sarvamai 0.1.20a1__py3-none-any.whl → 0.1.20a3__py3-none-any.whl

sarvamai/__init__.py

@@ -189,14 +189,12 @@ from .speech_to_text_streaming import (
     SpeechToTextStreamingHighVadSensitivity,
     SpeechToTextStreamingInputAudioCodec,
     SpeechToTextStreamingLanguageCode,
-    SpeechToTextStreamingModel,
     SpeechToTextStreamingVadSignals,
 )
 from .speech_to_text_translate_streaming import (
     SpeechToTextTranslateStreamingFlushSignal,
     SpeechToTextTranslateStreamingHighVadSensitivity,
     SpeechToTextTranslateStreamingInputAudioCodec,
-    SpeechToTextTranslateStreamingModel,
     SpeechToTextTranslateStreamingVadSignals,
 )
 from .text_to_speech_streaming import TextToSpeechStreamingSendCompletionEvent
@@ -322,7 +320,6 @@ __all__ = [
     "SpeechToTextStreamingHighVadSensitivity",
     "SpeechToTextStreamingInputAudioCodec",
     "SpeechToTextStreamingLanguageCode",
-    "SpeechToTextStreamingModel",
     "SpeechToTextStreamingResponse",
     "SpeechToTextStreamingResponseParams",
     "SpeechToTextStreamingVadSignals",
@@ -339,7 +336,6 @@ __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
     "SpeechToTextTranslateStreamingInputAudioCodec",
-    "SpeechToTextTranslateStreamingModel",
     "SpeechToTextTranslateStreamingResponse",
     "SpeechToTextTranslateStreamingResponseParams",
     "SpeechToTextTranslateStreamingVadSignals",

sarvamai/core/client_wrapper.py

@@ -23,10 +23,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.20a1",
+            "User-Agent": "sarvamai/0.1.20a3",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.20a1",
+            "X-Fern-SDK-Version": "0.1.20a3",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

sarvamai/play.py

@@ -13,19 +13,52 @@ def is_installed(lib_name: str) -> bool:
 
 
 def play(
-    audio: TextToSpeechResponse, 
-    notebook: bool = False, 
-    use_ffmpeg: bool = True
+    audio: TextToSpeechResponse, notebook: bool = False, use_ffmpeg: bool = True
 ) -> None:
-    af_str = "".join(audio.audios)
-    af_bytes = base64.b64decode(af_str)
+    # Iterate through all audio chunks and concatenate them properly
+    combined_audio_data = b""
+
+    for i, audio_chunk in enumerate(audio.audios):
+        # Decode each base64 chunk to get raw WAV data
+        chunk_data = base64.b64decode(audio_chunk)
+
+        if i == 0:
+            # For the first chunk, keep the entire WAV file
+            combined_audio_data = chunk_data
+        else:
+            # For subsequent chunks, find the data chunk and append only audio data
+            data_pos = chunk_data.find(b"data")
+            if data_pos != -1:
+                # Skip the 'data' header (8 bytes: 'data' + size)
+                audio_data_start = data_pos + 8
+                combined_audio_data += chunk_data[audio_data_start:]
+
+    # Update the WAV header with the correct total file size
+    if len(audio.audios) > 1:
+        # Update the RIFF chunk size (bytes 4-7)
+        total_size = len(combined_audio_data) - 8
+        combined_audio_data = (
+            combined_audio_data[:4]
+            + total_size.to_bytes(4, "little")
+            + combined_audio_data[8:]
+        )
+
+        # Update the data chunk size (find data chunk and update its size)
+        data_pos = combined_audio_data.find(b"data")
+        if data_pos != -1:
+            data_size = len(combined_audio_data) - data_pos - 8
+            combined_audio_data = (
+                combined_audio_data[: data_pos + 4]
+                + data_size.to_bytes(4, "little")
+                + combined_audio_data[data_pos + 8 :]
+            )
+
+    af_bytes = combined_audio_data
     if notebook:
         try:
             from IPython.display import Audio, display  # type: ignore
         except ModuleNotFoundError:
-            message = (
-                "`pip install ipython` required when `notebook=False` "
-            )
+            message = "`pip install ipython` required when `notebook=False` "
             raise ValueError(message)
 
