J7w8LJS0,2080
+sarvamai/core/client_wrapper.py,sha256=-Vik8MO2fDeTSfXmt3KybXUHsipm3dqlcwxLaBwaqA8,2080
 sarvamai/core/datetime_utils.py,sha256=nBys2IsYrhPdszxGKCNRPSOCwa-5DWOHG95FB8G9PKo,1047
 sarvamai/core/events.py,sha256=j7VWXgMpOsjCXdzY22wIhI7Q-v5InZ4WchRzA88x_Sk,856
 sarvamai/core/file.py,sha256=d4NNbX8XvXP32z8KpK2Xovv33nFfruIrpz0QWxlgpZk,2663
@@ -28,7 +28,7 @@ sarvamai/errors/too_many_requests_error.py,sha256=Dl-_pfpboXJh-OtSbRaPQOB-UXvpVO
 sarvamai/errors/unprocessable_entity_error.py,sha256=JqxtzIhvjkpQDqbT9Q-go1n-gyv9PsYqq0ng_ZYyBMo,347
 sarvamai/play.py,sha256=4fh86zy8g8IPU2O8yPBY7QxXQOivv_nWQvPQsOa1arw,2183
 sarvamai/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sarvamai/requests/__init__.py,sha256=UmEj75u8yYiZYL0M0QVJoCuS8oduaH82eD3bmP-6myg,4484
+sarvamai/requests/__init__.py,sha256=AYpixS_3RLRqMW4U2OfeACJjD3u3NnethhdYr_V-P9M,4478
 sarvamai/requests/audio_data.py,sha256=QI3SK5aiAg2yJ-m3l9CxOkONnH3CCKMFCl9kAdMs19o,410
 sarvamai/requests/audio_message.py,sha256=ZBeogjGE6YFXXM-0g8zq9SoizDk21reR0YXSB-0fMjg,214
 sarvamai/requests/audio_output.py,sha256=BnoX345rwoWgaMaj24u_19-SjmPV0xt7vlFEEDKRw20,280
@@ -41,6 +41,8 @@ sarvamai/requests/chat_completion_response_message.py,sha256=JFazj4zK-nj_wjdvNLD
 sarvamai/requests/choice.py,sha256=uulX4MZUoThEMcD3a80o_3V5YpnpqN8DfPaNZWVz-1o,867
 sarvamai/requests/completion_usage.py,sha256=LbZV-RxcxKdCAYqhCiaRtSFF3VwMJq71A989Z1rm-I8,428
 sarvamai/requests/config_message.py,sha256=EpYioGvDhCXDMvGH7Q1F7448zJzoHmlkQ1owoNGbWAw,383
+sarvamai/requests/configure_connection.py,sha256=a-foQtLxArL4CulvKEdeebbRqmS1GRmko3MZdnHVPEk,716
+sarvamai/requests/configure_connection_data.py,sha256=Niil2OrVBzQEtmWFn1JC-StLVp6WzzRIsu2i_M_8_44,2908
 sarvamai/requests/create_chat_completion_response.py,sha256=TqS9u5_WVWMok_NreT4TeOsLJQeybPkbJm45Q0Zxw30,857
 sarvamai/requests/diarized_entry.py,sha256=gbXB4D_r5_Q8gs1arRKjxPeFcYg16dVDLcg2VhxmKQA,462
 sarvamai/requests/diarized_transcript.py,sha256=X-znuJ45oqwXzVyJumBHSqVGLz6JnoYFZmluQlEpEAw,323
@@ -50,11 +52,9 @@ sarvamai/requests/error_message.py,sha256=-J21pfEJghsms4pNe55O_9qkODNd-BKLMt96AO
 sarvamai/requests/error_response.py,sha256=A8j12JQ7JJkUcnt26k2M9uwXXkwyT-LNqG3BO3U8NIk,288
 sarvamai/requests/error_response_data.py,sha256=l9tGTykaKZ8pKxdw9RKitpW49kKcs4aGibH7rKG2v7w,461
 sarvamai/requests/events_data.py,sha256=3seSash8DysPUWX6mKPzoEzWZlsrK4Tann2GFSbQjZg,286
-sarvamai/requests/flush_signal.py,sha256=k087oW96WFiC0j5opFMjytgqXPi37jYljhCEqLx9d5o,195
-sarvamai/requests/initialize_connection.py,sha256=QO4zyg2gEAeNRcxuew6Y5UW9l7OYG68sj_mL3c26GpA,317
-sarvamai/requests/initialize_connection_data.py,sha256=R6DA52P2Qlum2uz6Hld5QVSJgfY9GQGIcbvyyJOHK9A,1154
+sarvamai/requests/flush_signal.py,sha256=Aj_PzphMNcHMMOaxvTi1uQ5y36ZTtKEsUGCprbWIOvw,406
 sarvamai/requests/language_identification_response.py,sha256=BdS5U9Gic-71vb--ph6HGvd2hGNKDXERC7yrn8vFcvI,1098
-sarvamai/requests/ping_signal.py,sha256=Auzf9pafJD9vQFFtMLM3iyLtIqsOjEzVd7Jt9q2LoKY,193
