sarvamai 0.1.8rc3__py3-none-any.whl → 0.1.8rc4__py3-none-any.whl

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/0.1.8rc3",
+            "User-Agent": "sarvamai/0.1.8rc4",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.8rc3",
+            "X-Fern-SDK-Version": "0.1.8rc4",
         }
         headers["api-subscription-key"] = self.api_subscription_key
         return headers

sarvamai/text_to_speech_streaming/socket_client.py

@@ -11,8 +11,10 @@ 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.initialize_connection_data import InitializeConnectionData
 from ..types.ping_signal import PingSignal
 from ..types.send_text import SendText
+from ..types.send_text_data import SendTextData
 
 TextToSpeechStreamingSocketClientResponse = typing.Union[AudioOutput, ErrorResponse]
 
@@ -24,6 +26,7 @@ class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
 
     async def __aiter__(self):
         async for message in self._websocket:
+            message = json.loads(message) if isinstance(message, str) else message
             yield parse_obj_as(TextToSpeechStreamingSocketClientResponse, message)  # type: ignore
 
     async def start_listening(self):
@@ -39,6 +42,11 @@ class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
         self._emit(EventType.OPEN, None)
         try:
             async for raw_message in self._websocket:
+                raw_message = (
+                    json.loads(raw_message)
+                    if isinstance(raw_message, str)
+                    else raw_message
+                )
                 parsed = parse_obj_as(TextToSpeechStreamingSocketClientResponse, raw_message)  # type: ignore
                 self._emit(EventType.MESSAGE, parsed)
         except websockets.WebSocketException as exc:
@@ -46,32 +54,47 @@ class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
         finally:
             self._emit(EventType.CLOSE, None)
 
-    async def send_initialize_connection(self, message: InitializeConnection) -> None:
+    async def initialize_connection(
+        self,
+        target_language_code: str,
+        speaker: str,
+    ) -> None:
         """
-        Send a message to the websocket connection.
-        The message will be sent as a InitializeConnection.
+        Initialize the TTS connection with configuration parameters.
+
+        :param target_language_code: Target language code (e.g., 'hi-IN')
+        :param speaker: Voice speaker name (e.g., 'meera', 'arvind')
         """
+        data = InitializeConnectionData(
+            target_language_code=target_language_code,
+            speaker=speaker,
+        )
+        message = InitializeConnection(data=data)
         await self._send_model(message)
 
-    async def send_send_text(self, message: SendText) -> None:
+    async def convert(self, text: str) -> None:
         """
-        Send a message to the websocket connection.
-        The message will be sent as a SendText.
+        Send text to be converted to speech.
+
+        :param text: Text to be synthesized (1-2500 characters)
         """
+        data = SendTextData(text=text)
+        message = SendText(data=data)
         await self._send_model(message)
 
-    async def send_close_connection(self, message: CloseConnection) -> None:
+    async def flush(self) -> None:
         """
-        Send a message to the websocket connection.
-        The message will be sent as a CloseConnection.
+        Signal to flush the buffer and finalize audio output.
+        This indicates the end of text input.
         """
+        message = CloseConnection()
         await self._send_model(message)
 
-    async def send_ping_signal(self, message: PingSignal) -> None:
+    async def ping(self) -> None:
         """
-        Send a message to the websocket connection.
-        The message will be sent as a PingSignal.
+        Send ping signal to keep the WebSocket connection alive.
         """
+        message = PingSignal()
         await self._send_model(message)
 
     async def recv(self) -> TextToSpeechStreamingSocketClientResponse:
@@ -79,6 +102,7 @@ class AsyncTextToSpeechStreamingSocketClient(EventEmitterMixin):
         Receive a message from the websocket connection.
         """
         data = await self._websocket.recv()
+        data = json.loads(data) if isinstance(data, str) else data
         return parse_obj_as(TextToSpeechStreamingSocketClientResponse, data)  # type: ignore
 
