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

sarvamai/text/raw_client.py

@@ -44,7 +44,6 @@ class RawTextClient:
         speaker_gender: typing.Optional[TranslateSpeakerGender] = OMIT,
         mode: typing.Optional[TranslateMode] = OMIT,
         model: typing.Optional[TranslateModel] = OMIT,
-        enable_preprocessing: typing.Optional[bool] = OMIT,
         output_script: typing.Optional[TransliterateMode] = OMIT,
         numerals_format: typing.Optional[NumeralsFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
@@ -122,10 +121,6 @@ class RawTextClient:
             - mayura:v1: Supports 12 languages with all modes, output scripts, and automatic language detection.
             - sarvam-translate:v1: Supports all 22 scheduled languages of India, formal mode only.
 
-        enable_preprocessing : typing.Optional[bool]
-            This will enable custom preprocessing of the input text which can result in better translations.
-             Recommendation- You can switch on whenever there is some complex text with difficult vocabulary and sentences, for which you want simple translations that people can understand.
-
         output_script : typing.Optional[TransliterateMode]
             **output_script**: This is an optional parameter which controls the transliteration style applied to the output text.
 
@@ -174,7 +169,6 @@ class RawTextClient:
                 "speaker_gender": speaker_gender,
                 "mode": mode,
                 "model": model,
-                "enable_preprocessing": enable_preprocessing,
                 "output_script": output_script,
                 "numerals_format": numerals_format,
             },
@@ -554,7 +548,6 @@ class AsyncRawTextClient:
         speaker_gender: typing.Optional[TranslateSpeakerGender] = OMIT,
         mode: typing.Optional[TranslateMode] = OMIT,
         model: typing.Optional[TranslateModel] = OMIT,
-        enable_preprocessing: typing.Optional[bool] = OMIT,
         output_script: typing.Optional[TransliterateMode] = OMIT,
         numerals_format: typing.Optional[NumeralsFormat] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
@@ -632,10 +625,6 @@ class AsyncRawTextClient:
             - mayura:v1: Supports 12 languages with all modes, output scripts, and automatic language detection.
             - sarvam-translate:v1: Supports all 22 scheduled languages of India, formal mode only.
 
-        enable_preprocessing : typing.Optional[bool]
-            This will enable custom preprocessing of the input text which can result in better translations.
-             Recommendation- You can switch on whenever there is some complex text with difficult vocabulary and sentences, for which you want simple translations that people can understand.
-
         output_script : typing.Optional[TransliterateMode]
             **output_script**: This is an optional parameter which controls the transliteration style applied to the output text.
 
@@ -684,7 +673,6 @@ class AsyncRawTextClient:
                 "speaker_gender": speaker_gender,
                 "mode": mode,
                 "model": model,
-                "enable_preprocessing": enable_preprocessing,
                 "output_script": output_script,
                 "numerals_format": numerals_format,
             },

sarvamai/text_to_speech/client.py

@@ -44,15 +44,38 @@ class TextToSpeechClient:
         enable_preprocessing: typing.Optional[bool] = OMIT,
         model: typing.Optional[TextToSpeechModel] = OMIT,
         output_audio_codec: typing.Optional[TextToSpeechOutputAudioCodec] = OMIT,
+        temperature: typing.Optional[float] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> TextToSpeechResponse:
         """
-        This is the model to convert text into spoken audio.
-        The output is a wave file encoded as a base64 string.
+        Convert text into spoken audio. The output is a wave file encoded as a base64 string.
+
+        **Available Models:**
+        - **bulbul:v2** (default): Supports pitch, loudness, and pace controls
+        - **bulbul:v3-beta**: Newer model with temperature control and improved quality
+
+        **Important Notes for bulbul:v3-beta:**
+        - Pitch and loudness parameters are NOT supported
+        - Pace must be between 0.5 and 2.0
+        - Preprocessing is automatically enabled
+        - Default sample rate is 24000 Hz
+        - Temperature parameter available (0.01-1.0, default 0.6)
 
         Parameters
         ----------
         text : str
+            The text(s) to be converted into speech.
+
+            **Features:**
+            - Supports code-mixed text (English and Indic languages)
+
+            **Model-specific limits:**
+            - **bulbul:v2:** Max 1500 characters
+            - **bulbul:v3-beta:** Max 2500 characters
+
+            **Important Note:**
+            - For numbers larger than 4 digits, use commas (e.g., '10,000' instead of '10000')
+            - This ensures proper pronunciation as a whole number
 
         target_language_code : TextToSpeechLanguage
             The language of the text is BCP-47 format
@@ -60,36 +83,63 @@ class TextToSpeechClient:
         speaker : typing.Optional[TextToSpeechSpeaker]
             The speaker voice to be used for the output audio.
 