         display(Audio(af_bytes, rate=22050, autoplay=True))
@@ -65,8 +98,43 @@ def play(
 
 def save(audio: TextToSpeechResponse, filename: str) -> None:
     if isinstance(audio.audios, list):
-        combined_audio = "".join(audio.audios)
-        b64_file = base64.b64decode(combined_audio)
+        # Iterate through all audio chunks and concatenate them properly
+        combined_audio_data = b""
+
+        for i, audio_chunk in enumerate(audio.audios):
+            # Decode each base64 chunk to get raw WAV data
+            chunk_data = base64.b64decode(audio_chunk)
+
+            if i == 0:
+                # For the first chunk, keep the entire WAV file
+                combined_audio_data = chunk_data
+            else:
+                # For subsequent chunks, find the data chunk and append only audio data
+                data_pos = chunk_data.find(b"data")
+                if data_pos != -1:
+                    # Skip the 'data' header (8 bytes: 'data' + size)
+                    audio_data_start = data_pos + 8
+                    combined_audio_data += chunk_data[audio_data_start:]
+
+        # Update the WAV header with the correct total file size
+        if len(audio.audios) > 1:
+            # Update the RIFF chunk size (bytes 4-7)
+            total_size = len(combined_audio_data) - 8
+            combined_audio_data = (
+                combined_audio_data[:4]
+                + total_size.to_bytes(4, "little")
+                + combined_audio_data[8:]
+            )
+
+            # Update the data chunk size (find data chunk and update its size)
+            data_pos = combined_audio_data.find(b"data")
+            if data_pos != -1:
+                data_size = len(combined_audio_data) - data_pos - 8
+                combined_audio_data = (
+                    combined_audio_data[: data_pos + 4]
+                    + data_size.to_bytes(4, "little")
+                    + combined_audio_data[data_pos + 8 :]
+                )
 
         with open(filename, "wb") as f:
-            f.write(b64_file)
+            f.write(combined_audio_data)

sarvamai/requests/audio_output_data.py

@@ -13,3 +13,8 @@ class AudioOutputDataParams(typing_extensions.TypedDict):
     """
     Base64-encoded audio data ready for playback or download
     """
+
+    request_id: typing_extensions.NotRequired[str]
+    """
+    Unique identifier for the request
+    """

sarvamai/requests/error_response_data.py

@@ -16,3 +16,8 @@ class ErrorResponseDataParams(typing_extensions.TypedDict):
     """
     Additional error details and context information
     """
+
+    request_id: typing_extensions.NotRequired[str]
+    """
+    Unique identifier for the request
+    """

sarvamai/speech_to_text_streaming/__init__.py

@@ -7,7 +7,6 @@ from .types import (
     SpeechToTextStreamingHighVadSensitivity,
     SpeechToTextStreamingInputAudioCodec,
     SpeechToTextStreamingLanguageCode,
-    SpeechToTextStreamingModel,
     SpeechToTextStreamingVadSignals,
 )
 
@@ -16,6 +15,5 @@ __all__ = [
     "SpeechToTextStreamingHighVadSensitivity",
     "SpeechToTextStreamingInputAudioCodec",
     "SpeechToTextStreamingLanguageCode",
-    "SpeechToTextStreamingModel",
     "SpeechToTextStreamingVadSignals",
 ]

sarvamai/speech_to_text_streaming/client.py

@@ -15,7 +15,6 @@ from .types.speech_to_text_streaming_flush_signal import SpeechToTextStreamingFl
 from .types.speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
 from .types.speech_to_text_streaming_input_audio_codec import SpeechToTextStreamingInputAudioCodec
 from .types.speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
-from .types.speech_to_text_streaming_model import SpeechToTextStreamingModel
 from .types.speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignals
 
 try:
@@ -44,7 +43,7 @@ class SpeechToTextStreamingClient:
         self,
         *,
         language_code: SpeechToTextStreamingLanguageCode,
-        model: typing.Optional[SpeechToTextStreamingModel] = None,
+        model: typing.Optional[typing.Literal["saarika:v2.5"]] = None,
         input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
@@ -61,7 +60,7 @@ class SpeechToTextStreamingClient:
         language_code : SpeechToTextStreamingLanguageCode
             Language code for speech recognition
 
-        model : typing.Optional[SpeechToTextStreamingModel]
+        model : typing.Optional[typing.Literal["saarika:v2.5"]]
             Speech to text model to use
 
         input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
@@ -149,7 +148,7 @@ class AsyncSpeechToTextStreamingClient:
         self,
         *,
         language_code: SpeechToTextStreamingLanguageCode,
-        model: typing.Optional[SpeechToTextStreamingModel] = None,
+        model: typing.Optional[typing.Literal["saarika:v2.5"]] = None,
         input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
@@ -166,7 +165,7 @@ class AsyncSpeechToTextStreamingClient:
         language_code : SpeechToTextStreamingLanguageCode
             Language code for speech recognition
 