     async def _send(self, data: typing.Any) -> None:
@@ -103,6 +127,7 @@ class TextToSpeechStreamingSocketClient(EventEmitterMixin):
 
     def __iter__(self):
         for message in self._websocket:
+            message = json.loads(message) if isinstance(message, str) else message
             yield parse_obj_as(TextToSpeechStreamingSocketClientResponse, message)  # type: ignore
 
     def start_listening(self):
@@ -118,6 +143,11 @@ class TextToSpeechStreamingSocketClient(EventEmitterMixin):
         self._emit(EventType.OPEN, None)
         try:
             for raw_message in self._websocket:
+                raw_message = (
+                    json.loads(raw_message)
+                    if isinstance(raw_message, str)
+                    else raw_message
+                )
                 parsed = parse_obj_as(TextToSpeechStreamingSocketClientResponse, raw_message)  # type: ignore
                 self._emit(EventType.MESSAGE, parsed)
         except websockets.WebSocketException as exc:
@@ -125,32 +155,47 @@ class TextToSpeechStreamingSocketClient(EventEmitterMixin):
         finally:
             self._emit(EventType.CLOSE, None)
 
-    def send_initialize_connection(self, message: InitializeConnection) -> None:
+    def initialize_connection(
+        self,
+        target_language_code: str,
+        speaker: str,
+    ) -> None:
         """
-        Send a message to the websocket connection.
-        The message will be sent as a InitializeConnection.
+        Initialize the TTS connection with configuration parameters.
+
+        :param target_language_code: Target language code (e.g., 'hi-IN')
+        :param speaker: Voice speaker name (e.g., 'meera', 'arvind')
         """
+        data = InitializeConnectionData(
+            target_language_code=target_language_code,
+            speaker=speaker,
+        )
+        message = InitializeConnection(data=data)
         self._send_model(message)
 
-    def send_send_text(self, message: SendText) -> None:
+    def convert(self, text: str) -> None:
         """
-        Send a message to the websocket connection.
-        The message will be sent as a SendText.
+        Send text to be converted to speech.
+
+        :param text: Text to be synthesized (1-2500 characters)
         """
+        data = SendTextData(text=text)
+        message = SendText(data=data)
         self._send_model(message)
 
-    def send_close_connection(self, message: CloseConnection) -> None:
+    def flush(self) -> None:
         """
-        Send a message to the websocket connection.
-        The message will be sent as a CloseConnection.
+        Signal to flush the buffer and finalize audio output.
+        This indicates the end of text input.
         """
+        message = CloseConnection()
         self._send_model(message)
 
-    def send_ping_signal(self, message: PingSignal) -> None:
+    def ping(self) -> None:
         """
-        Send a message to the websocket connection.
-        The message will be sent as a PingSignal.
+        Send ping signal to keep the WebSocket connection alive.
         """
+        message = PingSignal()
         self._send_model(message)
 
     def recv(self) -> TextToSpeechStreamingSocketClientResponse:
@@ -158,6 +203,7 @@ class TextToSpeechStreamingSocketClient(EventEmitterMixin):
         Receive a message from the websocket connection.
         """
         data = self._websocket.recv()
+        data = json.loads(data) if isinstance(data, str) else data
         return parse_obj_as(TextToSpeechStreamingSocketClientResponse, data)  # type: ignore
 
     def _send(self, data: typing.Any) -> None:

{sarvamai-0.1.8rc3.dist-info → sarvamai-0.1.8rc4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.8rc3
+Version: 0.1.8rc4
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.8rc3.dist-info → sarvamai-0.1.8rc4.dist-info}/RECORD