-            **Default:** Anushka
+            **Default:** Anushka (for bulbul:v2), Aditya (for bulbul:v3-beta)
 
             **Model Compatibility (Speakers compatible with respective model):**
             - **bulbul:v2:**
               - Female: Anushka, Manisha, Vidya, Arya
               - Male: Abhilash, Karun, Hitesh
+            - **bulbul:v3-beta:**
+              - Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan, Shubh, Ashutosh, Advait, Amelia, Sophia
 
             **Note:** Speaker selection must match the chosen model version.
 
         pitch : typing.Optional[float]
             Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. The suitable range is between -0.75 and 0.75. Default is 0.0.
 
+            **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3-beta and will cause a validation error if provided.
+
         pace : typing.Optional[float]
-            Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. The suitable range is between 0.5 and 2.0. Default is 1.0.
+            Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. Default is 1.0.
+
+            **Model-specific ranges:**
+            - **bulbul:v2:** 0.3 to 3.0
+            - **bulbul:v3-beta:** 0.5 to 2.0
 
         loudness : typing.Optional[float]
             Controls the loudness of the audio. Lower values result in quieter audio, while higher values make it louder. The suitable range is between 0.3 and 3.0. Default is 1.0.
 
+            **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3-beta and will cause a validation error if provided.
+
         speech_sample_rate : typing.Optional[SpeechSampleRate]
-            Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+            Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz.
+
+            **Model-specific defaults:**
+            - **bulbul:v2:** Default is 22050 Hz
+            - **bulbul:v3-beta:** Default is 24000 Hz
 
         enable_preprocessing : typing.Optional[bool]
-             Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text. Default is false.
+            Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text.
+
+            **Model-specific behavior:**
+            - **bulbul:v2:** Default is false
+            - **bulbul:v3-beta:** Automatically enabled (true) and cannot be disabled
 
         model : typing.Optional[TextToSpeechModel]
-            Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
+            Specifies the model to use for text-to-speech conversion.
+
+            **Available models:**
+            - **bulbul:v2:** Default model with pitch, loudness controls
+            - **bulbul:v3-beta:** Newer model with temperature control, improved quality
 
         output_audio_codec : typing.Optional[TextToSpeechOutputAudioCodec]
             Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics.
 
+        temperature : typing.Optional[float]
+            Controls the randomness of the output. Lower values make the output more focused and deterministic, while higher values make it more random. The suitable range is between 0.01 and 1.0. Default is 0.6.
+
+            **Note:** This parameter is only supported for bulbul:v3-beta. It has no effect on bulbul:v2.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -121,6 +171,7 @@ class TextToSpeechClient:
             enable_preprocessing=enable_preprocessing,
             model=model,
             output_audio_codec=output_audio_codec,
+            temperature=temperature,
             request_options=request_options,
         )
         return _response.data
@@ -154,15 +205,38 @@ class AsyncTextToSpeechClient:
         enable_preprocessing: typing.Optional[bool] = OMIT,
         model: typing.Optional[TextToSpeechModel] = OMIT,
         output_audio_codec: typing.Optional[TextToSpeechOutputAudioCodec] = OMIT,
+        temperature: typing.Optional[float] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> TextToSpeechResponse:
         """
-        This is the model to convert text into spoken audio.
-        The output is a wave file encoded as a base64 string.
+        Convert text into spoken audio. The output is a wave file encoded as a base64 string.
+
+        **Available Models:**
+        - **bulbul:v2** (default): Supports pitch, loudness, and pace controls
+        - **bulbul:v3-beta**: Newer model with temperature control and improved quality
+
+        **Important Notes for bulbul:v3-beta:**
+        - Pitch and loudness parameters are NOT supported
+        - Pace must be between 0.5 and 2.0
+        - Preprocessing is automatically enabled
+        - Default sample rate is 24000 Hz
+        - Temperature parameter available (0.01-1.0, default 0.6)
 
         Parameters
         ----------
         text : str
+            The text(s) to be converted into speech.
+
+            **Features:**
+            - Supports code-mixed text (English and Indic languages)
+
+            **Model-specific limits:**
+            - **bulbul:v2:** Max 1500 characters
+            - **bulbul:v3-beta:** Max 2500 characters
+
+            **Important Note:**
+            - For numbers larger than 4 digits, use commas (e.g., '10,000' instead of '10000')
+            - This ensures proper pronunciation as a whole number
 
         target_language_code : TextToSpeechLanguage
             The language of the text is BCP-47 format
@@ -170,36 +244,63 @@ class AsyncTextToSpeechClient:
         speaker : typing.Optional[TextToSpeechSpeaker]
             The speaker voice to be used for the output audio.
 
-            **Default:** Anushka
+            **Default:** Anushka (for bulbul:v2), Aditya (for bulbul:v3-beta)
 
             **Model Compatibility (Speakers compatible with respective model):**
             - **bulbul:v2:**
               - Female: Anushka, Manisha, Vidya, Arya
               - Male: Abhilash, Karun, Hitesh
+            - **bulbul:v3-beta:**
+              - Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan, Shubh, Ashutosh, Advait, Amelia, Sophia
 
             **Note:** Speaker selection must match the chosen model version.
 
         pitch : typing.Optional[float]
             Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. The suitable range is between -0.75 and 0.75. Default is 0.0.
 
+            **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3-beta and will cause a validation error if provided.
+
         pace : typing.Optional[float]
-            Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. The suitable range is between 0.5 and 2.0. Default is 1.0.
+            Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. Default is 1.0.
+
+            **Model-specific ranges:**
+            - **bulbul:v2:** 0.3 to 3.0
+            - **bulbul:v3-beta:** 0.5 to 2.0
 
         loudness : typing.Optional[float]
             Controls the loudness of the audio. Lower values result in quieter audio, while higher values make it louder. The suitable range is between 0.3 and 3.0. Default is 1.0.
 
+            **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3-beta and will cause a validation error if provided.
+
         speech_sample_rate : typing.Optional[SpeechSampleRate]
-            Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+            Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz.
+
+            **Model-specific defaults:**
+            - **bulbul:v2:** Default is 22050 Hz
+            - **bulbul:v3-beta:** Default is 24000 Hz
 
         enable_preprocessing : typing.Optional[bool]
-             Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text. Default is false.
+            Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text.
+
+            **Model-specific behavior:**
+            - **bulbul:v2:** Default is false
+            - **bulbul:v3-beta:** Automatically enabled (true) and cannot be disabled
 
         model : typing.Optional[TextToSpeechModel]
-            Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
+            Specifies the model to use for text-to-speech conversion.
+
+            **Available models:**
+            - **bulbul:v2:** Default model with pitch, loudness controls
+            - **bulbul:v3-beta:** Newer model with temperature control, improved quality
 
         output_audio_codec : typing.Optional[TextToSpeechOutputAudioCodec]
             Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics.
 
+        temperature : typing.Optional[float]
+            Controls the randomness of the output. Lower values make the output more focused and deterministic, while higher values make it more random. The suitable range is between 0.01 and 1.0. Default is 0.6.
+
+            **Note:** This parameter is only supported for bulbul:v3-beta. It has no effect on bulbul:v2.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -239,6 +340,7 @@ class AsyncTextToSpeechClient:
             enable_preprocessing=enable_preprocessing,
             model=model,
             output_audio_codec=output_audio_codec,
+            temperature=temperature,
             request_options=request_options,
         )
         return _response.data

sarvamai/text_to_speech/raw_client.py

@@ -41,15 +41,38 @@ class RawTextToSpeechClient:
         enable_preprocessing: typing.Optional[bool] = OMIT,
         model: typing.Optional[TextToSpeechModel] = OMIT,
         output_audio_codec: typing.Optional[TextToSpeechOutputAudioCodec] = OMIT,
+        temperature: typing.Optional[float] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> HttpResponse[TextToSpeechResponse]:
         """
-        This is the model to convert text into spoken audio.
-        The output is a wave file encoded as a base64 string.
+        Convert text into spoken audio. The output is a wave file encoded as a base64 string.
+
+        **Available Models:**
+        - **bulbul:v2** (default): Supports pitch, loudness, and pace controls
+        - **bulbul:v3-beta**: Newer model with temperature control and improved quality
+
+        **Important Notes for bulbul:v3-beta:**
+        - Pitch and loudness parameters are NOT supported
+        - Pace must be between 0.5 and 2.0
+        - Preprocessing is automatically enabled
+        - Default sample rate is 24000 Hz
+        - Temperature parameter available (0.01-1.0, default 0.6)
 
         Parameters
         ----------
         text : str
+            The text(s) to be converted into speech.
+
+            **Features:**
+            - Supports code-mixed text (English and Indic languages)
+
+            **Model-specific limits:**
+            - **bulbul:v2:** Max 1500 characters
+            - **bulbul:v3-beta:** Max 2500 characters
+
+            **Important Note:**
+            - For numbers larger than 4 digits, use commas (e.g., '10,000' instead of '10000')
+            - This ensures proper pronunciation as a whole number
 
         target_language_code : TextToSpeechLanguage
             The language of the text is BCP-47 format
@@ -57,36 +80,63 @@ class RawTextToSpeechClient:
         speaker : typing.Optional[TextToSpeechSpeaker]
             The speaker voice to be used for the output audio.
 
