sarvamai 0.1.20a0__tar.gz → 0.1.20a2__tar.gz

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.20a0
+Version: 0.1.20a2
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.20a0"
+version = "0.1.20a2"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/__init__.py

@@ -4,6 +4,7 @@
 
 from .types import (
     AudioData,
+    AudioDataInputAudioCodec,
     AudioMessage,
     AudioOutput,
     AudioOutputData,
@@ -19,6 +20,7 @@ from .types import (
     ChatCompletionRequestUserMessage,
     ChatCompletionResponseMessage,
     Choice,
+    CompletionEventFlag,
     CompletionUsage,
     ConfigMessage,
     ConfigureConnection,
@@ -27,6 +29,7 @@ from .types import (
     ConfigureConnectionDataOutputAudioCodec,
     ConfigureConnectionDataSpeaker,
     ConfigureConnectionDataTargetLanguageCode,
+    ConnectionSampleRate,
     CreateChatCompletionResponse,
     DiarizedEntry,
     DiarizedTranscript,
@@ -36,6 +39,8 @@ from .types import (
     ErrorMessage,
     ErrorResponse,
     ErrorResponseData,
+    EventResponse,
+    EventResponseData,
     EventsData,
     EventsDataSignalType,
     FileSignedUrlDetails,
@@ -146,6 +151,8 @@ from .requests import (
     ErrorMessageParams,
     ErrorResponseDataParams,
     ErrorResponseParams,
+    EventResponseDataParams,
+    EventResponseParams,
     EventsDataParams,
     FileSignedUrlDetailsParams,
     FilesDownloadResponseParams,
@@ -180,6 +187,7 @@ from .requests import (
 from .speech_to_text_streaming import (
     SpeechToTextStreamingFlushSignal,
     SpeechToTextStreamingHighVadSensitivity,
+    SpeechToTextStreamingInputAudioCodec,
     SpeechToTextStreamingLanguageCode,
     SpeechToTextStreamingModel,
     SpeechToTextStreamingVadSignals,
@@ -187,14 +195,17 @@ from .speech_to_text_streaming import (
 from .speech_to_text_translate_streaming import (
     SpeechToTextTranslateStreamingFlushSignal,
     SpeechToTextTranslateStreamingHighVadSensitivity,
+    SpeechToTextTranslateStreamingInputAudioCodec,
     SpeechToTextTranslateStreamingModel,
     SpeechToTextTranslateStreamingVadSignals,
 )
+from .text_to_speech_streaming import TextToSpeechStreamingSendCompletionEvent
 from .version import __version__
 
 __all__ = [
     "AsyncSarvamAI",
     "AudioData",
+    "AudioDataInputAudioCodec",
     "AudioDataParams",
     "AudioMessage",
     "AudioMessageParams",
@@ -227,6 +238,7 @@ __all__ = [
     "ChatCompletionResponseMessageParams",
     "Choice",
     "ChoiceParams",
+    "CompletionEventFlag",
     "CompletionUsage",
     "CompletionUsageParams",
     "ConfigMessage",
@@ -239,6 +251,7 @@ __all__ = [
     "ConfigureConnectionDataSpeaker",
     "ConfigureConnectionDataTargetLanguageCode",
     "ConfigureConnectionParams",
+    "ConnectionSampleRate",
     "CreateChatCompletionResponse",
     "CreateChatCompletionResponseParams",
     "DiarizedEntry",
@@ -256,6 +269,10 @@ __all__ = [
     "ErrorResponseData",
     "ErrorResponseDataParams",
     "ErrorResponseParams",
+    "EventResponse",
+    "EventResponseData",
+    "EventResponseDataParams",
+    "EventResponseParams",
     "EventsData",
     "EventsDataParams",
     "EventsDataSignalType",
@@ -303,6 +320,7 @@ __all__ = [
     "SpeechToTextResponseParams",
     "SpeechToTextStreamingFlushSignal",
     "SpeechToTextStreamingHighVadSensitivity",
+    "SpeechToTextStreamingInputAudioCodec",
     "SpeechToTextStreamingLanguageCode",
     "SpeechToTextStreamingModel",
     "SpeechToTextStreamingResponse",
@@ -320,6 +338,7 @@ __all__ = [
     "SpeechToTextTranslateResponseParams",
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
+    "SpeechToTextTranslateStreamingInputAudioCodec",
     "SpeechToTextTranslateStreamingModel",
     "SpeechToTextTranslateStreamingResponse",
     "SpeechToTextTranslateStreamingResponseParams",
@@ -343,6 +362,7 @@ __all__ = [
     "TextToSpeechResponse",
     "TextToSpeechResponseParams",
     "TextToSpeechSpeaker",
+    "TextToSpeechStreamingSendCompletionEvent",
     "TimestampsModel",
     "TimestampsModelParams",
     "TooManyRequestsError",