@@ -5,7 +5,7 @@ sarvamai/chat/raw_client.py,sha256=A2kRuZcVWlJhyYCD7YKgqNkZEp3cYa1731KhRkhirU0,1
 sarvamai/client.py,sha256=aI1sw5LVGMjgukgZLDlUmA17ecK1yGsQxH-W_JiCrco,7177
 sarvamai/core/__init__.py,sha256=YE2CtXeASe1RAbaI39twKWYKCuT4tW5is9HWHhJjR_g,1653
 sarvamai/core/api_error.py,sha256=44vPoTyWN59gonCIZMdzw7M1uspygiLnr3GNFOoVL2Q,614
-sarvamai/core/client_wrapper.py,sha256=4X5OQTI0A__Cf2SlaCAN5xRAzRmOAjEDwg09z9V80gU,2080
+sarvamai/core/client_wrapper.py,sha256=n37XVBNUAT0tusKUk_VaNpSUmSysyGgwv6sSK9hXikI,2080
 sarvamai/core/datetime_utils.py,sha256=nBys2IsYrhPdszxGKCNRPSOCwa-5DWOHG95FB8G9PKo,1047
 sarvamai/core/events.py,sha256=j7VWXgMpOsjCXdzY22wIhI7Q-v5InZ4WchRzA88x_Sk,856
 sarvamai/core/file.py,sha256=d4NNbX8XvXP32z8KpK2Xovv33nFfruIrpz0QWxlgpZk,2663
@@ -100,7 +100,7 @@ sarvamai/text_to_speech/raw_client.py,sha256=3Zu6HN_FOY683Vm-EN-OL7YAbLsftjJlFm5
 sarvamai/text_to_speech_streaming/__init__.py,sha256=AyHwl9te1mTfiz6IkMU20quN-0RP5njbchknXCz-oK8,173
 sarvamai/text_to_speech_streaming/client.py,sha256=sEC5mVNALldkZri3gHVxHcJCI9TmVwF1vPTL8vfatbY,6161
 sarvamai/text_to_speech_streaming/raw_client.py,sha256=DXsU8Rq27yZGINkRmyeyqPWLlSAGsR1RTJWJH81FlTI,5342
-sarvamai/text_to_speech_streaming/socket_client.py,sha256=fKGmayvIj3qnmnuDlz_QrPDN14CvrtgkGVh0k27yI68,6313
+sarvamai/text_to_speech_streaming/socket_client.py,sha256=rvlRi2wmyUzWdh2jBqrveD6Ck9dXA-IiCAf0ehZIREE,7799
 sarvamai/text_to_speech_streaming/types/__init__.py,sha256=DUsvIGTtST5N1v3Hnodq5aNKfPcTBlod28DSypc8NzA,198
 sarvamai/text_to_speech_streaming/types/text_to_speech_streaming_model.py,sha256=1uOMrJIaAxi_XzwCYmnG5XA-il66cq9uC4ZuiI7HCHo,176
 sarvamai/types/__init__.py,sha256=oCDY6p7Hfd26vLAvluWMrP-qpUd-BJdlVE-KipWXqR8,6332
@@ -175,6 +175,6 @@ sarvamai/types/transliterate_mode.py,sha256=1jSEMlGcoLkWuk12TgoOpSgwifa4rThGKZ1h
 sarvamai/types/transliterate_source_language.py,sha256=bSY9wJszF0sg-Cgg6F-YcWC8ly1mIlj9rqa15-jBtx8,283
 sarvamai/types/transliteration_response.py,sha256=yt-lzTbDeJ_ZL4I8kQa6oESxA9ebeJJY7LfFHpdEsmM,815
 sarvamai/version.py,sha256=Qkp3Ee9YH-O9RTix90e0i7iNrFAGN-QDt2AFwGA4n8k,75
-sarvamai-0.1.8rc3.dist-info/METADATA,sha256=67z0IA-D0ClqEykj_oN9lC7zWXA484eqFN8xelZSXws,26760
-sarvamai-0.1.8rc3.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-sarvamai-0.1.8rc3.dist-info/RECORD,,
+sarvamai-0.1.8rc4.dist-info/METADATA,sha256=oq7Tpq7QybN8DkNwZe1pYJfxt1cuHCetcQxvCb1CO48,26760
+sarvamai-0.1.8rc4.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+sarvamai-0.1.8rc4.dist-info/RECORD,,