PyPI - sarvamai - Versions diffs - 0.1.23a4__py3-none-any.whl → 0.1.23a5__py3-none-any.whl - Mend

sarvamai 0.1.23a4py3-none-any.whl → 0.1.23a5py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (18) hide show

sarvamai/core/client_wrapper.py CHANGED Viewed

@@ -23,10 +23,10 @@ class BaseClientWrapper:
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "sarvamai/0.1.23a4",
+            "User-Agent": "sarvamai/0.1.23a5",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "sarvamai",
-            "X-Fern-SDK-Version": "0.1.23a4",
+            "X-Fern-SDK-Version": "0.1.23a5",
             **(self.get_custom_headers() or {}),
         }
         headers["api-subscription-key"] = self.api_subscription_key

sarvamai/requests/speech_to_text_job_parameters.py CHANGED Viewed

@@ -9,20 +9,52 @@ from ..types.speech_to_text_translate_language import SpeechToTextTranslateLangu
 class SpeechToTextJobParametersParams(typing_extensions.TypedDict):
     language_code: typing_extensions.NotRequired[SpeechToTextTranslateLanguage]
     """
-    Language code
+    Specifies the language of the input audio in BCP-47 format.
+    **Available Options:**
+    - `unknown` (default): 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
     """
     model: typing_extensions.NotRequired[SpeechToTextModel]
     """
     Model to be used for speech to text.
-    - **saarika:v2.5** (default)
-    - **saarika:v3**: Advanced transcription model
-    - **saaras:v3**: Advanced model with multiple modes
+    - **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_extensions.NotRequired[Mode]
     """
-    Mode of operation. Only applicable for saaras:v3 model.
+    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`
     """
     with_timestamps: typing_extensions.NotRequired[bool]

sarvamai/requests/speech_to_text_translate_job_parameters.py CHANGED Viewed

@@ -12,7 +12,10 @@ class SpeechToTextTranslateJobParametersParams(typing_extensions.TypedDict):
     model: typing_extensions.NotRequired[SpeechToTextTranslateModel]
     """
-    Model to be used for converting speech to text in target language
+    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
     """
     with_diarization: typing_extensions.NotRequired[bool]

sarvamai/speech_to_text/client.py CHANGED Viewed

@@ -65,23 +65,49 @@ class SpeechToTextClient:
         model : typing.Optional[SpeechToTextModel]
             Specifies the model to use for speech-to-text conversion.
-            - **saarika:v2.5** (default): Standard transcription model
-            - **saarika:v3**: Advanced transcription model
-            - **saaras:v3**: Advanced model with multiple output modes
+            - **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.**
-            - **transcribe** (default): Standard transcription
-            - **translate**: Translation to English
-            - **indic-en**: Indic to English translation
-            - **verbatim**: Exact transcription
-            - **translit**: Transliteration to Latin script
-            - **codemix**: Code-mixed output
+            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.
-             For the `saarika:v2.5` model, it is optional.
-            `unknown`: Use this when the language is not known; the API will detect it automatically.
+            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
         input_audio_codec : typing.Optional[InputAudioCodec]
             Input Audio codec/format of the input file. PCM files are supported only at 16kHz sample rate.
@@ -146,7 +172,10 @@ class SpeechToTextClient:
             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 converting speech to text in target language
+            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.
@@ -221,23 +250,49 @@ class AsyncSpeechToTextClient:
         model : typing.Optional[SpeechToTextModel]
             Specifies the model to use for speech-to-text conversion.
-            - **saarika:v2.5** (default): Standard transcription model
-            - **saarika:v3**: Advanced transcription model
-            - **saaras:v3**: Advanced model with multiple output modes
+            - **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.**
-            - **transcribe** (default): Standard transcription
-            - **translate**: Translation to English
-            - **indic-en**: Indic to English translation
-            - **verbatim**: Exact transcription
-            - **translit**: Transliteration to Latin script
-            - **codemix**: Code-mixed output
+            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.
-             For the `saarika:v2.5` model, it is optional.
-            `unknown`: Use this when the language is not known; the API will detect it automatically.
+            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
         input_audio_codec : typing.Optional[InputAudioCodec]
             Input Audio codec/format of the input file. PCM files are supported only at 16kHz sample rate.
@@ -310,7 +365,10 @@ class AsyncSpeechToTextClient:
             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 converting speech to text in target language
+            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.

