sarvamai 0.1.11a2__tar.gz → 0.1.11a4__tar.gz

{sarvamai-0.1.11a2 → sarvamai-0.1.11a4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.11a2
+Version: 0.1.11a4
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.11a2 → sarvamai-0.1.11a4}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.11a2"
+version = "0.1.11a4"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.11a2 → sarvamai-0.1.11a4}/src/sarvamai/__init__.py

@@ -62,6 +62,7 @@ from .types import (
     SpeechToTextResponseData,
     SpeechToTextStreamingResponse,
     SpeechToTextTranscriptionData,
+    SpeechToTextTranslateJobParameters,
     SpeechToTextTranslateLanguage,
     SpeechToTextTranslateModel,
     SpeechToTextTranslateResponse,
@@ -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,
@@ -298,6 +301,8 @@ __all__ = [
     "SpeechToTextStreamingVadSignals",
     "SpeechToTextTranscriptionData",
     "SpeechToTextTranscriptionDataParams",
+    "SpeechToTextTranslateJobParameters",
+    "SpeechToTextTranslateJobParametersParams",
     "SpeechToTextTranslateLanguage",
     "SpeechToTextTranslateModel",
     "SpeechToTextTranslateResponse",
@@ -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-0.1.11a2 → sarvamai-0.1.11a4}/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-0.1.11a2 → sarvamai-0.1.11a4}/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/0.1.11a2",
+            "User-Agent": "sarvamai/0.1.11a4",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.11a2",
+            "X-Fern-SDK-Version": "0.1.11a4",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

{sarvamai-0.1.11a2 → sarvamai-0.1.11a4}/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-0.1.11a4/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.
+    """

{sarvamai-0.1.11a2 → sarvamai-0.1.11a4}/src/sarvamai/speech_to_text_job/client.py

@@ -238,6 +238,25 @@ class SpeechToTextJobClient:
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextJob:
+        """
+        Create a new Speech-to-Text bulk job.
+
+        Parameters
+        ----------
+        job_parameters : SpeechToTextJobParametersParams
+            The parameters required to configure the speech-to-text job.
+
+        callback : typing.Optional[BulkJobCallbackParams], default=OMIT
+            Optional callback configuration to receive job completion events.
+
+        request_options : typing.Optional[RequestOptions], default=None
+            Request-specific configuration.
+
+        Returns
+        -------
+        SpeechToTextJob
+            A handle to the newly created Speech-to-Text job.
+        """
         response = self.initialise(
             job_parameters=job_parameters,
             callback=callback,
@@ -247,7 +266,17 @@ class SpeechToTextJobClient:
 
     def get_job(self, job_id: str) -> SpeechToTextJob:
         """
-        Return a job handle for an existing Speech-to-Text job.
+        Get an existing Speech-to-Text job handle by job ID.
+
+        Parameters
+        ----------
+        job_id : str
+            The job ID of the previously created Speech-to-Text job.
+
+        Returns
+        -------
+        SpeechToTextJob
+            A job handle which can be used to check status or retrieve results.
         """
         return SpeechToTextJob(job_id=job_id, client=self)
 
@@ -515,6 +544,25 @@ class AsyncSpeechToTextJobClient:
         callback: typing.Optional[BulkJobCallbackParams] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> "AsyncSpeechToTextJob":
+        """
+        Create a new Speech-to-Text bulk job.
+
+        Parameters
+        ----------
+        job_parameters : SpeechToTextJobParametersParams
+            The parameters required to configure the speech-to-text  job.
+
+        callback : typing.Optional[BulkJobCallbackParams], default=OMIT
+            Optional callback configuration to receive job completion events.
+
+        request_options : typing.Optional[RequestOptions], default=None
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncSpeechToTextJob
+            A handle to the newly created job.
+        """
         response = await self.initialise(
             job_parameters=job_parameters,
             callback=callback,
@@ -524,6 +572,16 @@ class AsyncSpeechToTextJobClient:
 
     async def get_job(self, job_id: str) -> "AsyncSpeechToTextJob":
         """
-        Return a job handle for an existing Speech-to-Text job.
+        Get an existing Speech-to-Text job handle by job ID.
+
+        Parameters
+        ----------
+        job_id : str
+            The job ID of the previously created speech-to-text job.
+
+        Returns
+        -------
+        AsyncSpeechToTextJob
+            A job handle which can be used to check status or retrieve results.
         """
         return AsyncSpeechToTextJob(job_id=job_id, client=self)

{sarvamai-0.1.11a2 → sarvamai-0.1.11a4}/src/sarvamai/speech_to_text_job/job.py

@@ -1,4 +1,5 @@
 import asyncio
+import mimetypes
 import os
 import time
 import typing
@@ -66,12 +67,15 @@ class AsyncSpeechToTextJob:
                 file_name = os.path.basename(path)
                 url = upload_links.upload_urls[file_name].file_url
                 with open(path, "rb") as f:
+                    content_type, _ = mimetypes.guess_type(path)
+                    if content_type is None:
+                        content_type = "audio/wav"
                     response = await session.put(
                         url,
                         content=f.read(),
                         headers={
                             "x-ms-blob-type": "BlockBlob",
-                            "Content-Type": "audio/wav",
+                            "Content-Type": content_type,
                         },
                     )
                 if response.status_code != 201: