sarvamai 0.1.11a1__tar.gz → 0.1.11a3__tar.gz

{sarvamai-0.1.11a1 → sarvamai-0.1.11a3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.11a1
+Version: 0.1.11a3
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.11a1 → sarvamai-0.1.11a3}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.11a1"
+version = "0.1.11a3"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.11a1 → sarvamai-0.1.11a3}/src/sarvamai/__init__.py

@@ -3,7 +3,6 @@
 # isort: skip_file
 
 from .types import (
-    AudioCodec,
     AudioData,
     AudioMessage,
     AudioOutput,
@@ -25,6 +24,7 @@ from .types import (
     ConfigureConnection,
     ConfigureConnectionData,
     ConfigureConnectionDataOutputAudioBitrate,
+    ConfigureConnectionDataOutputAudioCodec,
     ConfigureConnectionDataSpeaker,
     ConfigureConnectionDataTargetLanguageCode,
     CreateChatCompletionResponse,
@@ -43,7 +43,6 @@ from .types import (
     FilesUploadResponse,
     FinishReason,
     FlushSignal,
-    Format,
     JobState,
     JobStatusV1,
     LanguageIdentificationResponse,
@@ -63,6 +62,7 @@ from .types import (
     SpeechToTextResponseData,
     SpeechToTextStreamingResponse,
     SpeechToTextTranscriptionData,
+    SpeechToTextTranslateJobParameters,
     SpeechToTextTranslateLanguage,
     SpeechToTextTranslateModel,
     SpeechToTextTranslateResponse,
@@ -77,6 +77,7 @@ from .types import (
     TaskState,
     TextToSpeechLanguage,
     TextToSpeechModel,
+    TextToSpeechOutputAudioCodec,
     TextToSpeechResponse,
     TextToSpeechSpeaker,
     TimestampsModel,
@@ -105,6 +106,7 @@ from . import (
     speech_to_text,
     speech_to_text_job,
     speech_to_text_streaming,
+    speech_to_text_translate_job,
     speech_to_text_translate_streaming,
     text,
     text_to_speech,
@@ -157,6 +159,7 @@ from .requests import (
     SpeechToTextResponseParams,
     SpeechToTextStreamingResponseParams,
     SpeechToTextTranscriptionDataParams,
+    SpeechToTextTranslateJobParametersParams,
     SpeechToTextTranslateResponseDataParams,
     SpeechToTextTranslateResponseParams,
     SpeechToTextTranslateStreamingResponseParams,
@@ -185,7 +188,6 @@ from .version import __version__
 
 __all__ = [
     "AsyncSarvamAI",
-    "AudioCodec",
     "AudioData",
     "AudioDataParams",
     "AudioMessage",
@@ -226,6 +228,7 @@ __all__ = [
     "ConfigureConnection",
     "ConfigureConnectionData",
     "ConfigureConnectionDataOutputAudioBitrate",
+    "ConfigureConnectionDataOutputAudioCodec",
     "ConfigureConnectionDataParams",
     "ConfigureConnectionDataSpeaker",
     "ConfigureConnectionDataTargetLanguageCode",
@@ -261,7 +264,6 @@ __all__ = [
     "FlushSignal",
     "FlushSignalParams",
     "ForbiddenError",
-    "Format",
     "InternalServerError",
     "JobState",
     "JobStatusV1",
@@ -299,6 +301,8 @@ __all__ = [
     "SpeechToTextStreamingVadSignals",
     "SpeechToTextTranscriptionData",
     "SpeechToTextTranscriptionDataParams",
+    "SpeechToTextTranslateJobParameters",
+    "SpeechToTextTranslateJobParametersParams",
     "SpeechToTextTranslateLanguage",
     "SpeechToTextTranslateModel",
     "SpeechToTextTranslateResponse",
@@ -323,6 +327,7 @@ __all__ = [
     "TaskState",
     "TextToSpeechLanguage",
     "TextToSpeechModel",
+    "TextToSpeechOutputAudioCodec",
     "TextToSpeechResponse",
     "TextToSpeechResponseParams",
     "TextToSpeechSpeaker",
@@ -349,6 +354,7 @@ __all__ = [
     "speech_to_text",
     "speech_to_text_job",
     "speech_to_text_streaming",
+    "speech_to_text_translate_job",
     "speech_to_text_translate_streaming",
     "text",
     "text_to_speech",