sarvamai/speech_to_text/raw_client.py CHANGED Viewed

@@ -63,23 +63,49 @@ class RawSpeechToTextClient:
         model : typing.Optional[SpeechToTextModel]
             Specifies the model to use for speech-to-text conversion.
-            - **saarika:v2.5** (default): Standard transcription model
-            - **saarika:v3**: Advanced transcription model
-            - **saaras:v3**: Advanced model with multiple output modes
+            - **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.**
-            - **transcribe** (default): Standard transcription
-            - **translate**: Translation to English
-            - **indic-en**: Indic to English translation
-            - **verbatim**: Exact transcription
-            - **translit**: Transliteration to Latin script
-            - **codemix**: Code-mixed output
+            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.
-             For the `saarika:v2.5` model, it is optional.
-            `unknown`: Use this when the language is not known; the API will detect it automatically.
+            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
         input_audio_codec : typing.Optional[InputAudioCodec]
             Input Audio codec/format of the input file. PCM files are supported only at 16kHz sample rate.
@@ -223,7 +249,10 @@ class RawSpeechToTextClient:
             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 converting speech to text in target language
+            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.
@@ -370,23 +399,49 @@ class AsyncRawSpeechToTextClient:
         model : typing.Optional[SpeechToTextModel]
             Specifies the model to use for speech-to-text conversion.
-            - **saarika:v2.5** (default): Standard transcription model
-            - **saarika:v3**: Advanced transcription model
-            - **saaras:v3**: Advanced model with multiple output modes
+            - **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.**
-            - **transcribe** (default): Standard transcription
-            - **translate**: Translation to English
-            - **indic-en**: Indic to English translation
-            - **verbatim**: Exact transcription
-            - **translit**: Transliteration to Latin script
-            - **codemix**: Code-mixed output
+            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.
-             For the `saarika:v2.5` model, it is optional.
-            `unknown`: Use this when the language is not known; the API will detect it automatically.
+            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
         input_audio_codec : typing.Optional[InputAudioCodec]
             Input Audio codec/format of the input file. PCM files are supported only at 16kHz sample rate.
@@ -530,7 +585,10 @@ class AsyncRawSpeechToTextClient:
             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 converting speech to text in target language
+            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.

sarvamai/speech_to_text_streaming/client.py CHANGED Viewed

@@ -63,19 +63,47 @@ class SpeechToTextStreamingClient:
         Parameters
         ----------
         language_code : SpeechToTextStreamingLanguageCode
-            Language code for speech recognition (BCP-47 format)
+            Specifies the language of the input audio in BCP-47 format.
+            **Available Options:**
+            - `hi-IN`: Hindi
+            - `bn-IN`: Bengali
+            - `gu-IN`: Gujarati
+            - `kn-IN`: Kannada
+            - `ml-IN`: Malayalam
+            - `mr-IN`: Marathi
+            - `od-IN`: Odia
+            - `pa-IN`: Punjabi
+            - `ta-IN`: Tamil
+            - `te-IN`: Telugu
+            - `en-IN`: English
         model : typing.Optional[SpeechToTextStreamingModel]
-            Speech to text model to use
+            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[SpeechToTextStreamingMode]
-            Mode of operation for saaras:v3 model. Only applicable when model is 'saaras:v3'.
-            - transcribe: Standard Whisper transcription
-            - translate: Standard Whisper translation to English
-            - indic-en: Translate Indic languages to English
-            - verbatim: Exact transcription in original script
-            - translit: Transliteration to Latin script
-            - codemix: Code-mixed output (native + English)
+            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`
         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.
@@ -178,19 +206,47 @@ class AsyncSpeechToTextStreamingClient:
         Parameters
         ----------
         language_code : SpeechToTextStreamingLanguageCode
-            Language code for speech recognition (BCP-47 format)
+            Specifies the language of the input audio in BCP-47 format.
+            **Available Options:**
+            - `hi-IN`: Hindi
+            - `bn-IN`: Bengali
+            - `gu-IN`: Gujarati
+            - `kn-IN`: Kannada
+            - `ml-IN`: Malayalam
+            - `mr-IN`: Marathi
+            - `od-IN`: Odia
+            - `pa-IN`: Punjabi
+            - `ta-IN`: Tamil
+            - `te-IN`: Telugu
+            - `en-IN`: English
         model : typing.Optional[SpeechToTextStreamingModel]
-            Speech to text model to use
+            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[SpeechToTextStreamingMode]
-            Mode of operation for saaras:v3 model. Only applicable when model is 'saaras:v3'.
-            - transcribe: Standard Whisper transcription
-            - translate: Standard Whisper translation to English
-            - indic-en: Translate Indic languages to English
-            - verbatim: Exact transcription in original script
-            - translit: Transliteration to Latin script
-            - codemix: Code-mixed output (native + English)
+            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`
         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.

