sarvamai 0.1.17a0__tar.gz → 0.1.18__tar.gz

{sarvamai-0.1.17a0 → sarvamai-0.1.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.17a0
+Version: 0.1.18
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.17a0 → sarvamai-0.1.18}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.17a0"
+version = "0.1.18"
 description = ""
 readme = "README.md"
 authors = []

{sarvamai-0.1.17a0 → sarvamai-0.1.18}/src/sarvamai/__init__.py

@@ -44,6 +44,7 @@ from .types import (
     FilesUploadResponse,
     FinishReason,
     FlushSignal,
+    InputAudioCodec,
     JobState,
     JobStatusV1Response,
     LanguageIdentificationResponse,
@@ -174,7 +175,6 @@ from .requests import (
     TranslationResponseParams,
     TransliterationResponseParams,
 )
-from .speech_to_text import SpeechToTextTranscribeRequestInputAudioCodec, SpeechToTextTranslateRequestInputAudioCodec
 from .speech_to_text_streaming import (
     SpeechToTextStreamingHighVadSensitivity,
     SpeechToTextStreamingLanguageCode,
@@ -267,6 +267,7 @@ __all__ = [
     "FlushSignal",
     "FlushSignalParams",
     "ForbiddenError",
+    "InputAudioCodec",
     "InternalServerError",
     "JobState",
     "JobStatusV1Response",
@@ -302,14 +303,12 @@ __all__ = [
     "SpeechToTextStreamingResponse",
     "SpeechToTextStreamingResponseParams",
     "SpeechToTextStreamingVadSignals",
-    "SpeechToTextTranscribeRequestInputAudioCodec",
     "SpeechToTextTranscriptionData",
     "SpeechToTextTranscriptionDataParams",
     "SpeechToTextTranslateJobParameters",
     "SpeechToTextTranslateJobParametersParams",
     "SpeechToTextTranslateLanguage",
     "SpeechToTextTranslateModel",
-    "SpeechToTextTranslateRequestInputAudioCodec",
     "SpeechToTextTranslateResponse",
     "SpeechToTextTranslateResponseData",
     "SpeechToTextTranslateResponseDataParams",

{sarvamai-0.1.17a0 → sarvamai-0.1.18}/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/0.1.17a0",
+            "User-Agent": "sarvamai/0.1.18",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.17a0",
+            "X-Fern-SDK-Version": "0.1.18",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

{sarvamai-0.1.17a0 → sarvamai-0.1.18}/src/sarvamai/speech_to_text/client.py

@@ -5,14 +5,13 @@ import typing
 from .. import core
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
+from ..types.input_audio_codec import InputAudioCodec
 from ..types.speech_to_text_language import SpeechToTextLanguage
 from ..types.speech_to_text_model import SpeechToTextModel
 from ..types.speech_to_text_response import SpeechToTextResponse
 from ..types.speech_to_text_translate_model import SpeechToTextTranslateModel
 from ..types.speech_to_text_translate_response import SpeechToTextTranslateResponse
 from .raw_client import AsyncRawSpeechToTextClient, RawSpeechToTextClient
-from .types.speech_to_text_transcribe_request_input_audio_codec import SpeechToTextTranscribeRequestInputAudioCodec
-from .types.speech_to_text_translate_request_input_audio_codec import SpeechToTextTranslateRequestInputAudioCodec
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -39,7 +38,7 @@ class SpeechToTextClient:
         file: core.File,
         model: typing.Optional[SpeechToTextModel] = OMIT,
         language_code: typing.Optional[SpeechToTextLanguage] = OMIT,
-        input_audio_codec: typing.Optional[SpeechToTextTranscribeRequestInputAudioCodec] = OMIT,
+        input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextResponse:
         """
@@ -71,7 +70,7 @@ class SpeechToTextClient:
              For the `saarika:v2.5` model, it is optional.
             `unknown`: Use this when the language is not known; the API will detect it automatically.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranscribeRequestInputAudioCodec]
+        input_audio_codec : typing.Optional[InputAudioCodec]
             Input Audio codec/format of the input file. PCM files are supported only at 16kHz sample rate.
 