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/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/0.1.20a0",
+            "User-Agent": "sarvamai/0.1.20a2",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.20a0",
+            "X-Fern-SDK-Version": "0.1.20a2",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/requests/__init__.py

@@ -32,6 +32,8 @@ 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
@@ -92,6 +94,8 @@ __all__ = [
     "ErrorMessageParams",
     "ErrorResponseDataParams",
     "ErrorResponseParams",
+    "EventResponseDataParams",
+    "EventResponseParams",
     "EventsDataParams",
     "FileSignedUrlDetailsParams",
     "FilesDownloadResponseParams",

sarvamai-0.1.20a2/src/sarvamai/requests/audio_data.py

@@ -0,0 +1,34 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.audio_data_input_audio_codec import AudioDataInputAudioCodec
+
+
+class AudioDataParams(typing_extensions.TypedDict):
+    data: str
+    """
+    Base64 encoded audio data
+    """
+
+    sample_rate: int
+    """
+    Audio sample rate in Hz for individual audio messages. 
+    
+    **Backward Compatibility**: This property is maintained for legacy support.
+    **Recommended**: Use the connection-level sample_rate parameter instead.
+    **Note**: 8kHz is only supported via connection parameter, not in AudioData messages.
+    
+    Supported values: 16kHz (preferred), 22.05kHz, 24kHz
+    """
+
+    encoding: typing.Literal["audio/wav"]
+    """
+    Audio encoding format
+    """
+
+    input_audio_codec: typing_extensions.NotRequired[AudioDataInputAudioCodec]
+    """
+    Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+    """

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/requests/audio_output_data.py

@@ -13,8 +13,3 @@ 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-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/requests/error_response_data.py

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

sarvamai-0.1.20a2/src/sarvamai/requests/event_response.py

@@ -0,0 +1,19 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from .event_response_data import EventResponseDataParams
+
+
+class EventResponseParams(typing_extensions.TypedDict):
+    """
+    Event notification message sent when specific events occur during TTS processing
+    """
+
+    type: typing.Literal["event"]
+    """
+    Message type identifier for events
+    """
+
+    data: EventResponseDataParams

sarvamai-0.1.20a2/src/sarvamai/requests/event_response_data.py

@@ -0,0 +1,23 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+import typing_extensions
+
+
+class EventResponseDataParams(typing_extensions.TypedDict):
+    event_type: typing.Literal["final"]
+    """
+    Type of event that occurred
+    """
+
+    message: typing_extensions.NotRequired[str]
+    """
+    Human-readable description of the event
+    """
+
+    timestamp: typing_extensions.NotRequired[dt.datetime]
+    """
+    ISO 8601 timestamp when the event occurred
+    """

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/speech_to_text_streaming/__init__.py

@@ -5,6 +5,7 @@
 from .types import (
     SpeechToTextStreamingFlushSignal,
     SpeechToTextStreamingHighVadSensitivity,
+    SpeechToTextStreamingInputAudioCodec,
     SpeechToTextStreamingLanguageCode,
     SpeechToTextStreamingModel,
     SpeechToTextStreamingVadSignals,
@@ -13,6 +14,7 @@ from .types import (
 __all__ = [
     "SpeechToTextStreamingFlushSignal",
     "SpeechToTextStreamingHighVadSensitivity",
+    "SpeechToTextStreamingInputAudioCodec",
     "SpeechToTextStreamingLanguageCode",
     "SpeechToTextStreamingModel",
     "SpeechToTextStreamingVadSignals",

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/speech_to_text_streaming/client.py