sarvamai/speech_to_text_streaming/raw_client.py CHANGED Viewed

@@ -51,19 +51,47 @@ class RawSpeechToTextStreamingClient:
         Parameters
         ----------
         language_code : SpeechToTextStreamingLanguageCode
-            Language code for speech recognition (BCP-47 format)
+            Specifies the language of the input audio in BCP-47 format.
+            **Available Options:**
+            - `hi-IN`: Hindi
+            - `bn-IN`: Bengali
+            - `gu-IN`: Gujarati
+            - `kn-IN`: Kannada
+            - `ml-IN`: Malayalam
+            - `mr-IN`: Marathi
+            - `od-IN`: Odia
+            - `pa-IN`: Punjabi
+            - `ta-IN`: Tamil
+            - `te-IN`: Telugu
+            - `en-IN`: English
         model : typing.Optional[SpeechToTextStreamingModel]
-            Speech to text model to use
+            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[SpeechToTextStreamingMode]
-            Mode of operation for saaras:v3 model. Only applicable when model is 'saaras:v3'.
-            - transcribe: Standard Whisper transcription
-            - translate: Standard Whisper translation to English
-            - indic-en: Translate Indic languages to English
-            - verbatim: Exact transcription in original script
-            - translit: Transliteration to Latin script
-            - codemix: Code-mixed output (native + English)
+            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`
         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.
@@ -155,19 +183,47 @@ class AsyncRawSpeechToTextStreamingClient:
         Parameters
         ----------
         language_code : SpeechToTextStreamingLanguageCode
-            Language code for speech recognition (BCP-47 format)
+            Specifies the language of the input audio in BCP-47 format.
+            **Available Options:**
+            - `hi-IN`: Hindi
+            - `bn-IN`: Bengali
+            - `gu-IN`: Gujarati
+            - `kn-IN`: Kannada
+            - `ml-IN`: Malayalam
+            - `mr-IN`: Marathi
+            - `od-IN`: Odia
+            - `pa-IN`: Punjabi
+            - `ta-IN`: Tamil
+            - `te-IN`: Telugu
+            - `en-IN`: English
         model : typing.Optional[SpeechToTextStreamingModel]
-            Speech to text model to use
+            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[SpeechToTextStreamingMode]
-            Mode of operation for saaras:v3 model. Only applicable when model is 'saaras:v3'.
-            - transcribe: Standard Whisper transcription
-            - translate: Standard Whisper translation to English
-            - indic-en: Translate Indic languages to English
-            - verbatim: Exact transcription in original script
-            - translit: Transliteration to Latin script
-            - codemix: Code-mixed output (native + English)
+            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`
         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.

sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_mode.py CHANGED Viewed

@@ -3,5 +3,5 @@
 import typing
 SpeechToTextStreamingMode = typing.Union[
-    typing.Literal["transcribe", "translate", "indic-en", "verbatim", "translit", "codemix"], typing.Any
+    typing.Literal["transcribe", "translate", "verbatim", "translit", "codemix"], typing.Any
 ]

sarvamai/speech_to_text_translate_streaming/client.py CHANGED Viewed

@@ -60,7 +60,10 @@ 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.
+            - **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.
@@ -157,7 +160,10 @@ 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.
+            - **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.

