o qmi{@s.ddlZddlmZddlmZddlmZddlmZm Z ddl m Z m Z ddl mZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlmZddlm Z ddl!m"Z"ddl#m$Z$ddl%m&Z&ddl'm(Z(ddl)m*Z*e+ej,dZ-GdddZ.GdddZ/dS)N)JSONDecodeError)core)ApiError)AsyncClientWrapperSyncClientWrapper)AsyncHttpResponse HttpResponse) parse_obj_as)RequestOptions)BadRequestError)ForbiddenError)InternalServerError)ServiceUnavailableError)TooManyRequestsError)UnprocessableEntityError)InputAudioCodec)Mode)SpeechToTextLanguage)SpeechToTextModel)SpeechToTextResponse)SpeechToTextTranslateModel)SpeechToTextTranslateResponse.c@eZdZdefddZeeeedddejdej e dej e d ej e d ej e d ej ed eefd dZeeedddejdej edej ed ej e d ej ed eef ddZdS)RawSpeechToTextClientclient_wrappercC ||_dSN_client_wrapperselfrr"V/home/ubuntu/.local/lib/python3.10/site-packages/sarvamai/speech_to_text/raw_client.py__init__ zRawSpeechToTextClient.__init__Nmodelmode language_codeinput_audio_codecrequest_optionsfiler'r(r)r*r+returnc Cs@|jjjd|jjd||||dd|i|tdd}zd|jkr&dkr;nntt t t | d }t ||d WS|jd kr[t t|jttjtjt tjtj| d d |jd kr{tt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d | } Wntyt|jt|j|jdwt|jt|j| d)u ## 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 speech-to-textPOSTr'r(r)r*r,Tbase_urlmethoddatafilesr+omitforce_multipart,type_object_responser4headersbody status_coderArB)r httpx_clientrequestget_environmentbaseOMITrItypingcastrr jsonr r dictrAOptionalAnyr rrrrrrtext r!r,r'r(r)r*r+ _response_data_response_jsonr"r"r# transcribe"se                    z RawSpeechToTextClient.transcribepromptr'r*r+r\c Cs>|jjjd|jjd|||dd|i|tdd}zd|jkr%dkr:nntt t t | d }t ||d WS|jd krZt t|jttjtjt tjtj| d d |jd krztt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d | }Wntyt|jt|j|jdwt|jt|j|d)u ## 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 speech-to-text-translater/r\r'r*r,Tr1r8r9r:r=r?r@rCrDrErFrGrH)rrJrKrLrMrNrIrOrPrr rQr r rRrArSrTr rrrrrrrU r!r,r\r'r*r+rWrXrYr"r"r# translates1                    zRawSpeechToTextClient.translate)__name__ __module__ __qualname__rr$rNrFilerOrSrrrrr r rrZstrrrr`r"r"r"r#rP Lrc@r)AsyncRawSpeechToTextClientrcCrrrr r"r"r#r$}r%z#AsyncRawSpeechToTextClient.__init__Nr&r,r'r(r)r*r+r-c sH|jjjd|jjd||||dd|i|tddIdH}zd|jkr*d kr?nntt t t | d }t ||d WS|jd kr_t t|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d | } Wntyt|jt|j|jdwt|jt|j| d)u ## 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 r.r/r0r,Tr1Nr8r9r:r=r?r@rCrDrErFrGrH)rrJrKrLrMrNrIrOrPrr rQrr rRrArSrTr rrrrrrrUrVr"r"r#rZse                     z%AsyncRawSpeechToTextClient.transcriber[r\c sF|jjjd|jjd|||dd|i|tddIdH}zd|jkr)d kr>nntt t t | d }t ||d WS|jd kr^t t|jttjtjt tjtj| d d |jdkr~tt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d |jdkrtt|jttjtjt tjtj| d d | }Wntyt|jt|j|jdwt|jt|j|d)u ## 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 r]r/r^r,Tr1Nr8r9r:r=r?r@rCrDrErFrGrH)rrJrKrLrMrNrIrOrPrr rQrr rRrArSrTr rrrrrrrUr_r"r"r#r`Gs1                     z$AsyncRawSpeechToTextClient.translate)rarbrcrr$rNrrdrOrSrrrrr rrrZrerrr`r"r"r"r#rg|rfrg)0rO json.decoderrrcore.api_errorrcore.client_wrapperrrcore.http_responserr core.pydantic_utilitiesr core.request_optionsr errors.bad_request_errorr errors.forbidden_errorr errors.internal_server_errorr errors.service_unavailable_errorrerrors.too_many_requests_errorr!errors.unprocessable_entity_errorrtypes.input_audio_codecr types.modertypes.speech_to_text_languagertypes.speech_to_text_modelrtypes.speech_to_text_responser$types.speech_to_text_translate_modelr'types.speech_to_text_translate_responserrPrTrNrrgr"r"r"r#s4                  `