@@ -13,6 +13,7 @@ from .raw_client import AsyncRawSpeechToTextStreamingClient, RawSpeechToTextStre
 from .socket_client import AsyncSpeechToTextStreamingSocketClient, SpeechToTextStreamingSocketClient
 from .types.speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSignal
 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
@@ -44,6 +45,8 @@ class SpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[SpeechToTextStreamingModel] = None,
+        input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
+        sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextStreamingFlushSignal] = None,
@@ -61,6 +64,12 @@ class SpeechToTextStreamingClient:
         model : typing.Optional[SpeechToTextStreamingModel]
             Speech to text model to use
 
+        input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
+            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+
+        sample_rate : typing.Optional[str]
+            Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
+
         high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
@@ -86,6 +95,10 @@ class SpeechToTextStreamingClient:
             query_params = query_params.add("language-code", language_code)
         if model is not None:
             query_params = query_params.add("model", model)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
+        if sample_rate is not None:
+            query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
             query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
         if vad_signals is not None:
@@ -137,6 +150,8 @@ class AsyncSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[SpeechToTextStreamingModel] = None,
+        input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
+        sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextStreamingFlushSignal] = None,
@@ -154,6 +169,12 @@ class AsyncSpeechToTextStreamingClient:
         model : typing.Optional[SpeechToTextStreamingModel]
             Speech to text model to use
 
+        input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
+            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+
+        sample_rate : typing.Optional[str]
+            Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
+
         high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
@@ -179,6 +200,10 @@ class AsyncSpeechToTextStreamingClient:
             query_params = query_params.add("language-code", language_code)
         if model is not None:
             query_params = query_params.add("model", model)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
+        if sample_rate is not None:
+            query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
             query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
         if vad_signals is not None:

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/speech_to_text_streaming/raw_client.py

@@ -12,6 +12,7 @@ from ..core.request_options import RequestOptions
 from .socket_client import AsyncSpeechToTextStreamingSocketClient, SpeechToTextStreamingSocketClient
 from .types.speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSignal
 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
@@ -32,6 +33,8 @@ class RawSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[SpeechToTextStreamingModel] = None,
+        input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
+        sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextStreamingFlushSignal] = None,
@@ -49,6 +52,12 @@ class RawSpeechToTextStreamingClient:
         model : typing.Optional[SpeechToTextStreamingModel]
             Speech to text model to use
 
+        input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
+            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+
+        sample_rate : typing.Optional[str]
+            Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
+
         high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
@@ -74,6 +83,10 @@ class RawSpeechToTextStreamingClient:
             query_params = query_params.add("language-code", language_code)
         if model is not None:
             query_params = query_params.add("model", model)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
+        if sample_rate is not None:
+            query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
             query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
         if vad_signals is not None:
@@ -114,6 +127,8 @@ class AsyncRawSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[SpeechToTextStreamingModel] = None,
+        input_audio_codec: typing.Optional[SpeechToTextStreamingInputAudioCodec] = None,
+        sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextStreamingFlushSignal] = None,
@@ -131,6 +146,12 @@ class AsyncRawSpeechToTextStreamingClient:
         model : typing.Optional[SpeechToTextStreamingModel]
             Speech to text model to use
 
+        input_audio_codec : typing.Optional[SpeechToTextStreamingInputAudioCodec]
+            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+
+        sample_rate : typing.Optional[str]
+            Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
+
         high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
@@ -156,6 +177,10 @@ class AsyncRawSpeechToTextStreamingClient:
             query_params = query_params.add("language-code", language_code)
         if model is not None:
             query_params = query_params.add("model", model)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
+        if sample_rate is not None:
+            query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
             query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
         if vad_signals is not None:

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/speech_to_text_streaming/types/__init__.py

@@ -4,6 +4,7 @@
 
 from .speech_to_text_streaming_flush_signal import SpeechToTextStreamingFlushSignal
 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
@@ -11,6 +12,7 @@ from .speech_to_text_streaming_vad_signals import SpeechToTextStreamingVadSignal
 __all__ = [
     "SpeechToTextStreamingFlushSignal",
     "SpeechToTextStreamingHighVadSensitivity",
+    "SpeechToTextStreamingInputAudioCodec",
     "SpeechToTextStreamingLanguageCode",
     "SpeechToTextStreamingModel",
     "SpeechToTextStreamingVadSignals",

sarvamai-0.1.20a2/src/sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_input_audio_codec.py

@@ -0,0 +1,33 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+SpeechToTextStreamingInputAudioCodec = typing.Union[
+    typing.Literal[
+        "wav",
+        "x-wav",
+        "wave",
+        "mp3",
+        "mpeg",
+        "mpeg3",
+        "x-mp3",
+        "x-mpeg-3",
+        "aac",
+        "x-aac",
+        "aiff",
+        "x-aiff",
+        "ogg",
+        "opus",
+        "flac",
+        "x-flac",
+        "mp4",
+        "x-m4a",
+        "amr",
+        "x-ms-wma",
+        "webm",
+        "pcm_s16le",
+        "pcm_l16",
+        "pcm_raw",
+    ],
+    typing.Any,
+]

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/speech_to_text_translate_streaming/__init__.py

@@ -5,6 +5,7 @@
 from .types import (
     SpeechToTextTranslateStreamingFlushSignal,
     SpeechToTextTranslateStreamingHighVadSensitivity,
+    SpeechToTextTranslateStreamingInputAudioCodec,
     SpeechToTextTranslateStreamingModel,
     SpeechToTextTranslateStreamingVadSignals,
 )
@@ -12,6 +13,7 @@ from .types import (
 __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
+    "SpeechToTextTranslateStreamingInputAudioCodec",
     "SpeechToTextTranslateStreamingModel",
     "SpeechToTextTranslateStreamingVadSignals",
 ]

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/speech_to_text_translate_streaming/client.py

@@ -15,6 +15,7 @@ from .types.speech_to_text_translate_streaming_flush_signal import SpeechToTextT
 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
 
@@ -44,6 +45,8 @@ class SpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
+        sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
@@ -58,6 +61,12 @@ class SpeechToTextTranslateStreamingClient:
         model : typing.Optional[SpeechToTextTranslateStreamingModel]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+
+        sample_rate : typing.Optional[str]
+            Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
+
         high_vad_sensitivity : typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
@@ -81,6 +90,10 @@ class SpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
+        if sample_rate is not None:
+            query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
             query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
         if vad_signals is not None:
@@ -131,6 +144,8 @@ class AsyncSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
+        sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
@@ -145,6 +160,12 @@ class AsyncSpeechToTextTranslateStreamingClient:
         model : typing.Optional[SpeechToTextTranslateStreamingModel]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+
+        sample_rate : typing.Optional[str]
+            Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
+
         high_vad_sensitivity : typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
@@ -168,6 +189,10 @@ class AsyncSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
+        if sample_rate is not None:
+            query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
             query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
         if vad_signals is not None:

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/speech_to_text_translate_streaming/raw_client.py

@@ -14,6 +14,7 @@ from .types.speech_to_text_translate_streaming_flush_signal import SpeechToTextT
 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
 
@@ -32,6 +33,8 @@ class RawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
+        sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
@@ -46,6 +49,12 @@ class RawSpeechToTextTranslateStreamingClient:
         model : typing.Optional[SpeechToTextTranslateStreamingModel]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+
+        sample_rate : typing.Optional[str]
+            Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
+
         high_vad_sensitivity : typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
@@ -69,6 +78,10 @@ class RawSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
+        if sample_rate is not None:
+            query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
             query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
         if vad_signals is not None:
@@ -108,6 +121,8 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
+        sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
@@ -122,6 +137,12 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         model : typing.Optional[SpeechToTextTranslateStreamingModel]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+
+        sample_rate : typing.Optional[str]
+            Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
+
         high_vad_sensitivity : typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
@@ -145,6 +166,10 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
+        if sample_rate is not None:
+            query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
             query_params = query_params.add("high_vad_sensitivity", high_vad_sensitivity)
         if vad_signals is not None:

{sarvamai-0.1.20a0 → sarvamai-0.1.20a2}/src/sarvamai/speech_to_text_translate_streaming/types/__init__.py

@@ -4,12 +4,14 @@
 
 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",
 ]