sarvamai 0.1.5a13__tar.gz → 0.1.6__tar.gz

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.5a13
+Version: 0.1.6
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.5a13"
+version = "0.1.6"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/__init__.py

@@ -4,7 +4,6 @@
 
 from .types import (
     AudioData,
-    AudioDataEncoding,
     AudioMessage,
     ChatCompletionRequestAssistantMessage,
     ChatCompletionRequestMessage,
@@ -113,14 +112,22 @@ from .requests import (
     TranslationResponseParams,
     TransliterationResponseParams,
 )
-from .speech_to_text_streaming import SpeechToTextStreamingLanguageCode, SpeechToTextStreamingModel
-from .speech_to_text_translate_streaming import SpeechToTextTranslateStreamingModel
+from .speech_to_text_streaming import (
+    SpeechToTextStreamingHighVadSensitivity,
+    SpeechToTextStreamingLanguageCode,
+    SpeechToTextStreamingModel,
+    SpeechToTextStreamingVadSignals,
+)
+from .speech_to_text_translate_streaming import (
+    SpeechToTextTranslateStreamingHighVadSensitivity,
+    SpeechToTextTranslateStreamingModel,
+    SpeechToTextTranslateStreamingVadSignals,
+)
 from .version import __version__
 
 __all__ = [
     "AsyncSarvamAI",
     "AudioData",
-    "AudioDataEncoding",
     "AudioDataParams",
     "AudioMessage",
     "AudioMessageParams",
@@ -183,10 +190,12 @@ __all__ = [
     "SpeechToTextResponseData",
     "SpeechToTextResponseDataParams",
     "SpeechToTextResponseParams",
+    "SpeechToTextStreamingHighVadSensitivity",
     "SpeechToTextStreamingLanguageCode",
     "SpeechToTextStreamingModel",
     "SpeechToTextStreamingResponse",
     "SpeechToTextStreamingResponseParams",
+    "SpeechToTextStreamingVadSignals",
     "SpeechToTextTranscriptionData",
     "SpeechToTextTranscriptionDataParams",
     "SpeechToTextTranslateLanguage",
@@ -195,9 +204,11 @@ __all__ = [
     "SpeechToTextTranslateResponseData",
     "SpeechToTextTranslateResponseDataParams",
     "SpeechToTextTranslateResponseParams",
+    "SpeechToTextTranslateStreamingHighVadSensitivity",
     "SpeechToTextTranslateStreamingModel",
     "SpeechToTextTranslateStreamingResponse",
     "SpeechToTextTranslateStreamingResponseParams",
+    "SpeechToTextTranslateStreamingVadSignals",
     "SpeechToTextTranslateTranscriptionData",
     "SpeechToTextTranslateTranscriptionDataParams",
     "SpokenFormNumeralsFormat",

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/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/0.1.5a13",
+            "User-Agent": "sarvamai/0.1.6",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.5a13",
+            "X-Fern-SDK-Version": "0.1.6",
         }
         headers["api-subscription-key"] = self.api_subscription_key
         return headers

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/requests/audio_data.py

@@ -1,7 +1,8 @@
 # This file was auto-generated by Fern from our API Definition.
 
+import typing
+
 import typing_extensions
-from ..types.audio_data_encoding import AudioDataEncoding
 
 
 class AudioDataParams(typing_extensions.TypedDict):
@@ -15,7 +16,7 @@ class AudioDataParams(typing_extensions.TypedDict):
     Audio sample rate in Hz (16kHz preferred, 8kHz least preferred)
     """
 
-    encoding: AudioDataEncoding
+    encoding: typing.Literal["audio/wav"]
     """
     Audio encoding format
     """

sarvamai-0.1.6/src/sarvamai/speech_to_text_streaming/__init__.py

@@ -0,0 +1,17 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+
+from .types import (
+    SpeechToTextStreamingHighVadSensitivity,
+    SpeechToTextStreamingLanguageCode,
+    SpeechToTextStreamingModel,
+    SpeechToTextStreamingVadSignals,
+)
+
+__all__ = [
+    "SpeechToTextStreamingHighVadSensitivity",
+    "SpeechToTextStreamingLanguageCode",
+    "SpeechToTextStreamingModel",
+    "SpeechToTextStreamingVadSignals",
+]

