# This file was auto-generated by Fern from our API Definition. import typing from json.decoder import JSONDecodeError from .. import core from ..core.api_error import ApiError from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper from ..core.http_response import AsyncHttpResponse, HttpResponse from ..core.pydantic_utilities import parse_obj_as from ..core.request_options import RequestOptions from ..errors.bad_request_error import BadRequestError from ..errors.forbidden_error import ForbiddenError 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.mode import Mode 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 # this is used as the default value for optional parameters OMIT = typing.cast(typing.Any, ...) class RawSpeechToTextClient: def __init__(self, *, client_wrapper: SyncClientWrapper): self._client_wrapper = client_wrapper def transcribe( self, *, file: core.File, model: typing.Optional[SpeechToTextModel] = OMIT, mode: typing.Optional[Mode] = OMIT, language_code: typing.Optional[SpeechToTextLanguage] = OMIT, input_audio_codec: typing.Optional[InputAudioCodec] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[SpeechToTextResponse]: """ ## Speech to Text API This API transcribes speech to text in multiple Indian languages and English. Supports transcription for interactive applications. ### Available Options: - **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 REST and Batch APIs - Diarization is only available in Batch API with separate pricing - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information Parameters ---------- file : core.File See core.File for more documentation model : typing.Optional[SpeechToTextModel] Specifies the model to use for speech-to-text conversion. - **saarika:v2.5** (default): Transcribes audio in the spoken language. - **saaras:v3**: State-of-the-art model with flexible output formats. Supports multiple modes via the `mode` parameter: transcribe, translate, verbatim, translit, codemix. mode : typing.Optional[Mode] Mode of operation. **Only applicable when using saaras:v3 model.** Example audio: 'मेरा फोन नंबर है 9840950950' - **transcribe** (default): Standard transcription in the original language with proper formatting and number normalization. - Output: `मेरा फोन नंबर है 9840950950` - **translate**: Translates speech from any supported Indic language to English. - Output: `My phone number is 9840950950` - **verbatim**: Exact word-for-word transcription without normalization, preserving filler words and spoken numbers as-is. - Output: `मेरा फोन नंबर है नौ आठ चार zero नौ पांच zero नौ पांच zero` - **translit**: Romanization - Transliterates speech to Latin/Roman script only. - Output: `mera phone number hai 9840950950` - **codemix**: Code-mixed text with English words in English and Indic words in native script. - Output: `मेरा phone number है 9840950950` language_code : typing.Optional[SpeechToTextLanguage] Specifies the language of the input audio in BCP-47 format. **Note:** This parameter is optional for `saarika:v2.5` model. **Available Options:** - `unknown`: Use when the language is not known; the API will auto-detect. - `hi-IN`: Hindi - `bn-IN`: Bengali - `kn-IN`: Kannada - `ml-IN`: Malayalam - `mr-IN`: Marathi - `od-IN`: Odia - `pa-IN`: Punjabi - `ta-IN`: Tamil - `te-IN`: Telugu - `en-IN`: English - `gu-IN`: Gujarati **Additional Options (saaras:v3 only):** - `as-IN`: Assamese - `ur-IN`: Urdu - `ne-IN`: Nepali - `kok-IN`: Konkani - `ks-IN`: Kashmiri - `sd-IN`: Sindhi - `sa-IN`: Sanskrit - `sat-IN`: Santali - `mni-IN`: Manipuri - `brx-IN`: Bodo - `mai-IN`: Maithili - `doi-IN`: Dogri 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] Request-specific configuration. Returns ------- HttpResponse[SpeechToTextResponse] Successful Response """ _response = self._client_wrapper.httpx_client.request( "speech-to-text", base_url=self._client_wrapper.get_environment().base, method="POST", data={ "model": model, "mode": mode, "language_code": language_code, "input_audio_codec": input_audio_codec, }, files={ "file": file, }, request_options=request_options, omit=OMIT, force_multipart=True, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( SpeechToTextResponse, parse_obj_as( type_=SpeechToTextResponse, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 403: raise ForbiddenError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 429: raise TooManyRequestsError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 500: raise InternalServerError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 503: raise ServiceUnavailableError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) def translate( self, *, file: core.File, prompt: typing.Optional[str] = OMIT, model: typing.Optional[SpeechToTextTranslateModel] = OMIT, input_audio_codec: typing.Optional[InputAudioCodec] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> HttpResponse[SpeechToTextTranslateResponse]: """ ## Speech to Text Translation API This API automatically detects the input language, transcribes the speech, and translates the text to English. ### Available Options: - **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 REST and Batch APIs - Diarization is only available in Batch API with separate pricing - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information Parameters ---------- file : core.File See core.File for more documentation prompt : typing.Optional[str] Conversation context can be passed as a prompt to boost model accuracy. However, the current system is at an experimentation stage and doesn't match the prompt performance of large language models. model : typing.Optional[SpeechToTextTranslateModel] Model to be used for speech to text translation. - **saaras:v2.5** (default): Translation model that translates audio from any spoken Indic language to English. - Example: Hindi audio → English text output 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] Request-specific configuration. Returns ------- HttpResponse[SpeechToTextTranslateResponse] Successful Response """ _response = self._client_wrapper.httpx_client.request( "speech-to-text-translate", base_url=self._client_wrapper.get_environment().base, method="POST", data={ "prompt": prompt, "model": model, "input_audio_codec": input_audio_codec, }, files={ "file": file, }, request_options=request_options, omit=OMIT, force_multipart=True, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( SpeechToTextTranslateResponse, parse_obj_as( type_=SpeechToTextTranslateResponse, # type: ignore object_=_response.json(), ), ) return HttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 403: raise ForbiddenError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 429: raise TooManyRequestsError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 500: raise InternalServerError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 503: raise ServiceUnavailableError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) class AsyncRawSpeechToTextClient: def __init__(self, *, client_wrapper: AsyncClientWrapper): self._client_wrapper = client_wrapper async def transcribe( self, *, file: core.File, model: typing.Optional[SpeechToTextModel] = OMIT, mode: typing.Optional[Mode] = OMIT, language_code: typing.Optional[SpeechToTextLanguage] = OMIT, input_audio_codec: typing.Optional[InputAudioCodec] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[SpeechToTextResponse]: """ ## Speech to Text API This API transcribes speech to text in multiple Indian languages and English. Supports transcription for interactive applications. ### Available Options: - **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 REST and Batch APIs - Diarization is only available in Batch API with separate pricing - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information Parameters ---------- file : core.File See core.File for more documentation model : typing.Optional[SpeechToTextModel] Specifies the model to use for speech-to-text conversion. - **saarika:v2.5** (default): Transcribes audio in the spoken language. - **saaras:v3**: State-of-the-art model with flexible output formats. Supports multiple modes via the `mode` parameter: transcribe, translate, verbatim, translit, codemix. mode : typing.Optional[Mode] Mode of operation. **Only applicable when using saaras:v3 model.** Example audio: 'मेरा फोन नंबर है 9840950950' - **transcribe** (default): Standard transcription in the original language with proper formatting and number normalization. - Output: `मेरा फोन नंबर है 9840950950` - **translate**: Translates speech from any supported Indic language to English. - Output: `My phone number is 9840950950` - **verbatim**: Exact word-for-word transcription without normalization, preserving filler words and spoken numbers as-is. - Output: `मेरा फोन नंबर है नौ आठ चार zero नौ पांच zero नौ पांच zero` - **translit**: Romanization - Transliterates speech to Latin/Roman script only. - Output: `mera phone number hai 9840950950` - **codemix**: Code-mixed text with English words in English and Indic words in native script. - Output: `मेरा phone number है 9840950950` language_code : typing.Optional[SpeechToTextLanguage] Specifies the language of the input audio in BCP-47 