{sarvamai-0.1.11a1 → sarvamai-0.1.11a3}/src/sarvamai/client.py

@@ -11,6 +11,7 @@ from .environment import SarvamAIEnvironment
 from .speech_to_text.client import AsyncSpeechToTextClient, SpeechToTextClient
 from .speech_to_text_job.client import AsyncSpeechToTextJobClient, SpeechToTextJobClient
 from .speech_to_text_streaming.client import AsyncSpeechToTextStreamingClient, SpeechToTextStreamingClient
+from .speech_to_text_translate_job.client import AsyncSpeechToTextTranslateJobClient, SpeechToTextTranslateJobClient
 from .speech_to_text_translate_streaming.client import (
     AsyncSpeechToTextTranslateStreamingClient,
     SpeechToTextTranslateStreamingClient,
@@ -90,6 +91,7 @@ class SarvamAI:
         self.text_to_speech = TextToSpeechClient(client_wrapper=self._client_wrapper)
         self.chat = ChatClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_job = SpeechToTextJobClient(client_wrapper=self._client_wrapper)
+        self.speech_to_text_translate_job = SpeechToTextTranslateJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_streaming = SpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = SpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper
@@ -167,6 +169,7 @@ class AsyncSarvamAI:
         self.text_to_speech = AsyncTextToSpeechClient(client_wrapper=self._client_wrapper)
         self.chat = AsyncChatClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_job = AsyncSpeechToTextJobClient(client_wrapper=self._client_wrapper)
+        self.speech_to_text_translate_job = AsyncSpeechToTextTranslateJobClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_streaming = AsyncSpeechToTextStreamingClient(client_wrapper=self._client_wrapper)
         self.speech_to_text_translate_streaming = AsyncSpeechToTextTranslateStreamingClient(
             client_wrapper=self._client_wrapper

{sarvamai-0.1.11a1 → sarvamai-0.1.11a3}/src/sarvamai/core/client_wrapper.py

@@ -23,10 +23,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.11a1",
+            "User-Agent": "sarvamai/0.1.11a3",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.11a1",
+            "X-Fern-SDK-Version": "0.1.11a3",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

{sarvamai-0.1.11a1 → sarvamai-0.1.11a3}/src/sarvamai/requests/__init__.py

@@ -48,6 +48,7 @@ from .speech_to_text_response import SpeechToTextResponseParams
 from .speech_to_text_response_data import SpeechToTextResponseDataParams
 from .speech_to_text_streaming_response import SpeechToTextStreamingResponseParams
 from .speech_to_text_transcription_data import SpeechToTextTranscriptionDataParams
+from .speech_to_text_translate_job_parameters import SpeechToTextTranslateJobParametersParams
 from .speech_to_text_translate_response import SpeechToTextTranslateResponseParams
 from .speech_to_text_translate_response_data import SpeechToTextTranslateResponseDataParams
 from .speech_to_text_translate_streaming_response import SpeechToTextTranslateStreamingResponseParams
@@ -106,6 +107,7 @@ __all__ = [
     "SpeechToTextResponseParams",
     "SpeechToTextStreamingResponseParams",
     "SpeechToTextTranscriptionDataParams",
+    "SpeechToTextTranslateJobParametersParams",
     "SpeechToTextTranslateResponseDataParams",
     "SpeechToTextTranslateResponseParams",
     "SpeechToTextTranslateStreamingResponseParams",

{sarvamai-0.1.11a1 → sarvamai-0.1.11a3}/src/sarvamai/requests/configure_connection_data.py

@@ -1,9 +1,8 @@
 # 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_output_audio_codec import ConfigureConnectionDataOutputAudioCodec
 from ..types.configure_connection_data_speaker import ConfigureConnectionDataSpeaker
 from ..types.configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode
 
@@ -62,7 +61,7 @@ class ConfigureConnectionDataParams(typing_extensions.TypedDict):
     of mixed-language text. Default is false.
     """
 
-    output_audio_codec: typing_extensions.NotRequired[typing.Literal["mp3"]]
+    output_audio_codec: typing_extensions.NotRequired[ConfigureConnectionDataOutputAudioCodec]
     """
     Audio codec (currently supports MP3 only, optimized for real-time playback)
     """

sarvamai-0.1.11a3/src/sarvamai/requests/speech_to_text_translate_job_parameters.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing_extensions
+from ..types.speech_to_text_translate_model import SpeechToTextTranslateModel
+
+
+class SpeechToTextTranslateJobParametersParams(typing_extensions.TypedDict):
+    prompt: typing_extensions.NotRequired[str]
+    """
+    Prompt to assist the transcription
+    """
+
+    model: typing_extensions.NotRequired[SpeechToTextTranslateModel]
+    """
+    Model to be used for converting speech to text in target language
+    """
+
+    with_diarization: typing_extensions.NotRequired[bool]
+    """
+    Enables speaker diarization, which identifies and separates different speakers in the audio.
+     When set to true, the API will provide speaker-specific segments in the response.
+     Note: This parameter is currently in Beta mode.
+    """
+
+    num_speakers: typing_extensions.NotRequired[int]
+    """
+    Number of speakers to be detected in the audio. This is used when with_diarization is set to true.
+    """