-        model : typing.Optional[SpeechToTextStreamingModel]
+        model : typing.Optional[typing.Literal["saarika:v2.5"]]
             Speech to text model to use
 
         input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]

sarvamai/speech_to_text_streaming/raw_client.py

@@ -14,7 +14,6 @@ from .types.speech_to_text_streaming_flush_signal import SpeechToTextStreamingFl
 from .types.speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
 from .types.speech_to_text_streaming_input_audio_codec import SpeechToTextStreamingInputAudioCodec
 from .types.speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
-from .types.speech_to_text_streaming_model import SpeechToTextStreamingModel
 from .types.speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignals
 
 try:
@@ -32,7 +31,7 @@ class RawSpeechToTextStreamingClient:
         self,
         *,
         language_code: SpeechToTextStreamingLanguageCode,
-        model: typing.Optional[SpeechToTextStreamingModel] = None,
+        model: typing.Optional[typing.Literal["saarika:v2.5"]] = None,
         input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
@@ -49,7 +48,7 @@ class RawSpeechToTextStreamingClient:
         language_code : SpeechToTextStreamingLanguageCode
             Language code for speech recognition
 
-        model : typing.Optional[SpeechToTextStreamingModel]
+        model : typing.Optional[typing.Literal["saarika:v2.5"]]
             Speech to text model to use
 
         input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
@@ -126,7 +125,7 @@ class AsyncRawSpeechToTextStreamingClient:
         self,
         *,
         language_code: SpeechToTextStreamingLanguageCode,
-        model: typing.Optional[SpeechToTextStreamingModel] = None,
+        model: typing.Optional[typing.Literal["saarika:v2.5"]] = None,
         input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
@@ -143,7 +142,7 @@ class AsyncRawSpeechToTextStreamingClient:
         language_code : SpeechToTextStreamingLanguageCode
             Language code for speech recognition
 
-        model : typing.Optional[SpeechToTextStreamingModel]
+        model : typing.Optional[typing.Literal["saarika:v2.5"]]
             Speech to text model to use
 
         input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]

sarvamai/speech_to_text_streaming/types/__init__.py

@@ -6,7 +6,6 @@ from .speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSig
 from .speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
 from .speech_to_text_streaming_input_audio_codec import SpeechToTextStreamingInputAudioCodec
 from .speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
-from .speech_to_text_streaming_model import SpeechToTextStreamingModel
 from .speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignals
 
 __all__ = [
@@ -14,6 +13,5 @@ __all__ = [
     "SpeechToTextStreamingHighVadSensitivity",
     "SpeechToTextStreamingInputAudioCodec",
     "SpeechToTextStreamingLanguageCode",
-    "SpeechToTextStreamingModel",
     "SpeechToTextStreamingVadSignals",
 ]

sarvamai/speech_to_text_translate_streaming/__init__.py

@@ -6,7 +6,6 @@ from .types import (
     SpeechToTextTranslateStreamingFlushSignal,
     SpeechToTextTranslateStreamingHighVadSensitivity,
     SpeechToTextTranslateStreamingInputAudioCodec,
-    SpeechToTextTranslateStreamingModel,
     SpeechToTextTranslateStreamingVadSignals,
 )
 
@@ -14,6 +13,5 @@ __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
     "SpeechToTextTranslateStreamingInputAudioCodec",
-    "SpeechToTextTranslateStreamingModel",
     "SpeechToTextTranslateStreamingVadSignals",
 ]

sarvamai/speech_to_text_translate_streaming/client.py

@@ -16,7 +16,6 @@ from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
     SpeechToTextTranslateStreamingHighVadSensitivity,
 )
 from .types.speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .types.speech_to_text_translate_streaming_model import SpeechToTextTranslateStreamingModel
 from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 try:
@@ -44,7 +43,7 @@ class SpeechToTextTranslateStreamingClient:
     def connect(
         self,
         *,
-        model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
+        model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
         input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
@@ -58,7 +57,7 @@ class SpeechToTextTranslateStreamingClient:
 
         Parameters
         ----------
-        model : typing.Optional[SpeechToTextTranslateStreamingModel]
+        model : typing.Optional[typing.Literal["saaras:v2.5"]]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
         input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
@@ -143,7 +142,7 @@ class AsyncSpeechToTextTranslateStreamingClient:
     async def connect(
         self,
         *,
-        model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
+        model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
         input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
@@ -157,7 +156,7 @@ class AsyncSpeechToTextTranslateStreamingClient:
 