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/speech_to_text_streaming/client.py

@@ -11,8 +11,10 @@ from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from .raw_client import AsyncRawSpeechToTextStreamingClient, RawSpeechToTextStreamingClient
 from .socket_client import AsyncSpeechToTextStreamingSocketClient, SpeechToTextStreamingSocketClient
+from .types.speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
 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
 
 
 class SpeechToTextStreamingClient:
@@ -36,8 +38,8 @@ class SpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[SpeechToTextStreamingModel] = None,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
+        high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
+        vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextStreamingSocketClient]:
@@ -52,10 +54,10 @@ class SpeechToTextStreamingClient:
         model : typing.Optional[SpeechToTextStreamingModel]
             Speech to text model to use
 
-        high_vad_sensitivity : typing.Optional[str]
+        high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
-        vad_signals : typing.Optional[str]
+        vad_signals : typing.Optional[SpeechToTextStreamingVadSignals]
             Enable VAD signals in response
 
         api_subscription_key : typing.Optional[str]
@@ -123,8 +125,8 @@ class AsyncSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[SpeechToTextStreamingModel] = None,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
+        high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
+        vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextStreamingSocketClient]:
@@ -139,10 +141,10 @@ class AsyncSpeechToTextStreamingClient:
         model : typing.Optional[SpeechToTextStreamingModel]
             Speech to text model to use
 
-        high_vad_sensitivity : typing.Optional[str]
+        high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
-        vad_signals : typing.Optional[str]
+        vad_signals : typing.Optional[SpeechToTextStreamingVadSignals]
             Enable VAD signals in response
 
         api_subscription_key : typing.Optional[str]

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/speech_to_text_streaming/raw_client.py

@@ -10,8 +10,10 @@ from ..core.api_error import ApiError
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from .socket_client import AsyncSpeechToTextStreamingSocketClient, SpeechToTextStreamingSocketClient
+from .types.speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
 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
 
 
 class RawSpeechToTextStreamingClient:
@@ -24,8 +26,8 @@ class RawSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[SpeechToTextStreamingModel] = None,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
+        high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
+        vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextStreamingSocketClient]:
@@ -40,10 +42,10 @@ class RawSpeechToTextStreamingClient:
         model : typing.Optional[SpeechToTextStreamingModel]
             Speech to text model to use
 
-        high_vad_sensitivity : typing.Optional[str]
+        high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
-        vad_signals : typing.Optional[str]
+        vad_signals : typing.Optional[SpeechToTextStreamingVadSignals]
             Enable VAD signals in response
 
         api_subscription_key : typing.Optional[str]
@@ -100,8 +102,8 @@ class AsyncRawSpeechToTextStreamingClient:
         *,
         language_code: SpeechToTextStreamingLanguageCode,
         model: typing.Optional[SpeechToTextStreamingModel] = None,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
+        high_vad_sensitivity: typing.Optional[SpeechToTextStreamingHighVadSensitivity] = None,
+        vad_signals: typing.Optional[SpeechToTextStreamingVadSignals] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextStreamingSocketClient]:
@@ -116,10 +118,10 @@ class AsyncRawSpeechToTextStreamingClient:
         model : typing.Optional[SpeechToTextStreamingModel]
             Speech to text model to use
 
-        high_vad_sensitivity : typing.Optional[str]
+        high_vad_sensitivity : typing.Optional[SpeechToTextStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
-        vad_signals : typing.Optional[str]
+        vad_signals : typing.Optional[SpeechToTextStreamingVadSignals]
             Enable VAD signals in response
 
         api_subscription_key : typing.Optional[str]

sarvamai-0.1.6/src/sarvamai/speech_to_text_streaming/types/__init__.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+
+from .speech_to_text_streaming_high_vad_sensitivity import SpeechToTextStreamingHighVadSensitivity
+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__ = [
+    "SpeechToTextStreamingHighVadSensitivity",
+    "SpeechToTextStreamingLanguageCode",
+    "SpeechToTextStreamingModel",
+    "SpeechToTextStreamingVadSignals",
+]

sarvamai-0.1.6/src/sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_high_vad_sensitivity.py

