sarvamai 0.1.7__tar.gz → 0.1.8__tar.gz

{sarvamai-0.1.7 → sarvamai-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.7
+Version: 0.1.8
 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
 

{sarvamai-0.1.7 → sarvamai-0.1.8}/README.md

@@ -7,7 +7,7 @@ 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
 

{sarvamai-0.1.7 → sarvamai-0.1.8}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.7"
+version = "0.1.8"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.7 → sarvamai-0.1.8}/src/sarvamai/__init__.py

@@ -5,6 +5,8 @@
 from .types import (
     AudioData,
     AudioMessage,
+    AudioOutput,
+    AudioOutputData,
     ChatCompletionRequestAssistantMessage,
     ChatCompletionRequestMessage,
     ChatCompletionRequestMessage_Assistant,
@@ -16,6 +18,11 @@ from .types import (
     Choice,
     CompletionUsage,
     ConfigMessage,
+    ConfigureConnection,
+    ConfigureConnectionData,
+    ConfigureConnectionDataOutputAudioBitrate,
+    ConfigureConnectionDataSpeaker,
+    ConfigureConnectionDataTargetLanguageCode,
     CreateChatCompletionResponse,
     DiarizedEntry,
     DiarizedTranscript,
@@ -23,15 +30,21 @@ from .types import (
     ErrorData,
     ErrorDetails,
     ErrorMessage,
+    ErrorResponse,
+    ErrorResponseData,
     EventsData,
     FinishReason,
+    FlushSignal,
     Format,
     LanguageIdentificationResponse,
     NumeralsFormat,
+    PingSignal,
     ReasoningEffort,
     ResponseType,
     Role,
     SarvamModelIds,
+    SendText,
+    SendTextData,
     SpeechSampleRate,
     SpeechToTextLanguage,
     SpeechToTextModel,
@@ -72,12 +85,22 @@ from .errors import (
     TooManyRequestsError,
     UnprocessableEntityError,
 )
-from . import chat, speech_to_text, speech_to_text_streaming, speech_to_text_translate_streaming, text, text_to_speech
+from . import (
+    chat,
+    speech_to_text,
+    speech_to_text_streaming,
+    speech_to_text_translate_streaming,
+    text,
+    text_to_speech,
+    text_to_speech_streaming,
+)
 from .client import AsyncSarvamAI, SarvamAI
 from .environment import SarvamAIEnvironment
 from .requests import (
     AudioDataParams,
     AudioMessageParams,
+    AudioOutputDataParams,
+    AudioOutputParams,
     ChatCompletionRequestAssistantMessageParams,
     ChatCompletionRequestMessageParams,
     ChatCompletionRequestMessage_AssistantParams,
@@ -89,14 +112,22 @@ from .requests import (
     ChoiceParams,
     CompletionUsageParams,
     ConfigMessageParams,
+    ConfigureConnectionDataParams,
+    ConfigureConnectionParams,
     CreateChatCompletionResponseParams,
     DiarizedEntryParams,
     DiarizedTranscriptParams,
     ErrorDataParams,
     ErrorDetailsParams,
     ErrorMessageParams,
+    ErrorResponseDataParams,
+    ErrorResponseParams,
     EventsDataParams,
+    FlushSignalParams,
     LanguageIdentificationResponseParams,
+    PingSignalParams,
+    SendTextDataParams,
+    SendTextParams,
     SpeechToTextResponseDataParams,
     SpeechToTextResponseParams,
     SpeechToTextStreamingResponseParams,
@@ -131,6 +162,10 @@ __all__ = [
     "AudioDataParams",
     "AudioMessage",
     "AudioMessageParams",
+    "AudioOutput",
+    "AudioOutputData",
+    "AudioOutputDataParams",
+    "AudioOutputParams",
     "BadRequestError",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestAssistantMessageParams",
@@ -154,6 +189,13 @@ __all__ = [
     "CompletionUsageParams",
     "ConfigMessage",
     "ConfigMessageParams",
+    "ConfigureConnection",
+    "ConfigureConnectionData",
+    "ConfigureConnectionDataOutputAudioBitrate",
+    "ConfigureConnectionDataParams",
+    "ConfigureConnectionDataSpeaker",
+    "ConfigureConnectionDataTargetLanguageCode",
+    "ConfigureConnectionParams",
     "CreateChatCompletionResponse",
     "CreateChatCompletionResponseParams",
     "DiarizedEntry",
@@ -167,21 +209,33 @@ __all__ = [
     "ErrorDetailsParams",
     "ErrorMessage",
     "ErrorMessageParams",
+    "ErrorResponse",
+    "ErrorResponseData",
+    "ErrorResponseDataParams",
+    "ErrorResponseParams",
     "EventsData",
     "EventsDataParams",
     "FinishReason",
+    "FlushSignal",
+    "FlushSignalParams",
     "ForbiddenError",
     "Format",
     "InternalServerError",
     "LanguageIdentificationResponse",
     "LanguageIdentificationResponseParams",
     "NumeralsFormat",
+    "PingSignal",
+    "PingSignalParams",
     "ReasoningEffort",
     "ResponseType",
     "Role",
     "SarvamAI",
     "SarvamAIEnvironment",
     "SarvamModelIds",
+    "SendText",
+    "SendTextData",
+    "SendTextDataParams",
+    "SendTextParams",
     "ServiceUnavailableError",
     "SpeechSampleRate",
     "SpeechToTextLanguage",
@@ -244,4 +298,5 @@ __all__ = [
     "speech_to_text_translate_streaming",
     "text",
     "text_to_speech",
+    "text_to_speech_streaming",
 ]