sarvamai/speech_to_text_translate_streaming/raw_client.py CHANGED Viewed

@@ -48,7 +48,10 @@ 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.
+            - **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.
@@ -134,7 +137,10 @@ 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.
+            - **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.

sarvamai/types/mode.py CHANGED Viewed

@@ -2,6 +2,4 @@
 import typing
-Mode = typing.Union[
-    typing.Literal["transcribe", "translate", "indic-en", "verbatim", "translit", "codemix"], typing.Any
-]
+Mode = typing.Union[typing.Literal["transcribe", "translate", "verbatim", "translit", "codemix"], typing.Any]

sarvamai/types/speech_to_text_job_parameters.py CHANGED Viewed

@@ -12,20 +12,52 @@ from .speech_to_text_translate_language import SpeechToTextTranslateLanguage
 class SpeechToTextJobParameters(UniversalBaseModel):
     language_code: typing.Optional[SpeechToTextTranslateLanguage] = pydantic.Field(default=None)
     """
-    Language code
+    Specifies the language of the input audio in BCP-47 format.
+    **Available Options:**
+    - `unknown` (default): 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
     """
     model: typing.Optional[SpeechToTextModel] = pydantic.Field(default=None)
     """
     Model to be used for speech to text.
-    - **saarika:v2.5** (default)
-    - **saarika:v3**: Advanced transcription model
-    - **saaras:v3**: Advanced model with multiple modes
+    - **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] = pydantic.Field(default=None)
     """
-    Mode of operation. Only applicable for saaras:v3 model.
+    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`
     """
     with_timestamps: typing.Optional[bool] = pydantic.Field(default=None)

sarvamai/types/speech_to_text_model.py CHANGED Viewed

@@ -2,6 +2,4 @@
 import typing
-SpeechToTextModel = typing.Union[
-    typing.Literal["saarika:v2.5", "saarika:v1", "saarika:v2", "saarika:flash", "saaras:v3"], typing.Any
-]
+SpeechToTextModel = typing.Union[typing.Literal["saarika:v2.5", "saaras:v3"], typing.Any]

sarvamai/types/speech_to_text_translate_job_parameters.py CHANGED Viewed

@@ -15,7 +15,10 @@ class SpeechToTextTranslateJobParameters(UniversalBaseModel):
     model: typing.Optional[SpeechToTextTranslateModel] = pydantic.Field(default=None)
     """
-    Model to be used for converting speech to text in target language
+    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
     """
     with_diarization: typing.Optional[bool] = pydantic.Field(default=None)

sarvamai/types/speech_to_text_translate_model.py CHANGED Viewed

@@ -2,4 +2,4 @@
 import typing
-SpeechToTextTranslateModel = typing.Union[typing.Literal["saaras:v2.5", "saaras:v3"], typing.Any]
+SpeechToTextTranslateModel = typing.Literal["saaras:v2.5"]

{sarvamai-0.1.23a4.dist-info → sarvamai-0.1.23a5.dist-info}/METADATA RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sarvamai
-Version: 0.1.23a4
+Version: 0.1.23a5
 Summary:
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{sarvamai-0.1.23a4.dist-info → sarvamai-0.1.23a5.dist-info}/RECORD RENAMED Viewed

