sarvamai 0.1.22a3__py3-none-any.whl → 0.1.22a7__py3-none-any.whl

sarvamai/speech_to_text_translate_job/job.py

@@ -150,9 +150,58 @@ class AsyncSpeechToTextTranslateJob:
                 "output_file": detail.outputs[0].file_name,
             }
             for detail in (job_status.job_details or [])
-            if detail.inputs and detail.outputs
+            if detail.inputs and detail.outputs and detail.state == "Success"
         ]
 
+    async def get_file_results(
+        self,
+    ) -> typing.Dict[str, typing.List[typing.Dict[str, typing.Any]]]:
+        """
+        Get detailed results for each file in the batch job.
+
+        Returns
+        -------
+        Dict[str, List[Dict[str, Any]]]
+            Dictionary with 'successful' and 'failed' keys, each containing a list of file details.
+            Each file detail includes:
+            - 'file_name': Name of the input file
+            - 'status': Status of processing ('Success' or 'Failed')
+            - 'error_message': Error message if failed (None if successful)
+            - 'output_file': Name of output file if successful (None if failed)
+        """
+        job_status = await self.get_status()
+        results: typing.Dict[str, typing.List[typing.Dict[str, typing.Any]]] = {
+            "successful": [],
+            "failed": [],
+        }
+
+        for detail in job_status.job_details or []:
+            # Check for empty lists explicitly
+            if not detail.inputs or len(detail.inputs) == 0:
+                continue
+
+            try:
+                file_info = {
+                    "file_name": detail.inputs[0].file_name,
+                    "status": detail.state,
+                    "error_message": detail.error_message,
+                    "output_file": (
+                        detail.outputs[0].file_name
+                        if detail.outputs and len(detail.outputs) > 0
+                        else None
+                    ),
+                }
+
+                if detail.state == "Success":
+                    results["successful"].append(file_info)
+                else:
+                    results["failed"].append(file_info)
+            except (IndexError, AttributeError):
+                # Skip malformed job details
+                continue
+
+        return results
+
     async def download_outputs(self, output_dir: str) -> bool:
         """
         Download output files to the specified directory.
@@ -395,9 +444,58 @@ class SpeechToTextTranslateJob:
                 "output_file": detail.outputs[0].file_name,
             }
             for detail in (job_status.job_details or [])
-            if detail.inputs and detail.outputs
+            if detail.inputs and detail.outputs and detail.state == "Success"
         ]
 
+    def get_file_results(
+        self,
+    ) -> typing.Dict[str, typing.List[typing.Dict[str, typing.Any]]]:
+        """
+        Get detailed results for each file in the batch job.
+
+        Returns
+        -------
+        Dict[str, List[Dict[str, Any]]]
+            Dictionary with 'successful' and 'failed' keys, each containing a list of file details.
+            Each file detail includes:
+            - 'file_name': Name of the input file
+            - 'status': Status of processing ('Success' or 'Failed')
+            - 'error_message': Error message if failed (None if successful)
+            - 'output_file': Name of output file if successful (None if failed)
+        """
+        job_status = self.get_status()
+        results: typing.Dict[str, typing.List[typing.Dict[str, typing.Any]]] = {
+            "successful": [],
+            "failed": [],
+        }
+
+        for detail in job_status.job_details or []:
+            # Check for empty lists explicitly
+            if not detail.inputs or len(detail.inputs) == 0:
+                continue
+
+            try:
+                file_info = {
+                    "file_name": detail.inputs[0].file_name,
+                    "status": detail.state,
+                    "error_message": detail.error_message,
+                    "output_file": (
+                        detail.outputs[0].file_name
+                        if detail.outputs and len(detail.outputs) > 0
+                        else None
+                    ),
+                }
+
+                if detail.state == "Success":
+                    results["successful"].append(file_info)
+                else:
+                    results["failed"].append(file_info)
+            except (IndexError, AttributeError):
+                # Skip malformed job details
+                continue
+
+        return results
+
     def download_outputs(self, output_dir: str) -> bool:
         """
         Download output files to the specified directory.

sarvamai/speech_to_text_translate_job/raw_client.py

@@ -40,7 +40,7 @@ class RawSpeechToTextTranslateJobClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[BulkJobInitResponseV1]:
         """
-        Get a job uuid, and storage folder details for speech to text tranlsate bulk job v1
+        Create a new speech to text translate bulk job and receive a job UUID and storage folder details for processing multiple audio files with translation
 