         Parameters
         ----------
-        model : typing.Optional[SpeechToTextTranslateStreamingModel]
+        model : typing.Optional[typing.Literal["saaras:v2.5"]]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
         input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]

sarvamai/speech_to_text_translate_streaming/raw_client.py

@@ -15,7 +15,6 @@ from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
     SpeechToTextTranslateStreamingHighVadSensitivity,
 )
 from .types.speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .types.speech_to_text_translate_streaming_model import SpeechToTextTranslateStreamingModel
 from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 try:
@@ -32,7 +31,7 @@ class RawSpeechToTextTranslateStreamingClient:
     def connect(
         self,
         *,
-        model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
+        model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
         input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
@@ -46,7 +45,7 @@ class RawSpeechToTextTranslateStreamingClient:
 
         Parameters
         ----------
-        model : typing.Optional[SpeechToTextTranslateStreamingModel]
+        model : typing.Optional[typing.Literal["saaras:v2.5"]]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
         input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
@@ -120,7 +119,7 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
     async def connect(
         self,
         *,
-        model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
+        model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
         input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
@@ -134,7 +133,7 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
 
         Parameters
         ----------
-        model : typing.Optional[SpeechToTextTranslateStreamingModel]
+        model : typing.Optional[typing.Literal["saaras:v2.5"]]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
         input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]

sarvamai/speech_to_text_translate_streaming/types/__init__.py

@@ -5,13 +5,11 @@
 from .speech_to_text_translate_streaming_flush_signal import SpeechToTextTranslateStreamingFlushSignal
 from .speech_to_text_translate_streaming_high_vad_sensitivity import SpeechToTextTranslateStreamingHighVadSensitivity
 from .speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .speech_to_text_translate_streaming_model import SpeechToTextTranslateStreamingModel
 from .speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
     "SpeechToTextTranslateStreamingInputAudioCodec",
-    "SpeechToTextTranslateStreamingModel",
     "SpeechToTextTranslateStreamingVadSignals",
 ]

sarvamai/text_to_speech_streaming/socket_client.py

@@ -10,13 +10,14 @@ 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.event_response import EventResponse
 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
 
-TextToSpeechStreamingSocketClientResponse = typing.Union[AudioOutput, ErrorResponse]
+TextToSpeechStreamingSocketClientResponse = typing.Union[AudioOutput, ErrorResponse, EventResponse]
 
 
 class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):

sarvamai/types/audio_output_data.py

@@ -17,6 +17,11 @@ class AudioOutputData(UniversalBaseModel):
     Base64-encoded audio data ready for playback or download
     """
 
+    request_id: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Unique identifier for the request
+    """
+
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else:

sarvamai/types/error_response_data.py

@@ -18,6 +18,11 @@ class ErrorResponseData(UniversalBaseModel):
     Additional error details and context information
     """
 
+    request_id: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Unique identifier for the request
+    """
+
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else:

sarvamai/types/speech_to_text_model.py

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

sarvamai/types/speech_to_text_translate_model.py

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

{sarvamai-0.1.20a1.dist-info → sarvamai-0.1.20a3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.20a1
+Version: 0.1.20a3
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.20a1.dist-info → sarvamai-0.1.20a3.dist-info}/RECORD