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

sarvamai-0.1.6/src/sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_vad_signals.py

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

sarvamai-0.1.6/src/sarvamai/speech_to_text_translate_streaming/__init__.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+
+from .types import (
+    SpeechToTextTranslateStreamingHighVadSensitivity,
+    SpeechToTextTranslateStreamingModel,
+    SpeechToTextTranslateStreamingVadSignals,
+)
+
+__all__ = [
+    "SpeechToTextTranslateStreamingHighVadSensitivity",
+    "SpeechToTextTranslateStreamingModel",
+    "SpeechToTextTranslateStreamingVadSignals",
+]

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/speech_to_text_translate_streaming/client.py

@@ -11,7 +11,11 @@ from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from .raw_client import AsyncRawSpeechToTextTranslateStreamingClient, RawSpeechToTextTranslateStreamingClient
 from .socket_client import AsyncSpeechToTextTranslateStreamingSocketClient, SpeechToTextTranslateStreamingSocketClient
+from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
+    SpeechToTextTranslateStreamingHighVadSensitivity,
+)
 from .types.speech_to_text_translate_streaming_model import SpeechToTextTranslateStreamingModel
+from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 
 class SpeechToTextTranslateStreamingClient:
@@ -34,8 +38,8 @@ class SpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
+        high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
+        vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextTranslateStreamingSocketClient]:
@@ -47,10 +51,10 @@ class SpeechToTextTranslateStreamingClient:
         model : typing.Optional[SpeechToTextTranslateStreamingModel]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
-        high_vad_sensitivity : typing.Optional[str]
+        high_vad_sensitivity : typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
-        vad_signals : typing.Optional[str]
+        vad_signals : typing.Optional[SpeechToTextTranslateStreamingVadSignals]
             Enable VAD signals in response
 
         api_subscription_key : typing.Optional[str]
@@ -115,8 +119,8 @@ class AsyncSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
+        high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
+        vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextTranslateStreamingSocketClient]:
@@ -128,10 +132,10 @@ class AsyncSpeechToTextTranslateStreamingClient:
         model : typing.Optional[SpeechToTextTranslateStreamingModel]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
-        high_vad_sensitivity : typing.Optional[str]
+        high_vad_sensitivity : typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
-        vad_signals : typing.Optional[str]
+        vad_signals : typing.Optional[SpeechToTextTranslateStreamingVadSignals]
             Enable VAD signals in response
 
         api_subscription_key : typing.Optional[str]

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/speech_to_text_translate_streaming/raw_client.py

@@ -10,7 +10,11 @@ from ..core.api_error import ApiError
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from .socket_client import AsyncSpeechToTextTranslateStreamingSocketClient, SpeechToTextTranslateStreamingSocketClient
+from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
+    SpeechToTextTranslateStreamingHighVadSensitivity,
+)
 from .types.speech_to_text_translate_streaming_model import SpeechToTextTranslateStreamingModel
+from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 
 class RawSpeechToTextTranslateStreamingClient:
@@ -22,8 +26,8 @@ class RawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
+        high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
+        vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextTranslateStreamingSocketClient]:
@@ -35,10 +39,10 @@ class RawSpeechToTextTranslateStreamingClient:
         model : typing.Optional[SpeechToTextTranslateStreamingModel]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
-        high_vad_sensitivity : typing.Optional[str]
+        high_vad_sensitivity : typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
-        vad_signals : typing.Optional[str]
+        vad_signals : typing.Optional[SpeechToTextTranslateStreamingVadSignals]
             Enable VAD signals in response
 
         api_subscription_key : typing.Optional[str]
@@ -92,8 +96,8 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[SpeechToTextTranslateStreamingModel] = None,
-        high_vad_sensitivity: typing.Optional[str] = None,
-        vad_signals: typing.Optional[str] = None,
+        high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
+        vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextTranslateStreamingSocketClient]:
@@ -105,10 +109,10 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         model : typing.Optional[SpeechToTextTranslateStreamingModel]
             Speech to text model to use (defaults to "saaras:v2.5" if not specified)
 