+sarvamai/requests/ping_signal.py,sha256=TSgmfz2k4X1L6TzvX8u2SKZ6XQY3bSf7nPZf8mUViaM,343
 sarvamai/requests/send_text.py,sha256=DWzbNgeNN2xSIYgk2zEisgLqjwq5oleqJVHrtOnIqbE,267
 sarvamai/requests/send_text_data.py,sha256=2jds-xd77u-YTgIWQsTUBKE-_7tsrFshXXuC_Ld4ULo,161
 sarvamai/requests/speech_to_text_response.py,sha256=GS3jNmHDOxqNZ7cvftD62khUMSBIQUu6zEPdCqk8zJk,1041
@@ -97,13 +97,11 @@ sarvamai/text/raw_client.py,sha256=lQ7bV9aVqxjwEUHMPEZ4x0_Xs036_yFArMK9rnYT4ZI,4
 sarvamai/text_to_speech/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
 sarvamai/text_to_speech/client.py,sha256=aVvwdGTfgVUekALLpdyxKNsGUZQ2Ee2OZBLx6WP6g_E,8842
 sarvamai/text_to_speech/raw_client.py,sha256=3Zu6HN_FOY683Vm-EN-OL7YAbLsftjJlFm5OyRGNtYc,14780
-sarvamai/text_to_speech_streaming/__init__.py,sha256=AyHwl9te1mTfiz6IkMU20quN-0RP5njbchknXCz-oK8,173
-sarvamai/text_to_speech_streaming/client.py,sha256=sEC5mVNALldkZri3gHVxHcJCI9TmVwF1vPTL8vfatbY,6161
-sarvamai/text_to_speech_streaming/raw_client.py,sha256=DXsU8Rq27yZGINkRmyeyqPWLlSAGsR1RTJWJH81FlTI,5342
-sarvamai/text_to_speech_streaming/socket_client.py,sha256=qZpHFC1z1c6T_FaGOW6CPtWE15glmqClmdc5Iixa7FY,10429
-sarvamai/text_to_speech_streaming/types/__init__.py,sha256=DUsvIGTtST5N1v3Hnodq5aNKfPcTBlod28DSypc8NzA,198
-sarvamai/text_to_speech_streaming/types/text_to_speech_streaming_model.py,sha256=1uOMrJIaAxi_XzwCYmnG5XA-il66cq9uC4ZuiI7HCHo,176
-sarvamai/types/__init__.py,sha256=_5KKlTtdY4kOQ3go9T60EPmSA53AOFGbF5VJOkcnros,6320
+sarvamai/text_to_speech_streaming/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
+sarvamai/text_to_speech_streaming/client.py,sha256=geTF5xy-batzO12XVt0sPw_XJCi7-m2sDFK_B7SL7qc,6088
+sarvamai/text_to_speech_streaming/raw_client.py,sha256=asOcNw1WAViOiXDVWH4sxWSXGVoLwAOh9vUtq_xralA,5269
+sarvamai/text_to_speech_streaming/socket_client.py,sha256=NEcijnvjuNcWfzqpBi-xWsXVkL0NPq6EGAkEjnaq9hw,13909
+sarvamai/types/__init__.py,sha256=cEfGVQMYlbz13iS9v83_CB9160Cky4JOImmxM30fGhg,6305
 sarvamai/types/audio_data.py,sha256=rgOukLkLNJ_HBBVE2g5dfEL2CWjRoGiMvCtpq0qTB1Y,829
 sarvamai/types/audio_message.py,sha256=sB4EgkWkWJzipYXobkmM9AYZTTZtCpg_ySKssUeznUE,560
 sarvamai/types/audio_output.py,sha256=Eq-YUZa1mSDwt7bax2c4Vv2gBlyM_JBJWzHhTAhFSko,621
@@ -116,6 +114,11 @@ sarvamai/types/chat_completion_response_message.py,sha256=wz935eBnCkSIl0I0qMxBuH
 sarvamai/types/choice.py,sha256=uXBCsjWP9VK3XWQWZUeI4EnU10w0G9nAfKn2tJZvxko,1244
 sarvamai/types/completion_usage.py,sha256=xYQGlQUbKqsksuV73H-1ajjfT5M7w47eLfdWXSlrI5M,843
 sarvamai/types/config_message.py,sha256=sGrT-qYTRqLVfIo5nRUuRlqPtPVmiAkUAnaMtlmQYCU,778
+sarvamai/types/configure_connection.py,sha256=SnSNk02gQqP8e4VB4y88jjeFQ4ClpImjGLn2ANI8cZ4,1058
+sarvamai/types/configure_connection_data.py,sha256=brMO-Z1TDq3oTJ22m1icBkkmnd9k67p_DzecnMcqNko,3421
+sarvamai/types/configure_connection_data_output_audio_bitrate.py,sha256=h00YvKLxsZC8L3__rH4XH53nN_GY40UElW1EjysCwUs,208
+sarvamai/types/configure_connection_data_speaker.py,sha256=SzyAiK5LynXwb9KniaO2qoOLY-II3-PMZbRuIsQ9shw,230
