sarvamai 0.1.8rc5__tar.gz → 0.1.8rc6__tar.gz

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.8rc5
+Version: 0.1.8rc6
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.8rc5"
+version = "0.1.8rc6"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/src/sarvamai/__init__.py

@@ -154,7 +154,6 @@ from .speech_to_text_translate_streaming import (
     SpeechToTextTranslateStreamingModel,
     SpeechToTextTranslateStreamingVadSignals,
 )
-from .text_to_speech_streaming import TextToSpeechStreamingModel
 from .version import __version__
 
 __all__ = [
@@ -274,7 +273,6 @@ __all__ = [
     "TextToSpeechResponse",
     "TextToSpeechResponseParams",
     "TextToSpeechSpeaker",
-    "TextToSpeechStreamingModel",
     "TimestampsModel",
     "TimestampsModelParams",
     "TooManyRequestsError",

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/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/0.1.8rc5",
+            "User-Agent": "sarvamai/0.1.8rc6",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.8rc5",
+            "X-Fern-SDK-Version": "0.1.8rc6",
         }
         headers["api-subscription-key"] = self.api_subscription_key
         return headers

sarvamai-0.1.8rc6/src/sarvamai/requests/flush_signal.py

@@ -0,0 +1,14 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+
+
+class FlushSignalParams(typing_extensions.TypedDict):
+    """
+    Forces the text buffer to process immediately, regardless of the min_buffer_size threshold.
+    Use this when you need to process remaining text that hasn't reached the minimum buffer size.
+    """
+
+    type: typing.Literal["flush"]

sarvamai-0.1.8rc6/src/sarvamai/requests/initialize_connection.py

@@ -0,0 +1,18 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from .initialize_connection_data import InitializeConnectionDataParams
+
+
+class InitializeConnectionParams(typing_extensions.TypedDict):
+    """
+    Configuration message required as the first message after establishing the WebSocket connection.
+    This initializes TTS parameters and can be updated at any time during the WebSocket lifecycle
+    by sending a new config message. When a config update is sent, any text currently in the buffer
+    will be automatically flushed and processed before applying the new configuration.
+    """
+
+    type: typing.Literal["config"]
+    data: InitializeConnectionDataParams

sarvamai-0.1.8rc6/src/sarvamai/requests/initialize_connection_data.py

@@ -0,0 +1,83 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from ..types.initialize_connection_data_output_audio_bitrate import InitializeConnectionDataOutputAudioBitrate
+from ..types.initialize_connection_data_speaker import InitializeConnectionDataSpeaker
+from ..types.initialize_connection_data_target_language_code import InitializeConnectionDataTargetLanguageCode
+
+
+class InitializeConnectionDataParams(typing_extensions.TypedDict):
+    target_language_code: InitializeConnectionDataTargetLanguageCode
+    """
+    The language of the text is BCP-47 format
+    """
+
+    speaker: InitializeConnectionDataSpeaker
+    """
+    The speaker voice to be used for the output audio.
+    
+    **Default:** Anushka
+    
+    **Model Compatibility (Speakers compatible with respective model):**
+    - **bulbul:v2:**
+      - Female: Anushka, Manisha, Vidya, Arya
+      - Male: Abhilash, Karun, Hitesh
+    
+    **Note:** Speaker selection must match the chosen model version.
+    """
+
+    pitch: typing_extensions.NotRequired[float]
+    """
+    Controls the pitch of the audio. Lower values result in a deeper voice, 
+    while higher values make it sharper. The suitable range is between -0.75 
+    and 0.75. Default is 0.0.
+    """
+
+    pace: typing_extensions.NotRequired[float]
+    """
+    Controls the speed of the audio. Lower values result in slower speech, 
+    while higher values make it faster. The suitable range is between 0.5 
+    and 2.0. Default is 1.0.
+    """
+
+    loudness: typing_extensions.NotRequired[float]
+    """
+    Controls the loudness of the audio. Lower values result in quieter audio, 
+    while higher values make it louder. The suitable range is between 0.3 
+    and 3.0. Default is 1.0.
+    """
+
+    speech_sample_rate: typing_extensions.NotRequired[int]
+    """
+    Specifies the sample rate of the output audio. Supported values are 
+    8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+    """
+
+    enable_preprocessing: typing_extensions.NotRequired[bool]
+    """
+    Controls whether normalization of English words and numeric entities 
+    (e.g., numbers, dates) is performed. Set to true for better handling 
+    of mixed-language text. Default is false.
+    """
+
+    output_audio_codec: typing_extensions.NotRequired[typing.Literal["mp3"]]
+    """
+    Audio codec (currently supports MP3 only, optimized for real-time playback)
+    """
+
+    output_audio_bitrate: typing_extensions.NotRequired[InitializeConnectionDataOutputAudioBitrate]
+    """
+    Audio bitrate (choose from 5 supported bitrate options)
+    """
+
+    min_buffer_size: typing_extensions.NotRequired[int]
+    """
+    Minimum character length that triggers buffer flushing for TTS model processing
+    """
+
+    max_chunk_length: typing_extensions.NotRequired[int]
+    """
+    Maximum length for sentence splitting (adjust based on content length)
+    """

