sarvamai 0.1.13a2__py3-none-any.whl → 0.1.15__py3-none-any.whl

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/0.1.13a2",
+            "User-Agent": "sarvamai/0.1.15",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.13a2",
+            "X-Fern-SDK-Version": "0.1.15",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

sarvamai/speech_to_text/client.py

@@ -40,19 +40,19 @@ class SpeechToTextClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextResponse:
         """
-        ## Real-Time Speech to Text API
+        ## Speech to Text API
 
-        This API transcribes speech to text in multiple Indian languages and English. Supports real-time transcription for interactive applications.
+        This API transcribes speech to text in multiple Indian languages and English. Supports transcription for interactive applications.
 
         ### Available Options:
-        - **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
-        - **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt/stt-batch-api)
+        - **REST API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+        - **Batch API**: For longer audio files, [Follow This Documentation](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api)
           - Supports diarization (speaker identification)
 
         ### Note:
-        - Pricing differs for Real-Time and Batch APIs
+        - Pricing differs for REST and Batch APIs
         - Diarization is only available in Batch API with separate pricing
-        - Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+        - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information
 
         Parameters
         ----------
@@ -99,19 +99,19 @@ class SpeechToTextClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextTranslateResponse:
         """
-        ## Real-Time Speech to Text Translation API
+        ## Speech to Text Translation API
 
         This API automatically detects the input language, transcribes the speech, and translates the text to English.
 
         ### Available Options:
-        - **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
-        - **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt-translate/stt-translate-batch-api)
+        - **REST API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+        - **Batch API**: For longer audio files [Follow this documentation](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api)
           - Supports diarization (speaker identification)
 
         ### Note:
-        - Pricing differs for Real-Time and Batch APIs
+        - Pricing differs for REST and Batch APIs
         - Diarization is only available in Batch API with separate pricing
-        - Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+        - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information
 
         Parameters
         ----------
@@ -169,19 +169,19 @@ class AsyncSpeechToTextClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextResponse:
         """
-        ## Real-Time Speech to Text API
+        ## Speech to Text API
 
-        This API transcribes speech to text in multiple Indian languages and English. Supports real-time transcription for interactive applications.
+        This API transcribes speech to text in multiple Indian languages and English. Supports transcription for interactive applications.
 
         ### Available Options:
-        - **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
-        - **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt/stt-batch-api)
+        - **REST API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+        - **Batch API**: For longer audio files, [Follow This Documentation](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api)
           - Supports diarization (speaker identification)
 
         ### Note:
-        - Pricing differs for Real-Time and Batch APIs
+        - Pricing differs for REST and Batch APIs
         - Diarization is only available in Batch API with separate pricing
-        - Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+        - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information
 
         Parameters
         ----------
@@ -236,19 +236,19 @@ class AsyncSpeechToTextClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextTranslateResponse:
         """
-        ## Real-Time Speech to Text Translation API
+        ## Speech to Text Translation API
 
         This API automatically detects the input language, transcribes the speech, and translates the text to English.
 
         ### Available Options:
-        - **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
-        - **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt-translate/stt-translate-batch-api)
+        - **REST API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+        - **Batch API**: For longer audio files [Follow this documentation](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api)
           - Supports diarization (speaker identification)
 
         ### Note:
-        - Pricing differs for Real-Time and Batch APIs
+        - Pricing differs for REST and Batch APIs
         - Diarization is only available in Batch API with separate pricing
-        - Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+        - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information
 
         Parameters
         ----------

sarvamai/speech_to_text/raw_client.py

@@ -38,19 +38,19 @@ class RawSpeechToTextClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[SpeechToTextResponse]:
         """
-        ## Real-Time Speech to Text API
+        ## Speech to Text API
 
-        This API transcribes speech to text in multiple Indian languages and English. Supports real-time transcription for interactive applications.
+        This API transcribes speech to text in multiple Indian languages and English. Supports transcription for interactive applications.
 
         ### Available Options:
-        - **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
-        - **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt/stt-batch-api)
+        - **REST API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+        - **Batch API**: For longer audio files, [Follow This Documentation](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api)
           - Supports diarization (speaker identification)
 
         ### Note:
-        - Pricing differs for Real-Time and Batch APIs
+        - Pricing differs for REST and Batch APIs
         - Diarization is only available in Batch API with separate pricing
-        - Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+        - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information
 
         Parameters
         ----------
@@ -179,19 +179,19 @@ class RawSpeechToTextClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[SpeechToTextTranslateResponse]:
         """
-        ## Real-Time Speech to Text Translation API
+        ## Speech to Text Translation API
 
         This API automatically detects the input language, transcribes the speech, and translates the text to English.
 
         ### Available Options:
-        - **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
-        - **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt-translate/stt-translate-batch-api)
+        - **REST API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+        - **Batch API**: For longer audio files [Follow this documentation](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api)
           - Supports diarization (speaker identification)
 
         ### Note:
-        - Pricing differs for Real-Time and Batch APIs
+        - Pricing differs for REST and Batch APIs
         - Diarization is only available in Batch API with separate pricing
-        - Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+        - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information
 
         Parameters
         ----------
@@ -322,19 +322,19 @@ class AsyncRawSpeechToTextClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[SpeechToTextResponse]:
         """
-        ## Real-Time Speech to Text API
+        ## Speech to Text API
 
-        This API transcribes speech to text in multiple Indian languages and English. Supports real-time transcription for interactive applications.
+        This API transcribes speech to text in multiple Indian languages and English. Supports transcription for interactive applications.
 