@@ -5,7 +5,7 @@ sarvamai/chat/raw_client.py,sha256=A2kRuZcVWlJhyYCD7YKgqNkZEp3cYa1731KhRkhirU0,1
 sarvamai/client.py,sha256=J30X_os1lPf8Wml0KDFEf6p8VGHhgF_lf3nw1T2D3qo,8207
 sarvamai/core/__init__.py,sha256=YE2CtXeASe1RAbaI39twKWYKCuT4tW5is9HWHhJjR_g,1653
 sarvamai/core/api_error.py,sha256=44vPoTyWN59gonCIZMdzw7M1uspygiLnr3GNFOoVL2Q,614
-sarvamai/core/client_wrapper.py,sha256=bEnbr4OmkyHdmJbqD-Hw3UlyjXlCyoV_Uc6OzqGk6u4,2570
+sarvamai/core/client_wrapper.py,sha256=xycjM0SER509jhTOV9GZTxV42go3HQOVrskOdattRwM,2570
 sarvamai/core/datetime_utils.py,sha256=nBys2IsYrhPdszxGKCNRPSOCwa-5DWOHG95FB8G9PKo,1047
 sarvamai/core/events.py,sha256=HvKBdSoYcFetk7cgNXb7FxuY-FtY8NtUhZIN7mGVx8U,1159
 sarvamai/core/file.py,sha256=d4NNbX8XvXP32z8KpK2Xovv33nFfruIrpz0QWxlgpZk,2663
@@ -67,12 +67,12 @@ sarvamai/requests/language_identification_response.py,sha256=BdS5U9Gic-71vb--ph6
 sarvamai/requests/ping_signal.py,sha256=TSgmfz2k4X1L6TzvX8u2SKZ6XQY3bSf7nPZf8mUViaM,343
 sarvamai/requests/send_text.py,sha256=DWzbNgeNN2xSIYgk2zEisgLqjwq5oleqJVHrtOnIqbE,267
 sarvamai/requests/send_text_data.py,sha256=2jds-xd77u-YTgIWQsTUBKE-_7tsrFshXXuC_Ld4ULo,161
-sarvamai/requests/speech_to_text_job_parameters.py,sha256=QxiiqhjL58mw8nw6SjxuM-221OrlIPF8wWhom5rS_T8,1303
+sarvamai/requests/speech_to_text_job_parameters.py,sha256=C1dpp5IkylFXdSNfKDhSo8jbFUquFh3SURFVME9XXq4,2854
 sarvamai/requests/speech_to_text_response.py,sha256=GS3jNmHDOxqNZ7cvftD62khUMSBIQUu6zEPdCqk8zJk,1041
 sarvamai/requests/speech_to_text_response_data.py,sha256=69fYRdL0tCKpgKQqwzcM4T4Nf_lRxJFh-VCFe_tN964,364
 sarvamai/requests/speech_to_text_streaming_response.py,sha256=cN5tKE9wOWuyBna4wmrf-0LfkOULMpRaJ7qjLuu76V0,348
 sarvamai/requests/speech_to_text_transcription_data.py,sha256=Vc65hXDq65d14cP-fDJm151bi7XEKgPItNGt1UL6cOY,877
-sarvamai/requests/speech_to_text_translate_job_parameters.py,sha256=Cco38i8IhX00S2eW3MhLekqUFMS7hZW2AwbpWyCAgpU,990
+sarvamai/requests/speech_to_text_translate_job_parameters.py,sha256=Q1mL3ul3WYArryp-HP_wHc8WCTLq6ZFhCUFeH3NM80E,1147
 sarvamai/requests/speech_to_text_translate_response.py,sha256=xLV2F37PkGR0erRDfTBEPWvywR8eVSL9JbH5a0C9wkY,893
 sarvamai/requests/speech_to_text_translate_response_data.py,sha256=OmjunP9R2xertJKn4fmpyzjDdj1_B_Yh6ZjH1eOlR-Q,407
 sarvamai/requests/speech_to_text_translate_streaming_response.py,sha256=KTjYZ0_oLapuM5Iiq7UwejMsrL1TGgFAW4k5l17TkZs,385
@@ -87,21 +87,21 @@ sarvamai/requests/transcription_metrics.py,sha256=FDclX2Z9Z3azrDXxtZW8xbkxxWMZQX
 sarvamai/requests/translation_response.py,sha256=8iwQeZB1purHY757bIQI-n9QeVRBItaAVcBJ_la-k1Y,414