{sarvamai-0.1.7 → sarvamai-0.1.8}/src/sarvamai/client.py

@@ -16,6 +16,7 @@ from .speech_to_text_translate_streaming.client import (
 )
 from .text.client import AsyncTextClient, TextClient
 from .text_to_speech.client import AsyncTextToSpeechClient, TextToSpeechClient
+from .text_to_speech_streaming.client import AsyncTextToSpeechStreamingClient, TextToSpeechStreamingClient
 
 
 class SarvamAI:
@@ -86,6 +87,7 @@ class SarvamAI:
         self.speech_to_text_translate_streaming = SpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper
         )
+        self.text_to_speech_streaming = TextToSpeechStreamingClient(client_wrapper=self._client_wrapper)
 
 
 class AsyncSarvamAI:
@@ -156,3 +158,4 @@ class AsyncSarvamAI:
         self.speech_to_text_translate_streaming = AsyncSpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper
         )
+        self.text_to_speech_streaming = AsyncTextToSpeechStreamingClient(client_wrapper=self._client_wrapper)

{sarvamai-0.1.7 → sarvamai-0.1.8}/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/0.1.7",
+            "User-Agent": "sarvamai/0.1.8",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.7",
+            "X-Fern-SDK-Version": "0.1.8",
         }
         headers["api-subscription-key"] = self.api_subscription_key
         return headers

{sarvamai-0.1.7 → sarvamai-0.1.8}/src/sarvamai/requests/__init__.py

@@ -4,6 +4,8 @@
 
 from .audio_data import AudioDataParams
 from .audio_message import AudioMessageParams
+from .audio_output import AudioOutputParams
+from .audio_output_data import AudioOutputDataParams
 from .chat_completion_request_assistant_message import ChatCompletionRequestAssistantMessageParams
 from .chat_completion_request_message import (
     ChatCompletionRequestMessageParams,
@@ -17,14 +19,22 @@ from .chat_completion_response_message import ChatCompletionResponseMessageParam
 from .choice import ChoiceParams
 from .completion_usage import CompletionUsageParams
 from .config_message import ConfigMessageParams
+from .configure_connection import ConfigureConnectionParams
+from .configure_connection_data import ConfigureConnectionDataParams
 from .create_chat_completion_response import CreateChatCompletionResponseParams
 from .diarized_entry import DiarizedEntryParams
 from .diarized_transcript import DiarizedTranscriptParams
 from .error_data import ErrorDataParams
 from .error_details import ErrorDetailsParams
 from .error_message import ErrorMessageParams
+from .error_response import ErrorResponseParams
+from .error_response_data import ErrorResponseDataParams
 from .events_data import EventsDataParams
+from .flush_signal import FlushSignalParams
 from .language_identification_response import LanguageIdentificationResponseParams
+from .ping_signal import PingSignalParams
+from .send_text import SendTextParams
+from .send_text_data import SendTextDataParams
 from .speech_to_text_response import SpeechToTextResponseParams
 from .speech_to_text_response_data import SpeechToTextResponseDataParams
 from .speech_to_text_streaming_response import SpeechToTextStreamingResponseParams
@@ -43,6 +53,8 @@ from .transliteration_response import TransliterationResponseParams
 __all__ = [
     "AudioDataParams",
     "AudioMessageParams",
+    "AudioOutputDataParams",
+    "AudioOutputParams",
     "ChatCompletionRequestAssistantMessageParams",
     "ChatCompletionRequestMessageParams",
     "ChatCompletionRequestMessage_AssistantParams",
@@ -54,14 +66,22 @@ __all__ = [
     "ChoiceParams",
     "CompletionUsageParams",
     "ConfigMessageParams",
+    "ConfigureConnectionDataParams",
+    "ConfigureConnectionParams",
     "CreateChatCompletionResponseParams",
     "DiarizedEntryParams",
     "DiarizedTranscriptParams",
     "ErrorDataParams",
     "ErrorDetailsParams",
     "ErrorMessageParams",
+    "ErrorResponseDataParams",
+    "ErrorResponseParams",
     "EventsDataParams",
+    "FlushSignalParams",
     "LanguageIdentificationResponseParams",
+    "PingSignalParams",
+    "SendTextDataParams",
+    "SendTextParams",
     "SpeechToTextResponseDataParams",
     "SpeechToTextResponseParams",
     "SpeechToTextStreamingResponseParams",

sarvamai-0.1.8/src/sarvamai/requests/audio_output.py

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

sarvamai-0.1.8/src/sarvamai/requests/audio_output_data.py

@@ -0,0 +1,15 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class AudioOutputDataParams(typing_extensions.TypedDict):
+    content_type: str
+    """
+    MIME type of the audio content (e.g., 'audio/mp3', 'audio/wav')
+    """
+
+    audio: str
+    """
+    Base64-encoded audio data ready for playback or download
+    """

sarvamai-0.1.8/src/sarvamai/requests/configure_connection.py

@@ -0,0 +1,18 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+from .configure_connection_data import ConfigureConnectionDataParams
+
+
+class ConfigureConnectionParams(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: ConfigureConnectionDataParams

sarvamai-0.1.8/src/sarvamai/requests/configure_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.configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
+from ..types.configure_connection_data_speaker import ConfigureConnectionDataSpeaker
+from ..types.configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
+
+
+class ConfigureConnectionDataParams(typing_extensions.TypedDict):
+    target_language_code: ConfigureConnectionDataTargetLanguageCode
+    """
+    The language of the text is BCP-47 format
+    """
+
+    speaker: ConfigureConnectionDataSpeaker
+    """
+    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[ConfigureConnectionDataOutputAudioBitrate]
+    """
+    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-0.1.8/src/sarvamai/requests/error_response.py

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

sarvamai-0.1.8/src/sarvamai/requests/error_response_data.py

@@ -0,0 +1,18 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+import typing_extensions
+
+
+class ErrorResponseDataParams(typing_extensions.TypedDict):
+    message: str
+    code: typing_extensions.NotRequired[int]
+    """
+    Optional error code for programmatic error handling
+    """
+
+    details: typing_extensions.NotRequired[typing.Dict[str, typing.Optional[typing.Any]]]
+    """
+    Additional error details and context information
+    """

sarvamai-0.1.8/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-0.1.8/src/sarvamai/requests/ping_signal.py

@@ -0,0 +1,14 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+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-0.1.8/src/sarvamai/requests/send_text.py

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

sarvamai-0.1.8/src/sarvamai/requests/send_text_data.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+
+
+class SendTextDataParams(typing_extensions.TypedDict):
+    text: str

sarvamai-0.1.8/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-0.1.8/src/sarvamai/text_to_speech_streaming/client.py

@@ -0,0 +1,153 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+from contextlib import asynccontextmanager, contextmanager
+
+import httpx
+import websockets
+import websockets.sync.client as websockets_sync_client
+from ..core.api_error import ApiError
+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
+
+
+class TextToSpeechStreamingClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._raw_client = RawTextToSpeechStreamingClient(client_wrapper=client_wrapper)
+
+    @property
+    def with_raw_response(self) -> RawTextToSpeechStreamingClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        RawTextToSpeechStreamingClient
+        """
+        return self._raw_client
+
+    @contextmanager
+    def connect(
+        self,
+        *,
+        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
+        api_subscription_key: typing.Optional[str] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[TextToSpeechStreamingSocketClient]:
+        """
+        Bidirectional WebSocket channel for real-time TTS synthesis.
+        Supports streaming, flushing, config updates, and audio playback.
+
+        Parameters
+        ----------
+        model : typing.Optional[typing.Literal["bulbul:v2"]]
+            Text to speech model to use
+
+        api_subscription_key : typing.Optional[str]
+            API subscription key for authentication
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        TextToSpeechStreamingSocketClient
+        """
+        ws_url = self._raw_client._client_wrapper.get_environment().production + "/text-to-speech/ws"
+        query_params = httpx.QueryParams()
+        if model is not None:
+            query_params = query_params.add("model", model)
+        ws_url = ws_url + f"?{query_params}"
+        headers = self._raw_client._client_wrapper.get_headers()
+        if api_subscription_key is not None:
+            headers["Api-Subscription-Key"] = str(api_subscription_key)
+        if request_options and "additional_headers" in request_options:
+            headers.update(request_options["additional_headers"])
+        try:
+            with websockets_sync_client.connect(ws_url, additional_headers=headers) as protocol:
+                yield TextToSpeechStreamingSocketClient(websocket=protocol)
+        except websockets.exceptions.InvalidStatusCode as exc:
+            status_code: int = exc.status_code
+            if status_code == 401:
+                raise ApiError(
+                    status_code=status_code,
+                    headers=dict(headers),
+                    body="Websocket initialized with invalid credentials.",
+                )
+            raise ApiError(
+                status_code=status_code,
+                headers=dict(headers),
+                body="Unexpected error when initializing websocket connection.",
+            )
+
+
+class AsyncTextToSpeechStreamingClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._raw_client = AsyncRawTextToSpeechStreamingClient(client_wrapper=client_wrapper)
+
+    @property
+    def with_raw_response(self) -> AsyncRawTextToSpeechStreamingClient:
+        """
+        Retrieves a raw implementation of this client that returns raw responses.
+
+        Returns
+        -------
+        AsyncRawTextToSpeechStreamingClient
+        """
+        return self._raw_client
+
+    @asynccontextmanager
+    async def connect(
+        self,
+        *,
+        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
+        api_subscription_key: typing.Optional[str] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[AsyncTextToSpeechStreamingSocketClient]:
+        """
+        Bidirectional WebSocket channel for real-time TTS synthesis.
+        Supports streaming, flushing, config updates, and audio playback.
+
+        Parameters
+        ----------
+        model : typing.Optional[typing.Literal["bulbul:v2"]]
+            Text to speech model to use
+
+        api_subscription_key : typing.Optional[str]
+            API subscription key for authentication
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncTextToSpeechStreamingSocketClient
+        """
+        ws_url = self._raw_client._client_wrapper.get_environment().production + "/text-to-speech/ws"
+        query_params = httpx.QueryParams()
+        if model is not None:
+            query_params = query_params.add("model", model)
+        ws_url = ws_url + f"?{query_params}"
+        headers = self._raw_client._client_wrapper.get_headers()
+        if api_subscription_key is not None:
+            headers["Api-Subscription-Key"] = str(api_subscription_key)
+        if request_options and "additional_headers" in request_options:
+            headers.update(request_options["additional_headers"])
+        try:
+            async with websockets.connect(ws_url, extra_headers=headers) as protocol:
+                yield AsyncTextToSpeechStreamingSocketClient(websocket=protocol)
+        except websockets.exceptions.InvalidStatusCode as exc:
+            status_code: int = exc.status_code
+            if status_code == 401:
+                raise ApiError(
+                    status_code=status_code,
+                    headers=dict(headers),
+                    body="Websocket initialized with invalid credentials.",
+                )
+            raise ApiError(
+                status_code=status_code,
+                headers=dict(headers),
+                body="Unexpected error when initializing websocket connection.",
+            )