format. **Note:** This parameter is optional for `saarika:v2.5` model. **Available Options:** - `unknown`: Use when the language is not known; the API will auto-detect. - `hi-IN`: Hindi - `bn-IN`: Bengali - `kn-IN`: Kannada - `ml-IN`: Malayalam - `mr-IN`: Marathi - `od-IN`: Odia - `pa-IN`: Punjabi - `ta-IN`: Tamil - `te-IN`: Telugu - `en-IN`: English - `gu-IN`: Gujarati **Additional Options (saaras:v3 only):** - `as-IN`: Assamese - `ur-IN`: Urdu - `ne-IN`: Nepali - `kok-IN`: Konkani - `ks-IN`: Kashmiri - `sd-IN`: Sindhi - `sa-IN`: Sanskrit - `sat-IN`: Santali - `mni-IN`: Manipuri - `brx-IN`: Bodo - `mai-IN`: Maithili - `doi-IN`: Dogri 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] Request-specific configuration. Returns ------- AsyncHttpResponse[SpeechToTextResponse] Successful Response """ _response = await self._client_wrapper.httpx_client.request( "speech-to-text", base_url=self._client_wrapper.get_environment().base, method="POST", data={ "model": model, "mode": mode, "language_code": language_code, "input_audio_codec": input_audio_codec, }, files={ "file": file, }, request_options=request_options, omit=OMIT, force_multipart=True, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( SpeechToTextResponse, parse_obj_as( type_=SpeechToTextResponse, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 403: raise ForbiddenError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 429: raise TooManyRequestsError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 500: raise InternalServerError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 503: raise ServiceUnavailableError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json) async def translate( self, *, file: core.File, prompt: typing.Optional[str] = OMIT, model: typing.Optional[SpeechToTextTranslateModel] = OMIT, input_audio_codec: typing.Optional[InputAudioCodec] = OMIT, request_options: typing.Optional[RequestOptions] = None, ) -> AsyncHttpResponse[SpeechToTextTranslateResponse]: """ ## Speech to Text Translation API This API automatically detects the input language, transcribes the speech, and translates the text to English. ### Available Options: - **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 REST and Batch APIs - Diarization is only available in Batch API with separate pricing - Please refer to [here](https://docs.sarvam.ai/api-reference-docs/getting-started/pricing) for detailed pricing information Parameters ---------- file : core.File See core.File for more documentation prompt : typing.Optional[str] Conversation context can be passed as a prompt to boost model accuracy. However, the current system is at an experimentation stage and doesn't match the prompt performance of large language models. model : typing.Optional[SpeechToTextTranslateModel] Model to be used for speech to text translation. - **saaras:v2.5** (default): Translation model that translates audio from any spoken Indic language to English. - Example: Hindi audio → English text output 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] Request-specific configuration. Returns ------- AsyncHttpResponse[SpeechToTextTranslateResponse] Successful Response """ _response = await self._client_wrapper.httpx_client.request( "speech-to-text-translate", base_url=self._client_wrapper.get_environment().base, method="POST", data={ "prompt": prompt, "model": model, "input_audio_codec": input_audio_codec, }, files={ "file": file, }, request_options=request_options, omit=OMIT, force_multipart=True, ) try: if 200 <= _response.status_code < 300: _data = typing.cast( SpeechToTextTranslateResponse, parse_obj_as( type_=SpeechToTextTranslateResponse, # type: ignore object_=_response.json(), ), ) return AsyncHttpResponse(response=_response, data=_data) if _response.status_code == 400: raise BadRequestError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 403: raise ForbiddenError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 422: raise UnprocessableEntityError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 429: raise TooManyRequestsError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 500: raise InternalServerError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) if _response.status_code == 503: raise ServiceUnavailableError( headers=dict(_response.headers), body=typing.cast( typing.Optional[typing.Any], parse_obj_as( type_=typing.Optional[typing.Any], # type: ignore object_=_response.json(), ), ), ) _response_json = _response.json() except JSONDecodeError: raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text) raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)