 sarvamai/requests/transliteration_response.py,sha256=KqRkqnegLmt7LjdVxjRePX6RoqaLm64KFGZ6q7mXyfw,426
 sarvamai/speech_to_text/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
-sarvamai/speech_to_text/client.py,sha256=3RxDjOGAWeb_sfSg6hbeQw5qIU98zDsZs1GHrqpT8jA,13741
-sarvamai/speech_to_text/raw_client.py,sha256=rhs_5Td7aKLapSTut4DFL6fhtAsYcOalrJt7KGNnioQ,28039
+sarvamai/speech_to_text/client.py,sha256=K9lb57rQRfYwwAonj7BSP9aKI7io_fXhjn79M-Brwag,16483
+sarvamai/speech_to_text/raw_client.py,sha256=Rw0x9ipXFWs6xF4aly4DgIN9tqdPZyLz5Powg2ZnQkA,30781
 sarvamai/speech_to_text_job/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
 sarvamai/speech_to_text_job/client.py,sha256=nMhBJa1rf1qQdQhlB1WUtyzOGhsWxECCPAJwBvWnq8M,18930
 sarvamai/speech_to_text_job/job.py,sha256=9AfVSp5nzrl-Cx_1n2AJZqTMzp6Dkz2cvmbdq78fCgM,18751
 sarvamai/speech_to_text_job/raw_client.py,sha256=6MB82mSqAOi92mE8vUeNSTB0wuxLZYRwizt15R6r-wo,49394
 sarvamai/speech_to_text_streaming/__init__.py,sha256=5l81Q5goyVA8oC5cKaS9-Hv4_PR2nYC318VcmaUTpg8,579
-sarvamai/speech_to_text_streaming/client.py,sha256=F8j1DALzxClbE1FRPqF5JQwRn6StOuHCuymGItXI1JI,12063
-sarvamai/speech_to_text_streaming/raw_client.py,sha256=5sWz5b0JpnvsDaszdg-foGOvKa_x_OqKE7O3yo1ESfI,11244
+sarvamai/speech_to_text_streaming/client.py,sha256=KiJEcJuHYc7bfbOXIBOEras0KjM2zhgVYo4lUK4Hlek,14801
+sarvamai/speech_to_text_streaming/raw_client.py,sha256=QzC3ytldXbH6b5-tpPT7tmie5VhaXSGd0J1RbvspnaY,13982
 sarvamai/speech_to_text_streaming/socket_client.py,sha256=P6qXRN0s3UFAp6CP5lkqrW2KPK9me70ZVfWquxLB4wI,7538
 sarvamai/speech_to_text_streaming/types/__init__.py,sha256=M6FNnzx7E98J7AzP2oU_94qVsWoxaYZG9_Syc5p5qQg,825
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_flush_signal.py,sha256=dDJOBlzAjhuiSVqW2RHHY1f6xy0DU_Yoo9UV8-7MjnA,173
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_high_vad_sensitivity.py,sha256=OwPwffa8TkLPGMnOTn5S7d-HmV8QmN3B7fHz8I1-VT8,180
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_language_code.py,sha256=LxgEifmgWTCFZn9U-f-TWKxRPng3a2J26Zt526QrA0Y,267
-sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_mode.py,sha256=ughojb-xTiqiV-PnzAWyl6t9zSfIjFTdPa_b6XwLsHQ,229
+sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_mode.py,sha256=jce75h2M9dEMD_eC29zCLQZFbLfCy8sdxEIISxtfubQ,217
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_model.py,sha256=CpWC1HmcPJKWCSHhTYSaC8_pMsfNTBA-EHq-sfCjS-A,179
 sarvamai/speech_to_text_streaming/types/speech_to_text_streaming_vad_signals.py,sha256=8wiFOB7WDMbYCcMTYgNFJaIjEytYeXpJLwr_O_mH0TI,172
 sarvamai/speech_to_text_translate_job/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