         Parameters
         ----------
@@ -166,7 +166,9 @@ class RawSpeechToTextTranslateJobClient:
         self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
     ) -> HttpResponse[JobStatusV1Response]:
         """
-        Get the status of a speech to text translate bulk job V1
+        Retrieve the current status and details of a speech to text translate bulk job, including progress and file-level information.
+
+        **Rate Limiting Best Practice:** To prevent rate limit errors and ensure optimal server performance, we recommend implementing a minimum 5-millisecond delay between consecutive status polling requests. This helps maintain system stability while still providing timely status updates.
 
         Parameters
         ----------
@@ -276,7 +278,7 @@ class RawSpeechToTextTranslateJobClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[JobStatusV1Response]:
         """
-        Start a speech to text translate bulk job V1
+        Start processing a speech to text translate bulk job after all audio files have been uploaded
 
         Parameters
         ----------
@@ -392,7 +394,7 @@ class RawSpeechToTextTranslateJobClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[FilesUploadResponse]:
         """
-        Start a speech to text bulk job V1
+        Generate presigned upload URLs for audio files that will be processed in a speech to text translate bulk job
 
         Parameters
         ----------
@@ -517,7 +519,7 @@ class RawSpeechToTextTranslateJobClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[FilesDownloadResponse]:
         """
-        Start a speech to text bulk job V1
+        Generate presigned download URLs for the translated transcription output files of a completed speech to text translate bulk job
 
         Parameters
         ----------
@@ -647,7 +649,7 @@ class AsyncRawSpeechToTextTranslateJobClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[BulkJobInitResponseV1]:
         """
-        Get a job uuid, and storage folder details for speech to text tranlsate bulk job v1
+        Create a new speech to text translate bulk job and receive a job UUID and storage folder details for processing multiple audio files with translation
 
         Parameters
         ----------
@@ -773,7 +775,9 @@ class AsyncRawSpeechToTextTranslateJobClient:
         self, job_id: str, *, request_options: typing.Optional[RequestOptions] = None
     ) -> AsyncHttpResponse[JobStatusV1Response]:
         """
-        Get the status of a speech to text translate bulk job V1
+        Retrieve the current status and details of a speech to text translate bulk job, including progress and file-level information.
+
+        **Rate Limiting Best Practice:** To prevent rate limit errors and ensure optimal server performance, we recommend implementing a minimum 5-millisecond delay between consecutive status polling requests. This helps maintain system stability while still providing timely status updates.
 
         Parameters
         ----------
@@ -883,7 +887,7 @@ class AsyncRawSpeechToTextTranslateJobClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[JobStatusV1Response]:
         """
-        Start a speech to text translate bulk job V1
+        Start processing a speech to text translate bulk job after all audio files have been uploaded
 
         Parameters
         ----------
@@ -999,7 +1003,7 @@ class AsyncRawSpeechToTextTranslateJobClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[FilesUploadResponse]:
         """
-        Start a speech to text bulk job V1
+        Generate presigned upload URLs for audio files that will be processed in a speech to text translate bulk job
 
         Parameters
         ----------
@@ -1124,7 +1128,7 @@ class AsyncRawSpeechToTextTranslateJobClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[FilesDownloadResponse]:
         """
-        Start a speech to text bulk job V1
+        Generate presigned download URLs for the translated transcription output files of a completed speech to text translate bulk job
 
         Parameters
         ----------

sarvamai/speech_to_text_translate_streaming/__init__.py

@@ -6,7 +6,6 @@ from .types import (
     SpeechToTextTranslateStreamingFlushSignal,
     SpeechToTextTranslateStreamingHighVadSensitivity,
     SpeechToTextTranslateStreamingInputAudioCodec,
-    SpeechToTextTranslateStreamingStreamOngoingSpeechResults,
     SpeechToTextTranslateStreamingVadSignals,
 )
 
@@ -14,6 +13,5 @@ __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
     "SpeechToTextTranslateStreamingInputAudioCodec",
-    "SpeechToTextTranslateStreamingStreamOngoingSpeechResults",
     "SpeechToTextTranslateStreamingVadSignals",
 ]

sarvamai/speech_to_text_translate_streaming/client.py

@@ -16,9 +16,6 @@ from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
     SpeechToTextTranslateStreamingHighVadSensitivity,
 )
 from .types.speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .types.speech_to_text_translate_streaming_stream_ongoing_speech_results import (
-    SpeechToTextTranslateStreamingStreamOngoingSpeechResults,
-)
 from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 try:
@@ -47,13 +44,11 @@ class SpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
-        stream_ongoing_speech_results: typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults] = None,
-        streaming_ongoing_requests_frame_size: typing.Optional[str] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextTranslateStreamingSocketClient]:
@@ -67,10 +62,10 @@ class SpeechToTextTranslateStreamingClient:
         Parameters
         ----------
         model : typing.Optional[typing.Literal["saaras:v2.5"]]
-            Speech to text model to use (defaults to "saaras:v2.5" if not specified)
+            Model to be used for speech to text translation.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+            - **saaras:v2.5** (default): Translation model that translates audio from any spoken Indic language to English.
+              - Example: Hindi audio → English text output
 
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
@@ -84,11 +79,9 @@ class SpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
-        stream_ongoing_speech_results : typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults]
-            Enable streaming of ongoing speech results during active speech
-
-        streaming_ongoing_requests_frame_size : typing.Optional[str]
-            Frame size for streaming ongoing speech results (1-100)
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input stream. Use this when sending raw PCM audio.
+            Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
 
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
@@ -104,8 +97,6 @@ class SpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -114,12 +105,8 @@ class SpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
-        if stream_ongoing_speech_results is not None:
-            query_params = query_params.add("stream_ongoing_speech_results", stream_ongoing_speech_results)
-        if streaming_ongoing_requests_frame_size is not None:
-            query_params = query_params.add(
-                "streaming_ongoing_requests_frame_size", streaming_ongoing_requests_frame_size
-            )
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
         ws_url = ws_url + f"?{query_params}"
         headers = self._raw_client._client_wrapper.get_headers()
         if api_subscription_key is not None:
@@ -164,13 +151,11 @@ class AsyncSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
-        stream_ongoing_speech_results: typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults] = None,
-        streaming_ongoing_requests_frame_size: typing.Optional[str] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextTranslateStreamingSocketClient]:
@@ -184,10 +169,10 @@ class AsyncSpeechToTextTranslateStreamingClient:
         Parameters
         ----------
         model : typing.Optional[typing.Literal["saaras:v2.5"]]
-            Speech to text model to use (defaults to "saaras:v2.5" if not specified)
+            Model to be used for speech to text translation.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+            - **saaras:v2.5** (default): Translation model that translates audio from any spoken Indic language to English.
+              - Example: Hindi audio → English text output
 
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
@@ -201,11 +186,9 @@ class AsyncSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
-        stream_ongoing_speech_results : typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults]
-            Enable streaming of ongoing speech results during active speech
-
-        streaming_ongoing_requests_frame_size : typing.Optional[str]
-            Frame size for streaming ongoing speech results (1-100)
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input stream. Use this when sending raw PCM audio.
+            Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
 
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
@@ -221,8 +204,6 @@ class AsyncSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -231,12 +212,8 @@ class AsyncSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
-        if stream_ongoing_speech_results is not None:
-            query_params = query_params.add("stream_ongoing_speech_results", stream_ongoing_speech_results)
-        if streaming_ongoing_requests_frame_size is not None:
-            query_params = query_params.add(
-                "streaming_ongoing_requests_frame_size", streaming_ongoing_requests_frame_size
-            )
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
         ws_url = ws_url + f"?{query_params}"
         headers = self._raw_client._client_wrapper.get_headers()
         if api_subscription_key is not None:

sarvamai/speech_to_text_translate_streaming/raw_client.py

@@ -15,9 +15,6 @@ from .types.speech_to_text_translate_streaming_high_vad_sensitivity import (
     SpeechToTextTranslateStreamingHighVadSensitivity,
 )
 from .types.speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .types.speech_to_text_translate_streaming_stream_ongoing_speech_results import (
-    SpeechToTextTranslateStreamingStreamOngoingSpeechResults,
-)
 from .types.speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 try:
@@ -35,13 +32,11 @@ class RawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
-        stream_ongoing_speech_results: typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults] = None,
-        streaming_ongoing_requests_frame_size: typing.Optional[str] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextTranslateStreamingSocketClient]:
@@ -55,10 +50,10 @@ class RawSpeechToTextTranslateStreamingClient:
         Parameters
         ----------
         model : typing.Optional[typing.Literal["saaras:v2.5"]]
-            Speech to text model to use (defaults to "saaras:v2.5" if not specified)
+            Model to be used for speech to text translation.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+            - **saaras:v2.5** (default): Translation model that translates audio from any spoken Indic language to English.
+              - Example: Hindi audio → English text output
 
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
@@ -72,11 +67,9 @@ class RawSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
-        stream_ongoing_speech_results : typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults]
-            Enable streaming of ongoing speech results during active speech
-
-        streaming_ongoing_requests_frame_size : typing.Optional[str]
-            Frame size for streaming ongoing speech results (1-100)
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input stream. Use this when sending raw PCM audio.
+            Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
 
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
@@ -92,8 +85,6 @@ class RawSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -102,12 +93,8 @@ class RawSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
-        if stream_ongoing_speech_results is not None:
-            query_params = query_params.add("stream_ongoing_speech_results", stream_ongoing_speech_results)
-        if streaming_ongoing_requests_frame_size is not None:
-            query_params = query_params.add(
-                "streaming_ongoing_requests_frame_size", streaming_ongoing_requests_frame_size
-            )
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
         ws_url = ws_url + f"?{query_params}"
         headers = self._client_wrapper.get_headers()
         if api_subscription_key is not None:
@@ -141,13 +128,11 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
-        stream_ongoing_speech_results: typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults] = None,
-        streaming_ongoing_requests_frame_size: typing.Optional[str] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextTranslateStreamingSocketClient]:
@@ -161,10 +146,10 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         Parameters
         ----------
         model : typing.Optional[typing.Literal["saaras:v2.5"]]
-            Speech to text model to use (defaults to "saaras:v2.5" if not specified)
+            Model to be used for speech to text translation.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            Audio codec/format of the input file. Our API automatically detects all codec formats, but for PCM files specifically (pcm_s16le, pcm_l16, pcm_raw), you must pass this parameter. PCM files supports sample rate 16000 and 8000.
+            - **saaras:v2.5** (default): Translation model that translates audio from any spoken Indic language to English.
+              - Example: Hindi audio → English text output
 
         sample_rate : typing.Optional[str]
             Audio sample rate for the WebSocket connection. When specified as a connection parameter, only 16kHz and 8kHz are supported. 8kHz is only available via this connection parameter. If not specified, defaults to 16kHz.
@@ -178,11 +163,9 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
-        stream_ongoing_speech_results : typing.Optional[SpeechToTextTranslateStreamingStreamOngoingSpeechResults]
-            Enable streaming of ongoing speech results during active speech
-
-        streaming_ongoing_requests_frame_size : typing.Optional[str]
-            Frame size for streaming ongoing speech results (1-100)
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input stream. Use this when sending raw PCM audio.
+            Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
 
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
@@ -198,8 +181,6 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -208,12 +189,8 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
-        if stream_ongoing_speech_results is not None:
-            query_params = query_params.add("stream_ongoing_speech_results", stream_ongoing_speech_results)
-        if streaming_ongoing_requests_frame_size is not None:
-            query_params = query_params.add(
-                "streaming_ongoing_requests_frame_size", streaming_ongoing_requests_frame_size
-            )
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
         ws_url = ws_url + f"?{query_params}"
         headers = self._client_wrapper.get_headers()
         if api_subscription_key is not None:

sarvamai/speech_to_text_translate_streaming/types/__init__.py

@@ -5,15 +5,11 @@
 from .speech_to_text_translate_streaming_flush_signal import SpeechToTextTranslateStreamingFlushSignal
 from .speech_to_text_translate_streaming_high_vad_sensitivity import SpeechToTextTranslateStreamingHighVadSensitivity
 from .speech_to_text_translate_streaming_input_audio_codec import SpeechToTextTranslateStreamingInputAudioCodec
-from .speech_to_text_translate_streaming_stream_ongoing_speech_results import (
-    SpeechToTextTranslateStreamingStreamOngoingSpeechResults,
-)
 from .speech_to_text_translate_streaming_vad_signals import SpeechToTextTranslateStreamingVadSignals
 
 __all__ = [
     "SpeechToTextTranslateStreamingFlushSignal",
     "SpeechToTextTranslateStreamingHighVadSensitivity",
     "SpeechToTextTranslateStreamingInputAudioCodec",
-    "SpeechToTextTranslateStreamingStreamOngoingSpeechResults",
     "SpeechToTextTranslateStreamingVadSignals",
 ]

sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_input_audio_codec.py

@@ -3,31 +3,5 @@
 import typing
 
 SpeechToTextTranslateStreamingInputAudioCodec = typing.Union[
-    typing.Literal[
-        "wav",
-        "x-wav",
-        "wave",
-        "mp3",
-        "mpeg",
-        "mpeg3",
-        "x-mp3",
-        "x-mpeg-3",
-        "aac",
-        "x-aac",
-        "aiff",
-        "x-aiff",
-        "ogg",
-        "opus",
-        "flac",
-        "x-flac",
-        "mp4",
-        "x-m4a",
-        "amr",
-        "x-ms-wma",
-        "webm",
-        "pcm_s16le",
-        "pcm_l16",
-        "pcm_raw",
-    ],
-    typing.Any,
+    typing.Literal["wav", "pcm_s16le", "pcm_l16", "pcm_raw"], typing.Any
 ]

sarvamai/text/client.py

@@ -47,7 +47,6 @@ class TextClient:
         speaker_gender: typing.Optional[TranslateSpeakerGender] = OMIT,
         mode: typing.Optional[TranslateMode] = OMIT,
         model: typing.Optional[TranslateModel] = OMIT,
-        enable_preprocessing: typing.Optional[bool] = OMIT,
         output_script: typing.Optional[TransliterateMode] = OMIT,
         numerals_format: typing.Optional[NumeralsFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
@@ -125,10 +124,6 @@ class TextClient:
             - mayura:v1: Supports 12 languages with all modes, output scripts, and automatic language detection.
             - sarvam-translate:v1: Supports all 22 scheduled languages of India, formal mode only.
 
-        enable_preprocessing : typing.Optional[bool]
-            This will enable custom preprocessing of the input text which can result in better translations.
-             Recommendation- You can switch on whenever there is some complex text with difficult vocabulary and sentences, for which you want simple translations that people can understand.
-
         output_script : typing.Optional[TransliterateMode]
             **output_script**: This is an optional parameter which controls the transliteration style applied to the output text.
 
@@ -186,7 +181,6 @@ class TextClient:
             speaker_gender=speaker_gender,
             mode=mode,
             model=model,
-            enable_preprocessing=enable_preprocessing,
             output_script=output_script,
             numerals_format=numerals_format,
             request_options=request_options,
@@ -371,7 +365,6 @@ class AsyncTextClient:
         speaker_gender: typing.Optional[TranslateSpeakerGender] = OMIT,
         mode: typing.Optional[TranslateMode] = OMIT,
         model: typing.Optional[TranslateModel] = OMIT,
-        enable_preprocessing: typing.Optional[bool] = OMIT,
         output_script: typing.Optional[TransliterateMode] = OMIT,
         numerals_format: typing.Optional[NumeralsFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
@@ -449,10 +442,6 @@ class AsyncTextClient:
             - mayura:v1: Supports 12 languages with all modes, output scripts, and automatic language detection.
             - sarvam-translate:v1: Supports all 22 scheduled languages of India, formal mode only.
 
-        enable_preprocessing : typing.Optional[bool]
-            This will enable custom preprocessing of the input text which can result in better translations.
-             Recommendation- You can switch on whenever there is some complex text with difficult vocabulary and sentences, for which you want simple translations that people can understand.
-
         output_script : typing.Optional[TransliterateMode]
             **output_script**: This is an optional parameter which controls the transliteration style applied to the output text.
 
@@ -518,7 +507,6 @@ class AsyncTextClient:
             speaker_gender=speaker_gender,
             mode=mode,
             model=model,
-            enable_preprocessing=enable_preprocessing,
             output_script=output_script,
             numerals_format=numerals_format,
             request_options=request_options,