         ### Available Options:
-        - **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
-        - **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt/stt-batch-api)
+        - **REST API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+        - **Batch API**: For longer audio files, [Follow This Documentation](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api)
           - Supports diarization (speaker identification)
 
         ### Note:
-        - Pricing differs for Real-Time and Batch APIs
+        - Pricing differs for REST and Batch APIs
         - Diarization is only available in Batch API with separate pricing
-        - Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+        - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information
 
         Parameters
         ----------
@@ -463,19 +463,19 @@ class AsyncRawSpeechToTextClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[SpeechToTextTranslateResponse]:
         """
-        ## Real-Time Speech to Text Translation API
+        ## Speech to Text Translation API
 
         This API automatically detects the input language, transcribes the speech, and translates the text to English.
 
         ### Available Options:
-        - **Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results
-        - **Batch API**: For longer audio files, requires following a notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt-translate/stt-translate-batch-api)
+        - **REST API** (Current Endpoint): For quick responses under 30 seconds with immediate results
+        - **Batch API**: For longer audio files [Follow this documentation](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api)
           - Supports diarization (speaker identification)
 
         ### Note:
-        - Pricing differs for Real-Time and Batch APIs
+        - Pricing differs for REST and Batch APIs
         - Diarization is only available in Batch API with separate pricing
-        - Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information
+        - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information
 
         Parameters
         ----------

sarvamai/speech_to_text_job/client.py

@@ -10,7 +10,10 @@ from ..types.bulk_job_init_response_v_1 import BulkJobInitResponseV1
 from ..types.files_download_response import FilesDownloadResponse
 from ..types.files_upload_response import FilesUploadResponse
 from ..types.job_status_v_1_response import JobStatusV1Response
+from ..types.speech_to_text_model import SpeechToTextModel
+from ..types.speech_to_text_language import SpeechToTextLanguage
 from .raw_client import AsyncRawSpeechToTextJobClient, RawSpeechToTextJobClient
+from .job import AsyncSpeechToTextJob, SpeechToTextJob
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -215,6 +218,76 @@ class SpeechToTextJobClient:
         _response = self._raw_client.get_download_links(job_id=job_id, files=files, request_options=request_options)
         return _response.data
 
+    def create_job(
+        self,
+        model: SpeechToTextModel = "saarika:v2.5",
+        with_diarization: bool = False,
+        with_timestamps: bool = False,
+        language_code: typing.Optional[SpeechToTextLanguage] = None,
+        num_speakers: typing.Optional[int] = None,
+        callback: typing.Optional[BulkJobCallbackParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> SpeechToTextJob:
+        """
+        Create a new Speech-to-Text bulk job.
+
+        Parameters
+        ----------
+        model : SpeechToTextModel, default="saarika:v2.5"
+            The model to use for transcription.
+
+        with_diarization : typing.Optional[bool], default=False
+            Whether to enable speaker diarization (distinguishing who said what).
+
+        with_timestamps : typing.Optional[bool], default=False
+            Whether to include word-level timestamps in the transcription output.
+
+        language_code : typing.Optional[SpeechToTextLanguage], default=None
+            The language code of the input audio (e.g., "hi-IN", "bn-IN").
+            
+        num_speakers : typing.Optional[int], default=None
+            The number of distinct speakers in the audio, if known.
+
+        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=SpeechToTextJobParametersParams(
+                language_code=language_code,
+                model=model,
+                num_speakers=num_speakers,  # type: ignore[typeddict-item]
+                with_diarization=with_diarization,
+                with_timestamps=with_timestamps,
+            ),
+            callback=callback,
+            request_options=request_options,
+        )
+        return SpeechToTextJob(job_id=response.job_id, client=self)
+
+    def get_job(self, job_id: str) -> SpeechToTextJob:
+        """
+        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)
+
 
 class AsyncSpeechToTextJobClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
@@ -456,3 +529,73 @@ class AsyncSpeechToTextJobClient:
             job_id=job_id, files=files, request_options=request_options
         )
         return _response.data
+
+    async def create_job(
+        self,
+        model: SpeechToTextModel = "saarika:v2.5",
+        with_diarization: bool = False,
+        with_timestamps: bool = False,
+        language_code: typing.Optional[SpeechToTextLanguage] = None,
+        num_speakers: typing.Optional[int] = None,
+        callback: typing.Optional[BulkJobCallbackParams] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> "AsyncSpeechToTextJob":
+        """
+        Create a new Speech-to-Text bulk job.
+
+        Parameters
+        ----------
+        model : SpeechToTextModel, default="saarika:v2.5"
+            The model to use for transcription.
+
+        with_diarization : typing.Optional[bool], default=False
+            Whether to enable speaker diarization (distinguishing who said what).
+
+        with_timestamps : typing.Optional[bool], default=False
+            Whether to include word-level timestamps in the transcription output.
+
+        language_code : typing.Optional[SpeechToTextLanguage], default=None
+            The language code of the input audio (e.g., "hi-IN", "bn-IN").
+            
+        num_speakers : typing.Optional[int], default=None
+            The number of distinct speakers in the audio, if known.
+
+        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=SpeechToTextJobParametersParams(
+                language_code=language_code,
+                model=model,
+                with_diarization=with_diarization,
+                with_timestamps=with_timestamps,
+                num_speakers=num_speakers,  # type: ignore[typeddict-item]
+            ),
+            callback=callback,
+            request_options=request_options,
+        )
+        return AsyncSpeechToTextJob(job_id=response.job_id, client=self)
+
+    async def get_job(self, job_id: str) -> "AsyncSpeechToTextJob":
+        """
+        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)