sarvamai 0.1.7__py3-none-any.whl → 0.1.8a0__py3-none-any.whl

sarvamai/text_to_speech_streaming/socket_client.py

@@ -0,0 +1,175 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import json
+import typing
+
+import websockets
+import websockets.sync.connection as websockets_sync_connection
+from ..core.events import EventEmitterMixin, EventType
+from ..core.pydantic_utilities import parse_obj_as
+from ..types.audio_output import AudioOutput
+from ..types.close_connection import CloseConnection
+from ..types.error_response import ErrorResponse
+from ..types.initialize_connection import InitializeConnection
+from ..types.ping_signal import PingSignal
+from ..types.send_text import SendText
+
+TextToSpeechStreamingSocketClientResponse = typing.Union[AudioOutput, ErrorResponse]
+
+
+class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
+    def __init__(self, *, websocket: websockets.WebSocketClientProtocol):
+        super().__init__()
+        self._websocket = websocket
+
+    async def __aiter__(self):
+        async for message in self._websocket:
+            yield parse_obj_as(TextToSpeechStreamingSocketClientResponse, message)  # type: ignore
+
+    async def start_listening(self):
+        """
+        Start listening for messages on the websocket connection.
+
+        Emits events in the following order:
+        - EventType.OPEN when connection is established
+        - EventType.MESSAGE for each message received
+        - EventType.ERROR if an error occurs
+        - EventType.CLOSE when connection is closed
+        """
+        self._emit(EventType.OPEN, None)
+        try:
+            async for raw_message in self._websocket:
+                parsed = parse_obj_as(TextToSpeechStreamingSocketClientResponse, raw_message)  # type: ignore
+                self._emit(EventType.MESSAGE, parsed)
+        except websockets.WebSocketException as exc:
+            self._emit(EventType.ERROR, exc)
+        finally:
+            self._emit(EventType.CLOSE, None)
+
+    async def send_initialize_connection(self, message: InitializeConnection) -> None:
+        """
+        Send a message to the websocket connection.
+        The message will be sent as a InitializeConnection.
+        """
+        await self._send_model(message)
+
+    async def send_send_text(self, message: SendText) -> None:
+        """
+        Send a message to the websocket connection.
+        The message will be sent as a SendText.
+        """
+        await self._send_model(message)
+
+    async def send_close_connection(self, message: CloseConnection) -> None:
+        """
+        Send a message to the websocket connection.
+        The message will be sent as a CloseConnection.
+        """
+        await self._send_model(message)
+
+    async def send_ping_signal(self, message: PingSignal) -> None:
+        """
+        Send a message to the websocket connection.
+        The message will be sent as a PingSignal.
+        """
+        await self._send_model(message)
+
+    async def recv(self) -> TextToSpeechStreamingSocketClientResponse:
+        """
+        Receive a message from the websocket connection.
+        """
+        data = await self._websocket.recv()
+        return parse_obj_as(TextToSpeechStreamingSocketClientResponse, data)  # type: ignore
+
+    async def _send(self, data: typing.Any) -> None:
+        """
+        Send a message to the websocket connection.
+        """
+        if isinstance(data, dict):
+            data = json.dumps(data)
+        await self._websocket.send(data)
+
+    async def _send_model(self, data: typing.Any) -> None:
+        """
+        Send a Pydantic model to the websocket connection.
+        """
+        await self._send(data.dict())
+
+
+class TextToSpeechStreamingSocketClient(EventEmitterMixin):
+    def __init__(self, *, websocket: websockets_sync_connection.Connection):
+        super().__init__()
+        self._websocket = websocket
+
+    def __iter__(self):
+        for message in self._websocket:
+            yield parse_obj_as(TextToSpeechStreamingSocketClientResponse, message)  # type: ignore
+
+    def start_listening(self):
+        """
+        Start listening for messages on the websocket connection.
+
+        Emits events in the following order:
+        - EventType.OPEN when connection is established
+        - EventType.MESSAGE for each message received
+        - EventType.ERROR if an error occurs
+        - EventType.CLOSE when connection is closed
+        """
+        self._emit(EventType.OPEN, None)
+        try:
+            for raw_message in self._websocket:
+                parsed = parse_obj_as(TextToSpeechStreamingSocketClientResponse, raw_message)  # type: ignore
+                self._emit(EventType.MESSAGE, parsed)
+        except websockets.WebSocketException as exc:
+            self._emit(EventType.ERROR, exc)
+        finally:
+            self._emit(EventType.CLOSE, None)
+
+    def send_initialize_connection(self, message: InitializeConnection) -> None:
+        """
+        Send a message to the websocket connection.
+        The message will be sent as a InitializeConnection.
+        """
+        self._send_model(message)
+
+    def send_send_text(self, message: SendText) -> None:
+        """
+        Send a message to the websocket connection.
+        The message will be sent as a SendText.
+        """
+        self._send_model(message)
+
+    def send_close_connection(self, message: CloseConnection) -> None:
+        """
+        Send a message to the websocket connection.
+        The message will be sent as a CloseConnection.
+        """
+        self._send_model(message)
+
+    def send_ping_signal(self, message: PingSignal) -> None:
+        """
+        Send a message to the websocket connection.
+        The message will be sent as a PingSignal.
+        """
+        self._send_model(message)
+
+    def recv(self) -> TextToSpeechStreamingSocketClientResponse:
+        """
+        Receive a message from the websocket connection.
+        """
+        data = self._websocket.recv()
+        return parse_obj_as(TextToSpeechStreamingSocketClientResponse, data)  # type: ignore
+
+    def _send(self, data: typing.Any) -> None:
+        """
+        Send a message to the websocket connection.
+        """
+        if isinstance(data, dict):
+            data = json.dumps(data)
+        self._websocket.send(data)
+
+    def _send_model(self, data: typing.Any) -> None:
+        """
+        Send a Pydantic model to the websocket connection.
+        """
+        self._send(data.dict())

sarvamai/types/__init__.py

@@ -4,6 +4,8 @@
 
 from .audio_data import AudioData
 from .audio_message import AudioMessage
+from .audio_output import AudioOutput
+from .audio_output_data import AudioOutputData
 from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessage
 from .chat_completion_request_message import (
     ChatCompletionRequestMessage,
@@ -15,6 +17,7 @@ from .chat_completion_request_system_message import ChatCompletionRequestSystemM
 from .chat_completion_request_user_message import ChatCompletionRequestUserMessage
 from .chat_completion_response_message import ChatCompletionResponseMessage
 from .choice import Choice
+from .close_connection import CloseConnection
 from .completion_usage import CompletionUsage
 from .config_message import ConfigMessage
 from .create_chat_completion_response import CreateChatCompletionResponse
@@ -24,15 +27,26 @@ from .error_code import ErrorCode
 from .error_data import ErrorData
 from .error_details import ErrorDetails
 from .error_message import ErrorMessage
+from .error_response import ErrorResponse
+from .error_response_data import ErrorResponseData
 from .events_data import EventsData
 from .finish_reason import FinishReason
 from .format import Format
+from .initialize_connection import InitializeConnection
+from .initialize_connection_data import InitializeConnectionData
+from .initialize_connection_data_model import InitializeConnectionDataModel
+from .initialize_connection_data_output_audio_bitrate import InitializeConnectionDataOutputAudioBitrate
+from .initialize_connection_data_speaker import InitializeConnectionDataSpeaker
+from .initialize_connection_data_target_language_code import InitializeConnectionDataTargetLanguageCode
 from .language_identification_response import LanguageIdentificationResponse
 from .numerals_format import NumeralsFormat
+from .ping_signal import PingSignal
 from .reasoning_effort import ReasoningEffort
 from .response_type import ResponseType
 from .role import Role
 from .sarvam_model_ids import SarvamModelIds
+from .send_text import SendText
+from .send_text_data import SendTextData
 from .speech_sample_rate import SpeechSampleRate
 from .speech_to_text_language import SpeechToTextLanguage
 from .speech_to_text_model import SpeechToTextModel
@@ -68,6 +82,8 @@ from .transliteration_response import TransliterationResponse
 __all__ = [
     "AudioData",
     "AudioMessage",
+    "AudioOutput",
+    "AudioOutputData",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestMessage",
     "ChatCompletionRequestMessage_Assistant",
@@ -77,6 +93,7 @@ __all__ = [
     "ChatCompletionRequestUserMessage",
     "ChatCompletionResponseMessage",
     "Choice",
+    "CloseConnection",
     "CompletionUsage",
     "ConfigMessage",
     "CreateChatCompletionResponse",
@@ -86,15 +103,26 @@ __all__ = [
     "ErrorData",
     "ErrorDetails",
     "ErrorMessage",
+    "ErrorResponse",
+    "ErrorResponseData",
     "EventsData",
     "FinishReason",
     "Format",
+    "InitializeConnection",
+    "InitializeConnectionData",
+    "InitializeConnectionDataModel",
+    "InitializeConnectionDataOutputAudioBitrate",
+    "InitializeConnectionDataSpeaker",
+    "InitializeConnectionDataTargetLanguageCode",
     "LanguageIdentificationResponse",
     "NumeralsFormat",
+    "PingSignal",
     "ReasoningEffort",
     "ResponseType",
     "Role",
     "SarvamModelIds",
+    "SendText",
+    "SendTextData",
     "SpeechSampleRate",
     "SpeechToTextLanguage",
     "SpeechToTextModel",