-        high_vad_sensitivity : typing.Optional[str]
+        high_vad_sensitivity : typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity]
             Enable high VAD (Voice Activity Detection) sensitivity
 
-        vad_signals : typing.Optional[str]
+        vad_signals : typing.Optional[SpeechToTextTranslateStreamingVadSignals]
             Enable VAD signals in response
 
         api_subscription_key : typing.Optional[str]

sarvamai-0.1.6/src/sarvamai/speech_to_text_translate_streaming/types/__init__.py

@@ -0,0 +1,13 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+
+from .speech_to_text_translate_streaming_high_vad_sensitivity import SpeechToTextTranslateStreamingHighVadSensitivity
+from .speech_to_text_translate_streaming_model import SpeechToTextTranslateStreamingModel
+from .speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
+
+__all__ = [
+    "SpeechToTextTranslateStreamingHighVadSensitivity",
+    "SpeechToTextTranslateStreamingModel",
+    "SpeechToTextTranslateStreamingVadSignals",
+]

sarvamai-0.1.6/src/sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_high_vad_sensitivity.py

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

sarvamai-0.1.6/src/sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_vad_signals.py

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

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/text_to_speech/client.py

@@ -58,13 +58,9 @@ class TextToSpeechClient:
         speaker : typing.Optional[TextToSpeechSpeaker]
             The speaker voice to be used for the output audio.
 
-            **Default:** Meera
-
-            **Model Compatibility (Speakers compatible with respective models):**
-            - **bulbul:v1:**
-              - Female: Diya, Maya, Meera, Pavithra, Maitreyi, Misha
-              - Male: Amol, Arjun, Amartya, Arvind, Neel, Vian
+            **Default:** Anushka
 
+            **Model Compatibility (Speakers compatible with respective model):**
             - **bulbul:v2:**
               - Female: Anushka, Manisha, Vidya, Arya
               - Male: Abhilash, Karun, Hitesh
@@ -87,7 +83,7 @@ class TextToSpeechClient:
              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.
 
         model : typing.Optional[TextToSpeechModel]
-            Specifies the model to use for text-to-speech conversion. Default is bulbul:v1.
+            Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
@@ -167,13 +163,9 @@ class AsyncTextToSpeechClient:
         speaker : typing.Optional[TextToSpeechSpeaker]
             The speaker voice to be used for the output audio.
 
-            **Default:** Meera
-
-            **Model Compatibility (Speakers compatible with respective models):**
-            - **bulbul:v1:**
-              - Female: Diya, Maya, Meera, Pavithra, Maitreyi, Misha
-              - Male: Amol, Arjun, Amartya, Arvind, Neel, Vian
+            **Default:** Anushka
 
+            **Model Compatibility (Speakers compatible with respective model):**
             - **bulbul:v2:**
               - Female: Anushka, Manisha, Vidya, Arya
               - Male: Abhilash, Karun, Hitesh
@@ -196,7 +188,7 @@ class AsyncTextToSpeechClient:
              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.
 
         model : typing.Optional[TextToSpeechModel]
-            Specifies the model to use for text-to-speech conversion. Default is bulbul:v1.
+            Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/text_to_speech/raw_client.py

@@ -55,13 +55,9 @@ class RawTextToSpeechClient:
         speaker : typing.Optional[TextToSpeechSpeaker]
             The speaker voice to be used for the output audio.
 