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/src/sarvamai/requests/ping_signal.py

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

sarvamai-0.1.8rc6/src/sarvamai/text_to_speech_streaming/__init__.py

@@ -0,0 +1,4 @@
+# This file was auto-generated by Fern from our API Definition.
+
+# isort: skip_file
+

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/src/sarvamai/text_to_speech_streaming/client.py

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

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/src/sarvamai/text_to_speech_streaming/raw_client.py

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

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/src/sarvamai/types/flush_signal.py

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

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/src/sarvamai/types/initialize_connection.py

@@ -8,6 +8,13 @@ from .initialize_connection_data import InitializeConnectionData
 
 
 class InitializeConnection(UniversalBaseModel):
+    """
+    Configuration message required as the first message after establishing the WebSocket connection.
+    This initializes TTS parameters and can be updated at any time during the WebSocket lifecycle
+    by sending a new config message. When a config update is sent, any text currently in the buffer
+    will be automatically flushed and processed before applying the new configuration.
+    """
+
     type: typing.Literal["config"] = "config"
     data: InitializeConnectionData
 

sarvamai-0.1.8rc6/src/sarvamai/types/initialize_connection_data.py

@@ -0,0 +1,93 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .initialize_connection_data_output_audio_bitrate import InitializeConnectionDataOutputAudioBitrate
+from .initialize_connection_data_speaker import InitializeConnectionDataSpeaker
+from .initialize_connection_data_target_language_code import InitializeConnectionDataTargetLanguageCode
+
+
+class InitializeConnectionData(UniversalBaseModel):
+    target_language_code: InitializeConnectionDataTargetLanguageCode = pydantic.Field()
+    """
+    The language of the text is BCP-47 format
+    """
+
+    speaker: InitializeConnectionDataSpeaker = pydantic.Field()
+    """
+    The speaker voice to be used for the output audio.
+    
+    **Default:** Anushka
+    
+    **Model Compatibility (Speakers compatible with respective model):**
+    - **bulbul:v2:**
+      - Female: Anushka, Manisha, Vidya, Arya
+      - Male: Abhilash, Karun, Hitesh
+    
+    **Note:** Speaker selection must match the chosen model version.
+    """
+
+    pitch: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    Controls the pitch of the audio. Lower values result in a deeper voice, 
+    while higher values make it sharper. The suitable range is between -0.75 
+    and 0.75. Default is 0.0.
+    """
+
+    pace: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    Controls the speed of the audio. Lower values result in slower speech, 
+    while higher values make it faster. The suitable range is between 0.5 
+    and 2.0. Default is 1.0.
+    """
+
+    loudness: typing.Optional[float] = pydantic.Field(default=None)
+    """
+    Controls the loudness of the audio. Lower values result in quieter audio, 
+    while higher values make it louder. The suitable range is between 0.3 
+    and 3.0. Default is 1.0.
+    """
+
+    speech_sample_rate: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Specifies the sample rate of the output audio. Supported values are 
+    8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+    """
+
+    enable_preprocessing: typing.Optional[bool] = pydantic.Field(default=None)
+    """
+    Controls whether normalization of English words and numeric entities 
+    (e.g., numbers, dates) is performed. Set to true for better handling 
+    of mixed-language text. Default is false.
+    """
+
+    output_audio_codec: typing.Optional[typing.Literal["mp3"]] = pydantic.Field(default=None)
+    """
+    Audio codec (currently supports MP3 only, optimized for real-time playback)
+    """
+
+    output_audio_bitrate: typing.Optional[InitializeConnectionDataOutputAudioBitrate] = pydantic.Field(default=None)
+    """
+    Audio bitrate (choose from 5 supported bitrate options)
+    """
+
+    min_buffer_size: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Minimum character length that triggers buffer flushing for TTS model processing
+    """
+
+    max_chunk_length: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Maximum length for sentence splitting (adjust based on content length)
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai-0.1.8rc6/src/sarvamai/types/initialize_connection_data_speaker.py

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

{sarvamai-0.1.8rc5 → sarvamai-0.1.8rc6}/src/sarvamai/types/ping_signal.py

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

sarvamai-0.1.8rc5/src/sarvamai/requests/flush_signal.py

@@ -1,9 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import typing_extensions
-
-
-class FlushSignalParams(typing_extensions.TypedDict):
-    type: typing.Literal["flush"]

sarvamai-0.1.8rc5/src/sarvamai/requests/initialize_connection.py

@@ -1,11 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import typing_extensions
-from .initialize_connection_data import InitializeConnectionDataParams
-
-
-class InitializeConnectionParams(typing_extensions.TypedDict):
-    type: typing.Literal["config"]
-    data: InitializeConnectionDataParams

sarvamai-0.1.8rc5/src/sarvamai/requests/initialize_connection_data.py

@@ -1,22 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import typing_extensions
-from ..types.initialize_connection_data_output_audio_bitrate import InitializeConnectionDataOutputAudioBitrate
-from ..types.initialize_connection_data_speaker import InitializeConnectionDataSpeaker
-from ..types.initialize_connection_data_target_language_code import InitializeConnectionDataTargetLanguageCode
-
-
-class InitializeConnectionDataParams(typing_extensions.TypedDict):
-    target_language_code: InitializeConnectionDataTargetLanguageCode
-    speaker: InitializeConnectionDataSpeaker
-    pitch: typing_extensions.NotRequired[float]
-    pace: typing_extensions.NotRequired[float]
-    loudness: typing_extensions.NotRequired[float]
-    speech_sample_rate: typing_extensions.NotRequired[int]
-    enable_preprocessing: typing_extensions.NotRequired[bool]
-    output_audio_codec: typing_extensions.NotRequired[typing.Literal["mp3"]]
-    output_audio_bitrate: typing_extensions.NotRequired[InitializeConnectionDataOutputAudioBitrate]
-    min_buffer_size: typing_extensions.NotRequired[int]
-    max_chunk_length: typing_extensions.NotRequired[int]

sarvamai-0.1.8rc5/src/sarvamai/text_to_speech_streaming/__init__.py

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

sarvamai-0.1.8rc5/src/sarvamai/text_to_speech_streaming/types/__init__.py

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

sarvamai-0.1.8rc5/src/sarvamai/text_to_speech_streaming/types/text_to_speech_streaming_model.py

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

sarvamai-0.1.8rc5/src/sarvamai/types/initialize_connection_data.py

@@ -1,32 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-import pydantic
-from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
-from .initialize_connection_data_output_audio_bitrate import InitializeConnectionDataOutputAudioBitrate
-from .initialize_connection_data_speaker import InitializeConnectionDataSpeaker
-from .initialize_connection_data_target_language_code import InitializeConnectionDataTargetLanguageCode
-
-
-class InitializeConnectionData(UniversalBaseModel):
-    target_language_code: InitializeConnectionDataTargetLanguageCode
-    speaker: InitializeConnectionDataSpeaker
-    pitch: typing.Optional[float] = None
-    pace: typing.Optional[float] = None
-    loudness: typing.Optional[float] = None
-    speech_sample_rate: typing.Optional[int] = None
-    enable_preprocessing: typing.Optional[bool] = None
-    output_audio_codec: typing.Optional[typing.Literal["mp3"]] = None
-    output_audio_bitrate: typing.Optional[InitializeConnectionDataOutputAudioBitrate] = None
-    min_buffer_size: typing.Optional[int] = None
-    max_chunk_length: typing.Optional[int] = None
-
-    if IS_PYDANTIC_V2:
-        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
-    else:
-
-        class Config:
-            frozen = True
-            smart_union = True
-            extra = pydantic.Extra.allow

sarvamai-0.1.8rc5/src/sarvamai/types/initialize_connection_data_speaker.py

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