@@ -109,8 +109,8 @@ sarvamai/speech_to_text_translate_job/client.py,sha256=xu8kYtCESDB7LzL8YKBUq5qhT
 sarvamai/speech_to_text_translate_job/job.py,sha256=tL1Zemsogb_AK9wqZwN4ooPaN176sFKduTH9g87y-WU,18938
 sarvamai/speech_to_text_translate_job/raw_client.py,sha256=Emx14cRiAZXg1PqZkoJbDOKwyDmOgwxWlqPkAPZ9GPU,50797
 sarvamai/speech_to_text_translate_streaming/__init__.py,sha256=HYq3MzUyWa4Kt1ou6vgAkbMCHoIcXzoqn6V1kya5c6g,423
-sarvamai/speech_to_text_translate_streaming/client.py,sha256=bQ2T3frXMQe8-L42zEQf-zPcHpnL7mVWPyMxcMp59cw,10433
-sarvamai/speech_to_text_translate_streaming/raw_client.py,sha256=j-SxOkqchXIbOIBKvaEPAzOCYw4aXrLcS073OMhNS0c,9542
+sarvamai/speech_to_text_translate_streaming/client.py,sha256=wFAn-mrcOUFFa5sAgjSkAx9OZiTNbQvyJwBlid3hJP8,10757
+sarvamai/speech_to_text_translate_streaming/raw_client.py,sha256=jDUuPdYWeh-sxeNHdEzLeMaAyCKJZDz-5mrVRUPoFZU,9866
 sarvamai/speech_to_text_translate_streaming/socket_client.py,sha256=ipEPSj5eHAyDpuEXfaP7JJL1rXJXGEo-IB888ReAFKs,8901
 sarvamai/speech_to_text_translate_streaming/types/__init__.py,sha256=NFfpVz1gILXj96rWMFw4MgSpni0Yvs8CHgwJ9Xry7OU,575
 sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_flush_signal.py,sha256=jkjvCGJ1pFKi3AOTkwMW-lo18WGgrgAhMpoe5P0AMzA,182
@@ -177,7 +177,7 @@ sarvamai/types/input_audio_codec.py,sha256=P3rz6lg-T34E7psQ1DX4e2yvPxVJDDsMVn4TS
 sarvamai/types/job_state.py,sha256=H6Zph2mIcjsd3upEDt1VzIEORkEpnIDs0kH8BvIyrow,189
 sarvamai/types/job_status_v_1_response.py,sha256=jusn-3XLCk8vCnu3q3GGSzz_yYgKB5PY_01Q32-1aJk,1605
 sarvamai/types/language_identification_response.py,sha256=jG4ZQ6KQHCiEDqC51OniOwiRdW14Fbz22bbTsUDp_kc,1483
-sarvamai/types/mode.py,sha256=Va8CxtXqSt-aVtKOlIyR_o7IuHYnhGPQy9-MwlgcOLg,208
+sarvamai/types/mode.py,sha256=ENoXfbrT2rt9ClT6QHC3xQHiSJwM0Q0dZK5iEKJp41k,190
 sarvamai/types/numerals_format.py,sha256=xg3lYiHcnzyFwuwRcaIteJLH_Pz6pJ9n9kTlYPEnCBU,165
 sarvamai/types/ping_signal.py,sha256=cE53FRIXlc8bSo18z6jlAnOh6DhZEMX36huWEX6X3-A,695
 sarvamai/types/reasoning_effort.py,sha256=_TBLn3rQgzJAdnKqV2g0PETbrSBZl0fPLfQ5ZE9H4Pc,164
@@ -187,16 +187,16 @@ sarvamai/types/sarvam_model_ids.py,sha256=iYBMglf31KQ1iUZeAMQ-2PP9NDcyHRG7goz7O9
 sarvamai/types/send_text.py,sha256=kgST6V5NuURzgBpuiDi8fVwDg768ttDoeY9k1dSSb1Y,607
 sarvamai/types/send_text_data.py,sha256=H8yfcvd4gvyN34RrZ9i4qQvieednNBhL7i7isX4asuY,519
 sarvamai/types/speech_sample_rate.py,sha256=Hfi79KL2Y1W7OIvvrfWnt7EUvmU5i7bxYvXivrY_aUA,88
-sarvamai/types/speech_to_text_job_parameters.py,sha256=k96J4a9hzkTs50qz30GKy4nTN7uswQomCll1AThhUAw,1742
+sarvamai/types/speech_to_text_job_parameters.py,sha256=JFKO2rIyBJE_PK4mrMMwY4e562l_6HbZtP2kd4CbKa8,3293