+sarvamai/types/configure_connection_data_target_language_code.py,sha256=jrU1EblAtDYbybUO1KUkHhevmlSBj2AQxX13ii3QhAQ,275
 sarvamai/types/create_chat_completion_response.py,sha256=4nEzeWzHGW1_BmRAtOuGsbRZ0ojNgnzJSMUFyYuYviw,1285
 sarvamai/types/diarized_entry.py,sha256=kf9DLrcoMHZdTKNCAaF0z46q_iAe7CE-DFP4CNrZGTw,896
 sarvamai/types/diarized_transcript.py,sha256=a491XmALLE7AQcByaaOYTew0BZoFTlewEMHLMJyj-Js,669
@@ -127,16 +130,11 @@ sarvamai/types/error_response.py,sha256=3m17Aj3GY_-mSY2lH-GkbuiyewTm-wNL9UQ1exLv
 sarvamai/types/error_response_data.py,sha256=hncN_zmPg8kqSHjNciYLn2QeNqzqHxKiZDlKOvjKdwA,838
 sarvamai/types/events_data.py,sha256=hDSOyODc8-lmpduJIQkps9kHlUZKYXGw3lETi8irHt0,681
 sarvamai/types/finish_reason.py,sha256=PBWtBNkX4FMaODmlUehpF6qLB5uH_zR-Mw3M4uhIB6U,209
-sarvamai/types/flush_signal.py,sha256=zX-jCXQixmellMi1-NKKPyqcRaxeOMycw90fKRpWWAQ,548
+sarvamai/types/flush_signal.py,sha256=N7MJWb658KoxRpFN9cIbyQGY45zZcg8YCou3E1v--9o,759
 sarvamai/types/format.py,sha256=57LicD0XLqW4D1QEnZWsWGifzRy1GV9P5utKPXLoxtg,144
-sarvamai/types/initialize_connection.py,sha256=qL9vhyZL7fJxV1UFHtCmFMYaVgZkCWMkP4v-TCREAow,659
-sarvamai/types/initialize_connection_data.py,sha256=iCl6fC3QpmIJXOkoC3TjVU4HmUQdbq95RJUHe0nRv1M,1413
-sarvamai/types/initialize_connection_data_output_audio_bitrate.py,sha256=Wl2b6KR_shf6FzsBr1RJxBeVduS6AtO8skwQqOaffFc,209
-sarvamai/types/initialize_connection_data_speaker.py,sha256=TW-tEGVALD-67FqWLzudeWtFmUPKjZBOy7X2_pjg9Y4,507
-sarvamai/types/initialize_connection_data_target_language_code.py,sha256=iEuRFQJPsXO6lCwbNOoB7BzvoLCPIXL7UbIOKOMIjPs,276
 sarvamai/types/language_identification_response.py,sha256=jG4ZQ6KQHCiEDqC51OniOwiRdW14Fbz22bbTsUDp_kc,1483
 sarvamai/types/numerals_format.py,sha256=xg3lYiHcnzyFwuwRcaIteJLH_Pz6pJ9n9kTlYPEnCBU,165
-sarvamai/types/ping_signal.py,sha256=4X0E96-0Gf4VpJP3GDjzw4963LMxU0a_ykaknJwS_7o,545
+sarvamai/types/ping_signal.py,sha256=cE53FRIXlc8bSo18z6jlAnOh6DhZEMX36huWEX6X3-A,695
 sarvamai/types/reasoning_effort.py,sha256=_TBLn3rQgzJAdnKqV2g0PETbrSBZl0fPLfQ5ZE9H4Pc,164
 sarvamai/types/response_type.py,sha256=yyk0QTIQlNa9W0Uoj_5_ey_Q3Bu8Jij5GkgR0Rt_WnU,163
 sarvamai/types/role.py,sha256=3eY01zZQKB8BSD4cFDeVjz-o2qnHJKz1vnToLqbExxs,115
@@ -175,6 +173,6 @@ sarvamai/types/transliterate_mode.py,sha256=1jSEMlGcoLkWuk12TgoOpSgwifa4rThGKZ1h
 sarvamai/types/transliterate_source_language.py,sha256=bSY9wJszF0sg-Cgg6F-YcWC8ly1mIlj9rqa15-jBtx8,283
 sarvamai/types/transliteration_response.py,sha256=yt-lzTbDeJ_ZL4I8kQa6oESxA9ebeJJY7LfFHpdEsmM,815
 sarvamai/version.py,sha256=Qkp3Ee9YH-O9RTix90e0i7iNrFAGN-QDt2AFwGA4n8k,75
-sarvamai-0.1.8rc5.dist-info/METADATA,sha256=UJapTnAvJLabUeDXBxpUj9-KIZQeHYdoeoCNsHKLUvQ,26760
-sarvamai-0.1.8rc5.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-sarvamai-0.1.8rc5.dist-info/RECORD,,
+sarvamai-0.1.8rc7.dist-info/METADATA,sha256=byv0QyLj3QnQ13nxHgu9h8pKdiCy8e_hRmp7HL01tCU,26760
+sarvamai-0.1.8rc7.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+sarvamai-0.1.8rc7.dist-info/RECORD,,