-            **Default:** Meera
-
-            **Model Compatibility (Speakers compatible with respective models):**
-            - **bulbul:v1:**
-              - Female: Diya, Maya, Meera, Pavithra, Maitreyi, Misha
-              - Male: Amol, Arjun, Amartya, Arvind, Neel, Vian
+            **Default:** Anushka
 
+            **Model Compatibility (Speakers compatible with respective model):**
             - **bulbul:v2:**
               - Female: Anushka, Manisha, Vidya, Arya
               - Male: Abhilash, Karun, Hitesh
@@ -84,7 +80,7 @@ class RawTextToSpeechClient:
              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.
 
         model : typing.Optional[TextToSpeechModel]
-            Specifies the model to use for text-to-speech conversion. Default is bulbul:v1.
+            Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
@@ -218,13 +214,9 @@ class AsyncRawTextToSpeechClient:
         speaker : typing.Optional[TextToSpeechSpeaker]
             The speaker voice to be used for the output audio.
 
-            **Default:** Meera
-
-            **Model Compatibility (Speakers compatible with respective models):**
-            - **bulbul:v1:**
-              - Female: Diya, Maya, Meera, Pavithra, Maitreyi, Misha
-              - Male: Amol, Arjun, Amartya, Arvind, Neel, Vian
+            **Default:** Anushka
 
+            **Model Compatibility (Speakers compatible with respective model):**
             - **bulbul:v2:**
               - Female: Anushka, Manisha, Vidya, Arya
               - Male: Abhilash, Karun, Hitesh
@@ -247,7 +239,7 @@ class AsyncRawTextToSpeechClient:
              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.
 
         model : typing.Optional[TextToSpeechModel]
-            Specifies the model to use for text-to-speech conversion. Default is bulbul:v1.
+            Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
 
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/types/__init__.py

@@ -3,7 +3,6 @@
 # isort: skip_file
 
 from .audio_data import AudioData
-from .audio_data_encoding import AudioDataEncoding
 from .audio_message import AudioMessage
 from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessage
 from .chat_completion_request_message import (
@@ -68,7 +67,6 @@ from .transliteration_response import TransliterationResponse
 
 __all__ = [
     "AudioData",
-    "AudioDataEncoding",
     "AudioMessage",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestMessage",

{sarvamai-0.1.5a13 → sarvamai-0.1.6}/src/sarvamai/types/audio_data.py

@@ -4,7 +4,6 @@ import typing
 
 import pydantic
 from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .audio_data_encoding import AudioDataEncoding
 
 
 class AudioData(UniversalBaseModel):
@@ -18,7 +17,7 @@ class AudioData(UniversalBaseModel):
     Audio sample rate in Hz (16kHz preferred, 8kHz least preferred)
     """
 
-    encoding: AudioDataEncoding = pydantic.Field()
+    encoding: typing.Literal["audio/wav"] = pydantic.Field(default="audio/wav")
     """
     Audio encoding format
     """

sarvamai-0.1.6/src/sarvamai/types/text_to_speech_model.py

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

sarvamai-0.1.6/src/sarvamai/types/text_to_speech_speaker.py

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

sarvamai-0.1.5a13/src/sarvamai/speech_to_text_streaming/__init__.py

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

sarvamai-0.1.5a13/src/sarvamai/speech_to_text_streaming/types/__init__.py

@@ -1,8 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-# isort: skip_file
-
-from .speech_to_text_streaming_language_code import SpeechToTextStreamingLanguageCode
-from .speech_to_text_streaming_model import SpeechToTextStreamingModel
-
-__all__ = ["SpeechToTextStreamingLanguageCode", "SpeechToTextStreamingModel"]

sarvamai-0.1.5a13/src/sarvamai/speech_to_text_translate_streaming/__init__.py

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

sarvamai-0.1.5a13/src/sarvamai/speech_to_text_translate_streaming/types/__init__.py

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

sarvamai-0.1.5a13/src/sarvamai/types/audio_data_encoding.py

@@ -1,5 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-AudioDataEncoding = typing.Union[typing.Literal["audio/wav", "audio/pcm", "audio/flac", "audio/mp3"], typing.Any]

sarvamai-0.1.5a13/src/sarvamai/types/text_to_speech_model.py

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