@@ -1,11 +1,11 @@
-sarvamai/__init__.py,sha256=-HM4Xf9WWwFScK90X45K7GH1AHZL6w7UcIRVE7VULvo,11649
+sarvamai/__init__.py,sha256=vI_MiA00kkNnsVNJmIFkf1o_-vLIp8SeNy4xdzjQ_wY,11499
 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=J30X_os1lPf8Wml0KDFEf6p8VGHhgF_lf3nw1T2D3qo,8207
 sarvamai/core/__init__.py,sha256=YE2CtXeASe1RAbaI39twKWYKCuT4tW5is9HWHhJjR_g,1653
 sarvamai/core/api_error.py,sha256=44vPoTyWN59gonCIZMdzw7M1uspygiLnr3GNFOoVL2Q,614
-sarvamai/core/client_wrapper.py,sha256=5f4_nM8kBdZM8Yp8FVUuJkKPNuV0n1yFvwKTufsBKek,2570
+sarvamai/core/client_wrapper.py,sha256=ZSinVWwLcEoiBinSQsL_LCNa37D6WzIjGqnNN450h8I,2570
 sarvamai/core/datetime_utils.py,sha256=nBys2IsYrhPdszxGKCNRPSOCwa-5DWOHG95FB8G9PKo,1047
 sarvamai/core/events.py,sha256=HvKBdSoYcFetk7cgNXb7FxuY-FtY8NtUhZIN7mGVx8U,1159
 sarvamai/core/file.py,sha256=d4NNbX8XvXP32z8KpK2Xovv33nFfruIrpz0QWxlgpZk,2663
@@ -26,13 +26,13 @@ sarvamai/errors/internal_server_error.py,sha256=t1-kpoDC2biEuoE-Ne8v1kuQswvsIEwt
 sarvamai/errors/service_unavailable_error.py,sha256=MIoOqruDBRDJtJJFK45O4_Xwjcwh4diwKbpHlqNQ-ZI,346
 sarvamai/errors/too_many_requests_error.py,sha256=Dl-_pfpboXJh-OtSbRaPQOB-UXvpVOElRDgjxbi4j7w,343
 sarvamai/errors/unprocessable_entity_error.py,sha256=JqxtzIhvjkpQDqbT9Q-go1n-gyv9PsYqq0ng_ZYyBMo,347
-sarvamai/play.py,sha256=4fh86zy8g8IPU2O8yPBY7QxXQOivv_nWQvPQsOa1arw,2183
+sarvamai/play.py,sha256=FKsQ5nRq-nF8iVVwJIWb5i-1TCWku_vq989wBXOE6Yg,5190
 sarvamai/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sarvamai/requests/__init__.py,sha256=jL9z3hA1vtYkoCLOIlBUOmiE31WEyDtSC81jRhC6X8g,5865
 sarvamai/requests/audio_data.py,sha256=weVNgM3zaHim3a17qvXD5ayyhaJ8MnzWJWATOjRuhvM,1116
 sarvamai/requests/audio_message.py,sha256=ZBeogjGE6YFXXM-0g8zq9SoizDk21reR0YXSB-0fMjg,214
 sarvamai/requests/audio_output.py,sha256=BnoX345rwoWgaMaj24u_19-SjmPV0xt7vlFEEDKRw20,280
-sarvamai/requests/audio_output_data.py,sha256=v5s67mI1RNO20-C39lRXWpHgV13yOPXML1VrZHke9sY,349
+sarvamai/requests/audio_output_data.py,sha256=6-pmWDr9U99xDB2Khw8r3W0Mt4oRo1jPEvHWqeeOR6s,455
 sarvamai/requests/base_job_parameters.py,sha256=5-DGqoCcIt5PM_-LO8hzuTqnuW5arxpEzimAmL9rLKM,161
 sarvamai/requests/bulk_job_callback.py,sha256=6MvZSY0l2lch9skJzy8qBpuZ9KJoLv3ZL7SYP2rNlUI,345
 sarvamai/requests/bulk_job_init_response_v_1.py,sha256=prWUzJ5x3pdOdInKqeVahKWYL5uvwf7gOlecgZU2qfE,524
@@ -53,7 +53,7 @@ sarvamai/requests/error_data.py,sha256=u87qHVagiqyyowBgMDAPPLlZzr0Z5GXlOU7VIUzfQ
 sarvamai/requests/error_details.py,sha256=By7cYfitQynAM1D5_3yFc22zXQJEceNgkhoyGWmg4zw,529
 sarvamai/requests/error_message.py,sha256=-J21pfEJghsms4pNe55O_9qkODNd-BKLMt96AOztYUs,257
 sarvamai/requests/error_response.py,sha256=A8j12JQ7JJkUcnt26k2M9uwXXkwyT-LNqG3BO3U8NIk,288
-sarvamai/requests/error_response_data.py,sha256=l9tGTykaKZ8pKxdw9RKitpW49kKcs4aGibH7rKG2v7w,461
+sarvamai/requests/error_response_data.py,sha256=t-kD8EQAV8ZKB_S4r3BnNrWTJijsiK6mazX2m77KxkQ,567
 sarvamai/requests/event_response.py,sha256=Mk5lXlcmFmn50-99TWqLoLMuDl9pVT9B9JcOGaAZVZM,446
 sarvamai/requests/event_response_data.py,sha256=2IzBUllUSrbxU6-JS-CgdnImT6NT3Q7yh81tmn2g_7A,508
 sarvamai/requests/events_data.py,sha256=DgwSqyeFzL36i1z72mxKGP1qGjs27GpO1h9fL-ziWqo,728