         request_options : typing.Optional[RequestOptions]
@@ -106,7 +105,7 @@ class SpeechToTextClient:
         file: core.File,
         prompt: typing.Optional[str] = OMIT,
         model: typing.Optional[SpeechToTextTranslateModel] = OMIT,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateRequestInputAudioCodec] = OMIT,
+        input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextTranslateResponse:
         """
@@ -135,7 +134,7 @@ class SpeechToTextClient:
         model : typing.Optional[SpeechToTextTranslateModel]
             Model to be used for converting speech to text in target language
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateRequestInputAudioCodec]
+        input_audio_codec : typing.Optional[InputAudioCodec]
             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 are supported only at 16kHz sample rate.
 
         request_options : typing.Optional[RequestOptions]
@@ -182,7 +181,7 @@ class AsyncSpeechToTextClient:
         file: core.File,
         model: typing.Optional[SpeechToTextModel] = OMIT,
         language_code: typing.Optional[SpeechToTextLanguage] = OMIT,
-        input_audio_codec: typing.Optional[SpeechToTextTranscribeRequestInputAudioCodec] = OMIT,
+        input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextResponse:
         """
@@ -214,7 +213,7 @@ class AsyncSpeechToTextClient:
              For the `saarika:v2.5` model, it is optional.
             `unknown`: Use this when the language is not known; the API will detect it automatically.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranscribeRequestInputAudioCodec]
+        input_audio_codec : typing.Optional[InputAudioCodec]
             Input Audio codec/format of the input file. PCM files are supported only at 16kHz sample rate.
 
         request_options : typing.Optional[RequestOptions]
@@ -257,7 +256,7 @@ class AsyncSpeechToTextClient:
         file: core.File,
         prompt: typing.Optional[str] = OMIT,
         model: typing.Optional[SpeechToTextTranslateModel] = OMIT,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateRequestInputAudioCodec] = OMIT,
+        input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SpeechToTextTranslateResponse:
         """
@@ -286,7 +285,7 @@ class AsyncSpeechToTextClient:
         model : typing.Optional[SpeechToTextTranslateModel]
             Model to be used for converting speech to text in target language
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateRequestInputAudioCodec]
+        input_audio_codec : typing.Optional[InputAudioCodec]
             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 are supported only at 16kHz sample rate.
 
         request_options : typing.Optional[RequestOptions]

{sarvamai-0.1.17a0 → sarvamai-0.1.18}/src/sarvamai/speech_to_text/raw_client.py

@@ -15,13 +15,12 @@ from ..errors.internal_server_error import InternalServerError
 from ..errors.service_unavailable_error import ServiceUnavailableError
 from ..errors.too_many_requests_error import TooManyRequestsError
 from ..errors.unprocessable_entity_error import UnprocessableEntityError
+from ..types.input_audio_codec import InputAudioCodec
 from ..types.speech_to_text_language import SpeechToTextLanguage
 from ..types.speech_to_text_model import SpeechToTextModel
 from ..types.speech_to_text_response import SpeechToTextResponse
 from ..types.speech_to_text_translate_model import SpeechToTextTranslateModel
 from ..types.speech_to_text_translate_response import SpeechToTextTranslateResponse
-from .types.speech_to_text_transcribe_request_input_audio_codec import SpeechToTextTranscribeRequestInputAudioCodec
-from .types.speech_to_text_translate_request_input_audio_codec import SpeechToTextTranslateRequestInputAudioCodec
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -37,7 +36,7 @@ class RawSpeechToTextClient:
         file: core.File,
         model: typing.Optional[SpeechToTextModel] = OMIT,
         language_code: typing.Optional[SpeechToTextLanguage] = OMIT,
-        input_audio_codec: typing.Optional[SpeechToTextTranscribeRequestInputAudioCodec] = OMIT,
+        input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[SpeechToTextResponse]:
         """
@@ -69,7 +68,7 @@ class RawSpeechToTextClient:
              For the `saarika:v2.5` model, it is optional.
             `unknown`: Use this when the language is not known; the API will detect it automatically.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranscribeRequestInputAudioCodec]
+        input_audio_codec : typing.Optional[InputAudioCodec]
             Input Audio codec/format of the input file. PCM files are supported only at 16kHz sample rate.
 
         request_options : typing.Optional[RequestOptions]
@@ -183,7 +182,7 @@ class RawSpeechToTextClient:
         file: core.File,
         prompt: typing.Optional[str] = OMIT,
         model: typing.Optional[SpeechToTextTranslateModel] = OMIT,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateRequestInputAudioCodec] = OMIT,
+        input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[SpeechToTextTranslateResponse]:
         """
@@ -212,7 +211,7 @@ class RawSpeechToTextClient:
         model : typing.Optional[SpeechToTextTranslateModel]
             Model to be used for converting speech to text in target language
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateRequestInputAudioCodec]
+        input_audio_codec : typing.Optional[InputAudioCodec]
             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 are supported only at 16kHz sample rate.
 
         request_options : typing.Optional[RequestOptions]
@@ -331,7 +330,7 @@ class AsyncRawSpeechToTextClient:
         file: core.File,
         model: typing.Optional[SpeechToTextModel] = OMIT,
         language_code: typing.Optional[SpeechToTextLanguage] = OMIT,
-        input_audio_codec: typing.Optional[SpeechToTextTranscribeRequestInputAudioCodec] = OMIT,
+        input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[SpeechToTextResponse]:
         """
@@ -363,7 +362,7 @@ class AsyncRawSpeechToTextClient:
              For the `saarika:v2.5` model, it is optional.
             `unknown`: Use this when the language is not known; the API will detect it automatically.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranscribeRequestInputAudioCodec]
+        input_audio_codec : typing.Optional[InputAudioCodec]
             Input Audio codec/format of the input file. PCM files are supported only at 16kHz sample rate.
 
         request_options : typing.Optional[RequestOptions]
@@ -477,7 +476,7 @@ class AsyncRawSpeechToTextClient:
         file: core.File,
         prompt: typing.Optional[str] = OMIT,
         model: typing.Optional[SpeechToTextTranslateModel] = OMIT,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateRequestInputAudioCodec] = OMIT,
+        input_audio_codec: typing.Optional[InputAudioCodec] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[SpeechToTextTranslateResponse]:
         """
@@ -506,7 +505,7 @@ class AsyncRawSpeechToTextClient:
         model : typing.Optional[SpeechToTextTranslateModel]
             Model to be used for converting speech to text in target language
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateRequestInputAudioCodec]
+        input_audio_codec : typing.Optional[InputAudioCodec]
             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 are supported only at 16kHz sample rate.
 
         request_options : typing.Optional[RequestOptions]

sarvamai-0.1.18/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-0.1.17a0 → sarvamai-0.1.18}/src/sarvamai/types/__init__.py

@@ -45,6 +45,7 @@ from .files_request import FilesRequest
 from .files_upload_response import FilesUploadResponse
 from .finish_reason import FinishReason
 from .flush_signal import FlushSignal
+from .input_audio_codec import InputAudioCodec
 from .job_state import JobState
 from .job_status_v_1_response import JobStatusV1Response
 from .language_identification_response import LanguageIdentificationResponse
@@ -137,6 +138,7 @@ __all__ = [
     "FilesUploadResponse",
     "FinishReason",
     "FlushSignal",
+    "InputAudioCodec",
     "JobState",
     "JobStatusV1Response",
     "LanguageIdentificationResponse",

sarvamai-0.1.17a0/src/sarvamai/speech_to_text/types/speech_to_text_translate_request_input_audio_codec.py → sarvamai-0.1.18/src/sarvamai/types/input_audio_codec.py

@@ -2,7 +2,7 @@
 
 import typing
 
-SpeechToTextTranslateRequestInputAudioCodec = typing.Union[
+InputAudioCodec = typing.Union[
     typing.Literal[
         "wav",
         "x-wav",

sarvamai-0.1.17a0/src/sarvamai/speech_to_text/__init__.py

@@ -1,7 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-# isort: skip_file
-
-from .types import SpeechToTextTranscribeRequestInputAudioCodec, SpeechToTextTranslateRequestInputAudioCodec
-
-__all__ = ["SpeechToTextTranscribeRequestInputAudioCodec", "SpeechToTextTranslateRequestInputAudioCodec"]

sarvamai-0.1.17a0/src/sarvamai/speech_to_text/types/__init__.py

@@ -1,8 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-# isort: skip_file
-
-from .speech_to_text_transcribe_request_input_audio_codec import SpeechToTextTranscribeRequestInputAudioCodec
-from .speech_to_text_translate_request_input_audio_codec import SpeechToTextTranslateRequestInputAudioCodec
-
-__all__ = ["SpeechToTextTranscribeRequestInputAudioCodec", "SpeechToTextTranslateRequestInputAudioCodec"]

sarvamai-0.1.17a0/src/sarvamai/speech_to_text/types/speech_to_text_transcribe_request_input_audio_codec.py

@@ -1,33 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import typing
-
-SpeechToTextTranscribeRequestInputAudioCodec = 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,
-]