sarvamai/types/audio_output.py

@@ -0,0 +1,21 @@
+# 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 .audio_output_data import AudioOutputData
+
+
+class AudioOutput(UniversalBaseModel):
+    type: typing.Literal["audio"] = "audio"
+    data: AudioOutputData
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/audio_output_data.py

@@ -0,0 +1,27 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class AudioOutputData(UniversalBaseModel):
+    content_type: str = pydantic.Field()
+    """
+    MIME type of the audio content (e.g., 'audio/mp3', 'audio/wav')
+    """
+
+    audio: str = pydantic.Field()
+    """
+    Base64-encoded audio data ready for playback or download
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/close_connection.py

@@ -0,0 +1,19 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class CloseConnection(UniversalBaseModel):
+    type: typing.Literal["flush"] = "flush"
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/error_response.py

@@ -0,0 +1,21 @@
+# 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 .error_response_data import ErrorResponseData
+
+
+class ErrorResponse(UniversalBaseModel):
+    type: typing.Literal["error"] = "error"
+    data: ErrorResponseData
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/error_response_data.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class ErrorResponseData(UniversalBaseModel):
+    message: str
+    code: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Optional error code for programmatic error handling
+    """
+
+    details: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = pydantic.Field(default=None)
+    """
+    Additional error details and context information
+    """
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/initialize_connection.py

@@ -0,0 +1,21 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+from .initialize_connection_data import InitializeConnectionData
+
+
+class InitializeConnection(UniversalBaseModel):
+    type: typing.Literal["config"] = "config"
+    data: InitializeConnectionData
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/initialize_connection_data.py

@@ -0,0 +1,34 @@
+# 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_model import InitializeConnectionDataModel
+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
+    model: InitializeConnectionDataModel
+    output_audio_codec: typing.Optional[typing.Literal["mp3"]] = None
+    output_audio_bitrate: typing.Optional[InitializeConnectionDataOutputAudioBitrate] = None
+    min_buffer_size: typing.Optional[int] = None
+    max_chunk_length: typing.Optional[int] = None
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/initialize_connection_data_model.py

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

sarvamai/types/initialize_connection_data_output_audio_bitrate.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+InitializeConnectionDataOutputAudioBitrate = typing.Union[
+    typing.Literal["32k", "64k", "96k", "128k", "192k"], typing.Any
+]

sarvamai/types/initialize_connection_data_speaker.py

@@ -0,0 +1,28 @@
+# 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,
+]

sarvamai/types/initialize_connection_data_target_language_code.py

@@ -0,0 +1,8 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+InitializeConnectionDataTargetLanguageCode = typing.Union[
+    typing.Literal["bn-IN", "en-IN", "gu-IN", "hi-IN", "kn-IN", "ml-IN", "mr-IN", "od-IN", "pa-IN", "ta-IN", "te-IN"],
+    typing.Any,
+]

sarvamai/types/ping_signal.py

@@ -0,0 +1,19 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class PingSignal(UniversalBaseModel):
+    type: typing.Literal["ping"] = "ping"
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/send_text.py

@@ -0,0 +1,21 @@
+# 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 .send_text_data import SendTextData
+
+
+class SendText(UniversalBaseModel):
+    type: typing.Literal["text"] = "text"
+    data: SendTextData
+
+    if IS_PYDANTIC_V2:
+        model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
+    else:
+
+        class Config:
+            frozen = True
+            smart_union = True
+            extra = pydantic.Extra.allow

sarvamai/types/send_text_data.py

@@ -0,0 +1,19 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import pydantic
+from ..core.pydantic_utilities import IS_PYDANTIC_V2, UniversalBaseModel
+
+
+class SendTextData(UniversalBaseModel):
+    text: str
+
+    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-0.1.7.dist-info → sarvamai-0.1.8a0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.7
+Version: 0.1.8a0
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers
@@ -34,7 +34,7 @@ The Sarvam Python library provides convenient access to the Sarvam API from Pyth
 
 ## Documentation
 
-API reference documentation is available [here](https://www.sarvam.ai/).
+API reference documentation is available [here](https://docs.sarvam.ai/api-reference-docs/speech-to-text/).
 
 ## Installation