sarvamai/requests/initialize_connection.py

@@ -1,11 +0,0 @@
-# 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

@@ -1,22 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import typing_extensions
-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]
-    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/text_to_speech_streaming/types/__init__.py

@@ -1,7 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-# isort: skip_file
-
-from .text_to_speech_streaming_model import TextToSpeechStreamingModel
-
-__all__ = ["TextToSpeechStreamingModel"]

sarvamai/text_to_speech_streaming/types/text_to_speech_streaming_model.py

@@ -1,5 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-TextToSpeechStreamingModel = typing.Union[typing.Literal["bulbul:v1", "bulbul:v2"], typing.Any]

sarvamai/types/initialize_connection.py

@@ -1,21 +0,0 @@
-# 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 .initialize_connection_data import InitializeConnectionData
-
-
-class InitializeConnection(UniversalBaseModel):
-    type: typing.Literal["config"] = "config"
-    data: InitializeConnectionData
-
-    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/initialize_connection_data.py

@@ -1,32 +0,0 @@
-# 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 .initialize_connection_data_output_audio_bitrate import InitializeConnectionDataOutputAudioBitrate
-from .initialize_connection_data_speaker import InitializeConnectionDataSpeaker
-from .initialize_connection_data_target_language_code import InitializeConnectionDataTargetLanguageCode
-
-
-class InitializeConnectionData(UniversalBaseModel):
-    target_language_code: InitializeConnectionDataTargetLanguageCode
-    speaker: InitializeConnectionDataSpeaker
-    pitch: typing.Optional[float] = None
-    pace: typing.Optional[float] = None
-    loudness: typing.Optional[float] = None
-    speech_sample_rate: typing.Optional[int] = None
-    enable_preprocessing: typing.Optional[bool] = None
-    output_audio_codec: typing.Optional[typing.Literal["mp3"]] = None
-    output_audio_bitrate: typing.Optional[InitializeConnectionDataOutputAudioBitrate] = None
-    min_buffer_size: typing.Optional[int] = None
-    max_chunk_length: typing.Optional[int] = 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/initialize_connection_data_speaker.py

@@ -1,28 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-InitializeConnectionDataSpeaker = typing.Union[
-    typing.Literal[
-        "meera",
-        "pavithra",
-        "maitreyi",
-        "arvind",
-        "amol",
-        "amartya",
-        "diya",
-        "neel",
-        "misha",
-        "vian",
-        "arjun",
-        "maya",
-        "anushka",
-        "abhilash",
-        "manisha",
-        "vidya",
-        "arya",
-        "karun",
-        "hitesh",
-    ],
-    typing.Any,
-]