@@ -93,30 +93,28 @@ sarvamai/speech_to_text_job/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23
 sarvamai/speech_to_text_job/client.py,sha256=WSGBJxYcNxl77Zd1X6VVWjg4zshqecXf6WCyhfLXVlI,18007
 sarvamai/speech_to_text_job/job.py,sha256=K8HOmwrYd6l82-MZfWDBmNkZeeERyg9YOihnFfvl-Js,15021
 sarvamai/speech_to_text_job/raw_client.py,sha256=OZTPzMhAn-ckE_xKzfZ9QLsEX5EZVOJS0Pf-PBa19jM,48200
-sarvamai/speech_to_text_streaming/__init__.py,sha256=l7yGZbLTVWVq63Y1mt_WuX2oyPiXDyc0E-BIonyPYP0,601
-sarvamai/speech_to_text_streaming/client.py,sha256=PqQfzgALEE8p-rpudmsGWR_lMlKy5SsCelQFqUpyzA8,11237
-sarvamai/speech_to_text_streaming/raw_client.py,sha256=Xzq4MSL7isxBa6JFqzd7U4knPNzauGiTVKNsXXaKsW4,10418
+sarvamai/speech_to_text_streaming/__init__.py,sha256=-7nN6AJFryjSvGHVbajYEt-vni6kNDfJUiZJFNl_ao4,535
+sarvamai/speech_to_text_streaming/client.py,sha256=s-0rKrNN5Phk7xR2WOGNoG6zSA00dd_3zBXEfVFdNqk,11176
+sarvamai/speech_to_text_streaming/raw_client.py,sha256=Oe9dz6hBTRkdfIDUGHuDhuCqJooCGdM_hxc9Z2DFfqs,10357
 sarvamai/speech_to_text_streaming/socket_client.py,sha256=P6qXRN0s3UFAp6CP5lkqrW2KPK9me70ZVfWquxLB4wI,7538
-sarvamai/speech_to_text_streaming/types/__init__.py,sha256=6DNWJo4YFCAEqTC3hqEGBJwnDTaj48o0v_3vlVfdOAI,860
+sarvamai/speech_to_text_streaming/types/__init__.py,sha256=_G5TSTthsnjGmwdV4fpsybjEWMMTNkh-kWXZjgK5X48,755
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_flush_signal.py,sha256=dDJOBlzAjhuiSVqW2RHHY1f6xy0DU_Yoo9UV8-7MjnA,173
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_high_vad_sensitivity.py,sha256=OwPwffa8TkLPGMnOTn5S7d-HmV8QmN3B7fHz8I1-VT8,180
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_input_audio_codec.py,sha256=yfINVbnoiAvhDskwVkpnFv10Q9SzU104oRJR-n__ugc,584
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_language_code.py,sha256=LxgEifmgWTCFZn9U-f-TWKxRPng3a2J26Zt526QrA0Y,267
-sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_model.py,sha256=b6F4ymgz4got6KVDqrweYvkET8itze63wUwWyjqDlO4,180
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_vad_signals.py,sha256=8wiFOB7WDMbYCcMTYgNFJaIjEytYeXpJLwr_O_mH0TI,172
 sarvamai/speech_to_text_translate_job/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
 sarvamai/speech_to_text_translate_job/client.py,sha256=xu8kYtCESDB7LzL8YKBUq5qhTPMIl3_H3XD2L_7y4UU,18969
 sarvamai/speech_to_text_translate_job/job.py,sha256=DU4k3eB28V8N16M_QEchakVng4IOul6_Qrdn3FumgHA,15208
 sarvamai/speech_to_text_translate_job/raw_client.py,sha256=dAitbu2B9afPK6iT9zNjUJnE5BIr5-lrAlwrfwFxdkU,49507
-sarvamai/speech_to_text_translate_streaming/__init__.py,sha256=_DvueqU3i0P_nIaCgPyfO0-I2dPkNZpamKpyB4nXPhU,611
-sarvamai/speech_to_text_translate_streaming/client.py,sha256=h7glgfA6bO5acuzz6yAZsdL0FyOj4Tq2HoSqG0FHZK0,11223
-sarvamai/speech_to_text_translate_streaming/raw_client.py,sha256=ArNbRV21MRZEmO6VDknYQDTdqfhK7h1lF8S_ucj5eM8,10332
+sarvamai/speech_to_text_translate_streaming/__init__.py,sha256=s6HPwrkABpkhDSsd_t6pVRiWfY4MfVE0lVj9b4V_fx4,527
+sarvamai/speech_to_text_translate_streaming/client.py,sha256=p8iZeb5cM8QfHIp_1Z36CLJLnkgn81wKCItLdy0-Mbc,11103
+sarvamai/speech_to_text_translate_streaming/raw_client.py,sha256=N7BqiHl5nHIdR-fEq9B4l99aJL1UQ2CQpU6nHxM698M,10212