 sarvamai/types/speech_to_text_language.py,sha256=cq8FBOX0DfYB3v8jgNteQtHeJcqWqzKWJVyYGwwo_w0,279
-sarvamai/types/speech_to_text_model.py,sha256=PQCoWUNBAhFslY69Zh2-6HFbBA6m683cu0JT8A_LYo0,221
+sarvamai/types/speech_to_text_model.py,sha256=hHC3aOXzdPt8i32qJw4ZLz5bdREWVQl4P7Y_lOURJu4,170
 sarvamai/types/speech_to_text_response.py,sha256=iWRGEJeHUFIOxeEhoCQu68njeA6lcqXbT2czV-O8Wx0,1438
 sarvamai/types/speech_to_text_response_data.py,sha256=gbxZTBSjbN3ZIa10K6tWPYtymcpnQTFIaUnXkOmsmD4,322
 sarvamai/types/speech_to_text_streaming_response.py,sha256=z6tVAHbVK9lC3w3lac__LEUfO8AAzEilkeGlaLskTtc,687
 sarvamai/types/speech_to_text_transcription_data.py,sha256=EqwPAPSi98PwARaTj-ufzFUSHyN-NPoPla5vi_KERrU,1297
-sarvamai/types/speech_to_text_translate_job_parameters.py,sha256=fvfcyzIyT0DtcRYePDvglHH-wAhGbsi3H5G4i5nuWT8,1409
+sarvamai/types/speech_to_text_translate_job_parameters.py,sha256=-E85BoIBxW5Ck638aRFE0fC_f43RCoIkboAFu2QlBBs,1566
 sarvamai/types/speech_to_text_translate_language.py,sha256=yikNM-roIumVG-eqBWss93wLGudZdLPwd0i3VcXH5zo,263
-sarvamai/types/speech_to_text_translate_model.py,sha256=8ZdAFjquozAkAxfyHQUyS0Hu2IEpGG2P5tFG-COYuxU,178
+sarvamai/types/speech_to_text_translate_model.py,sha256=CVSz6gJBY82GhhEuWSdzRLJW9XTsAgweRnKd1tN6mXo,139
 sarvamai/types/speech_to_text_translate_response.py,sha256=Z5Na7IQW2ok3TP21xd-jKkwioplEKfonNIMhoJQKkVw,1278
 sarvamai/types/speech_to_text_translate_response_data.py,sha256=_NlLVp7oQU3em_4E47QVbIP9nromPE07Z9HtMpY1lrU,359
 sarvamai/types/speech_to_text_translate_streaming_response.py,sha256=J6h3AGdAJxpODFs30bR-e6OaWKa__oVhwv_TrbPSO98,724
@@ -226,6 +226,6 @@ sarvamai/types/transliterate_mode.py,sha256=1jSEMlGcoLkWuk12TgoOpSgwifa4rThGKZ1h
 sarvamai/types/transliterate_source_language.py,sha256=bSY9wJszF0sg-Cgg6F-YcWC8ly1mIlj9rqa15-jBtx8,283
 sarvamai/types/transliteration_response.py,sha256=yt-lzTbDeJ_ZL4I8kQa6oESxA9ebeJJY7LfFHpdEsmM,815
 sarvamai/version.py,sha256=Qkp3Ee9YH-O9RTix90e0i7iNrFAGN-QDt2AFwGA4n8k,75
-sarvamai-0.1.23a4.dist-info/METADATA,sha256=mbfbKrGLegxZadUzXb9zLW9Xll7DYTEfefhtHanA-1I,26753
-sarvamai-0.1.23a4.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
-sarvamai-0.1.23a4.dist-info/RECORD,,
+sarvamai-0.1.23a5.dist-info/METADATA,sha256=nPZ4wzgXrEkNFWPm-2mlOxCW4n4xIFhbBehaDWxkTiE,26753
+sarvamai-0.1.23a5.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+sarvamai-0.1.23a5.dist-info/RECORD,,

{sarvamai-0.1.23a4.dist-info → sarvamai-0.1.23a5.dist-info}/WHEEL RENAMED Viewed

File without changes

sarvamai 0.1.23a4__py3-none-any.whl → 0.1.23a5__py3-none-any.whl

sarvamai 0.1.23a4py3-none-any.whl → 0.1.23a5py3-none-any.whl