 sarvamai/speech_to_text_translate_streaming/socket_client.py,sha256=ipEPSj5eHAyDpuEXfaP7JJL1rXJXGEo-IB888ReAFKs,8901
-sarvamai/speech_to_text_translate_streaming/types/__init__.py,sha256=__-K5UkFN9kA_-6kw6ApPt616nPsu8L2GS5CiJILb28,873
+sarvamai/speech_to_text_translate_streaming/types/__init__.py,sha256=nsKmvwkhcPekF9kcStDhTDilALFf2jT-wfCn25KVe7U,740
 sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_flush_signal.py,sha256=jkjvCGJ1pFKi3AOTkwMW-lo18WGgrgAhMpoe5P0AMzA,182
 sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_high_vad_sensitivity.py,sha256=r6MvTlkM0VEpb4dpnMHtINOZ-gYc22o0Fx_Xce2rjvo,189
 sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_input_audio_codec.py,sha256=IwO6IF9BQU5MpGWs7m-w0dV8yp__7s4y3L4hHDErBWM,593
-sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_model.py,sha256=6B8VxkpJG_pNprCSctseDtJb_ULVdKrPaeENkQ6Jvjg,187
 sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_vad_signals.py,sha256=EV3xd9qyKMnMvA9rO-qFDDIac4b84roBu7n-maaPxG8,181
 sarvamai/text/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
 sarvamai/text/client.py,sha256=2kA0Gxfi-r52zMQdqRRD811014alzlHB_FANkp3Kn_c,30595
@@ -127,7 +125,7 @@ sarvamai/text_to_speech/raw_client.py,sha256=si_aSjMR7SocIpKZFoVYqBmaIDuRm_6vxTM
 sarvamai/text_to_speech_streaming/__init__.py,sha256=TjBDNPwnsPQpuVZzh7Xi27A51pEEfVyaC8dpvafkmvQ,201
 sarvamai/text_to_speech_streaming/client.py,sha256=3WsyEcRI6h5EUeGCNZzWG-t-VJA2a7ceoGkXKBBNq7s,7415
 sarvamai/text_to_speech_streaming/raw_client.py,sha256=CHX4t6SiwEvRTflnKI61q0Z3GtjHzHb4Xz-yk2exxeU,6596
-sarvamai/text_to_speech_streaming/socket_client.py,sha256=NEcijnvjuNcWfzqpBi-xWsXVkL0NPq6EGAkEjnaq9hw,13909
+sarvamai/text_to_speech_streaming/socket_client.py,sha256=aun1nyc5ZYziXP0FmyvkCB0WKa_VdjA0XHYI2-Z_gCo,13973
 sarvamai/text_to_speech_streaming/types/__init__.py,sha256=fx2VJtnbh4RFUETiV2aPGslEQ0lq_us4UjDbQr_2J6I,242
 sarvamai/text_to_speech_streaming/types/text_to_speech_streaming_send_completion_event.py,sha256=cZWm6cAwNwPGF8ZADtnRev_AsgM_xj5ypg2oHHQfgZI,181
 sarvamai/types/__init__.py,sha256=hBtXC7VLxZdrBEPs7-Ym6c3fYlJJS1VxHbfb4J8CcEM,8334
@@ -135,7 +133,7 @@ sarvamai/types/audio_data.py,sha256=g-sQcFXiV0uFAsUJ_TjM3OSnPoCUmNkMORRJHOl152k,
 sarvamai/types/audio_data_input_audio_codec.py,sha256=Xb3UEr2wTniW0z8ND4iV051YHhgFazIFOd7q7UGH3nY,572
 sarvamai/types/audio_message.py,sha256=sB4EgkWkWJzipYXobkmM9AYZTTZtCpg_ySKssUeznUE,560
 sarvamai/types/audio_output.py,sha256=Eq-YUZa1mSDwt7bax2c4Vv2gBlyM_JBJWzHhTAhFSko,621
-sarvamai/types/audio_output_data.py,sha256=Og-yoeYzL--9G0-HATRe_M_XkKP6uLWuc1Qxbjte8LI,745
+sarvamai/types/audio_output_data.py,sha256=WMT8W_48uhosfvLOmyyfnCxPKMlgPFDfi3tjjgW8jFY,868
 sarvamai/types/base_job_parameters.py,sha256=x-6SDzT2JxsGNUNuMskw8drWj6UwqgCaeo33XrlgKvo,509
 sarvamai/types/bulk_job_callback.py,sha256=mEpKCadWIqZhXlaJztnAhGmydln_6ykvEotFGEQ0RtI,739
 sarvamai/types/bulk_job_init_response_v_1.py,sha256=iYr_jSp443R1IoQdlLtDK6f78z2x-47feBnhUXCdWBU,894
@@ -163,7 +161,7 @@ sarvamai/types/error_data.py,sha256=gdlrdKLkfgGoe-znCCfWTikKlf07iZy1l4lgPyZTPwE,
 sarvamai/types/error_details.py,sha256=Faggc5PWERfCN2d9E5JzsEMNq9XSnoPTEdgi0lL8ea0,935
 sarvamai/types/error_message.py,sha256=i_vDykKyMlkWLhJCpMAeYI1NzRDFsW2CTU4-mzdBAfE,622
 sarvamai/types/error_response.py,sha256=3m17Aj3GY_-mSY2lH-GkbuiyewTm-wNL9UQ1exLvXyQ,629
-sarvamai/types/error_response_data.py,sha256=hncN_zmPg8kqSHjNciYLn2QeNqzqHxKiZDlKOvjKdwA,838
+sarvamai/types/error_response_data.py,sha256=3OzlX46boFwfUVh6nBZRzRbf_Z3EcY4CBqT9MWk9fPw,961
 sarvamai/types/event_response.py,sha256=95pQQ8NApQ0jCRO4045vvW_GfnEkuecgptXmCMeR5fE,811
 sarvamai/types/event_response_data.py,sha256=tbyMxPhcC3MRWtgxKWF1VC1g_jmW5S0x0mUMARVbrmw,919
 sarvamai/types/events_data.py,sha256=9Gt9CuKF9Y9LmidxAxqTaE2SJgRhEIV_5Nk7X_S-HgU,1146
@@ -189,14 +187,14 @@ sarvamai/types/send_text_data.py,sha256=H8yfcvd4gvyN34RrZ9i4qQvieednNBhL7i7isX4a
 sarvamai/types/speech_sample_rate.py,sha256=Hfi79KL2Y1W7OIvvrfWnt7EUvmU5i7bxYvXivrY_aUA,88
 sarvamai/types/speech_to_text_job_parameters.py,sha256=J2DL2Q-Wzjk7vbPklbVWwn05uDfupCtQ97O32ttJa68,1438
 sarvamai/types/speech_to_text_language.py,sha256=cq8FBOX0DfYB3v8jgNteQtHeJcqWqzKWJVyYGwwo_w0,279
-sarvamai/types/speech_to_text_model.py,sha256=cYANeE-1Kjdpju97bLdQa8GuGqMBn0hVK4McFVqUGT0,208
+sarvamai/types/speech_to_text_model.py,sha256=DSnGHPpIT-OyRv1bpy1xqEoLw90MTKyDgc9JIPe-ycI,131
 sarvamai/types/speech_to_text_response.py,sha256=iWRGEJeHUFIOxeEhoCQu68njeA6lcqXbT2czV-O8Wx0,1438
 sarvamai/types/speech_to_text_response_data.py,sha256=gbxZTBSjbN3ZIa10K6tWPYtymcpnQTFIaUnXkOmsmD4,322
 sarvamai/types/speech_to_text_streaming_response.py,sha256=z6tVAHbVK9lC3w3lac__LEUfO8AAzEilkeGlaLskTtc,687
 sarvamai/types/speech_to_text_transcription_data.py,sha256=EqwPAPSi98PwARaTj-ufzFUSHyN-NPoPla5vi_KERrU,1297
 sarvamai/types/speech_to_text_translate_job_parameters.py,sha256=fvfcyzIyT0DtcRYePDvglHH-wAhGbsi3H5G4i5nuWT8,1409
 sarvamai/types/speech_to_text_translate_language.py,sha256=yikNM-roIumVG-eqBWss93wLGudZdLPwd0i3VcXH5zo,263
-sarvamai/types/speech_to_text_translate_model.py,sha256=hxKnhnelhH5Ah8QO5SymTJMnDw_WWAhGDJnutoNk3qw,213
+sarvamai/types/speech_to_text_translate_model.py,sha256=CVSz6gJBY82GhhEuWSdzRLJW9XTsAgweRnKd1tN6mXo,139
 sarvamai/types/speech_to_text_translate_response.py,sha256=Z5Na7IQW2ok3TP21xd-jKkwioplEKfonNIMhoJQKkVw,1278
 sarvamai/types/speech_to_text_translate_response_data.py,sha256=_NlLVp7oQU3em_4E47QVbIP9nromPE07Z9HtMpY1lrU,359
 sarvamai/types/speech_to_text_translate_streaming_response.py,sha256=J6h3AGdAJxpODFs30bR-e6OaWKa__oVhwv_TrbPSO98,724
@@ -226,6 +224,6 @@ 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-0.1.20a1.dist-info/METADATA,sha256=Kupxz3ZTha7d7va3jRouKTDdKJtgPLAta8HxQCFHWV4,26753
-sarvamai-0.1.20a1.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-sarvamai-0.1.20a1.dist-info/RECORD,,
+sarvamai-0.1.20a3.dist-info/METADATA,sha256=m3M5A9uBZCGLv8cidbPuqOpJOyOgna77JiJAzq6eGR0,26753
+sarvamai-0.1.20a3.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+sarvamai-0.1.20a3.dist-info/RECORD,,

sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_model.py

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

sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_model.py

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