-            **Default:** Anushka
+            **Default:** Anushka (for bulbul:v2), Aditya (for bulbul:v3-beta)
 
             **Model Compatibility (Speakers compatible with respective model):**
             - **bulbul:v2:**
               - Female: Anushka, Manisha, Vidya, Arya
               - Male: Abhilash, Karun, Hitesh
+            - **bulbul:v3-beta:**
+              - Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan, Shubh, Ashutosh, Advait, Amelia, Sophia
 
             **Note:** Speaker selection must match the chosen model version.
 
         pitch : typing.Optional[float]
             Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. The suitable range is between -0.75 and 0.75. Default is 0.0.
 
+            **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3-beta and will cause a validation error if provided.
+
         pace : typing.Optional[float]
-            Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. The suitable range is between 0.5 and 2.0. Default is 1.0.
+            Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. Default is 1.0.
+
+            **Model-specific ranges:**
+            - **bulbul:v2:** 0.3 to 3.0
+            - **bulbul:v3-beta:** 0.5 to 2.0
 
         loudness : typing.Optional[float]
             Controls the loudness of the audio. Lower values result in quieter audio, while higher values make it louder. The suitable range is between 0.3 and 3.0. Default is 1.0.
 
+            **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3-beta and will cause a validation error if provided.
+
         speech_sample_rate : typing.Optional[SpeechSampleRate]
-            Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+            Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz.
+
+            **Model-specific defaults:**
+            - **bulbul:v2:** Default is 22050 Hz
+            - **bulbul:v3-beta:** Default is 24000 Hz
 
         enable_preprocessing : typing.Optional[bool]
-             Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text. Default is false.
+            Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text.
+
+            **Model-specific behavior:**
+            - **bulbul:v2:** Default is false
+            - **bulbul:v3-beta:** Automatically enabled (true) and cannot be disabled
 
         model : typing.Optional[TextToSpeechModel]
-            Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
+            Specifies the model to use for text-to-speech conversion.
+
+            **Available models:**
+            - **bulbul:v2:** Default model with pitch, loudness controls
+            - **bulbul:v3-beta:** Newer model with temperature control, improved quality
 
         output_audio_codec : typing.Optional[TextToSpeechOutputAudioCodec]
             Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics.
 
+        temperature : typing.Optional[float]
+            Controls the randomness of the output. Lower values make the output more focused and deterministic, while higher values make it more random. The suitable range is between 0.01 and 1.0. Default is 0.6.
+
+            **Note:** This parameter is only supported for bulbul:v3-beta. It has no effect on bulbul:v2.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -110,6 +160,7 @@ class RawTextToSpeechClient:
                 "enable_preprocessing": enable_preprocessing,
                 "model": model,
                 "output_audio_codec": output_audio_codec,
+                "temperature": temperature,
             },
             headers={
                 "content-type": "application/json",
@@ -205,15 +256,38 @@ class AsyncRawTextToSpeechClient:
         enable_preprocessing: typing.Optional[bool] = OMIT,
         model: typing.Optional[TextToSpeechModel] = OMIT,
         output_audio_codec: typing.Optional[TextToSpeechOutputAudioCodec] = OMIT,
+        temperature: typing.Optional[float] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> AsyncHttpResponse[TextToSpeechResponse]:
         """
-        This is the model to convert text into spoken audio.
-        The output is a wave file encoded as a base64 string.
+        Convert text into spoken audio. The output is a wave file encoded as a base64 string.
+
+        **Available Models:**
+        - **bulbul:v2** (default): Supports pitch, loudness, and pace controls
+        - **bulbul:v3-beta**: Newer model with temperature control and improved quality
+
+        **Important Notes for bulbul:v3-beta:**
+        - Pitch and loudness parameters are NOT supported
+        - Pace must be between 0.5 and 2.0
+        - Preprocessing is automatically enabled
+        - Default sample rate is 24000 Hz
+        - Temperature parameter available (0.01-1.0, default 0.6)
 
         Parameters
         ----------
         text : str
+            The text(s) to be converted into speech.
+
+            **Features:**
+            - Supports code-mixed text (English and Indic languages)
+
+            **Model-specific limits:**
+            - **bulbul:v2:** Max 1500 characters
+            - **bulbul:v3-beta:** Max 2500 characters
+
+            **Important Note:**
+            - For numbers larger than 4 digits, use commas (e.g., '10,000' instead of '10000')
+            - This ensures proper pronunciation as a whole number
 
         target_language_code : TextToSpeechLanguage
             The language of the text is BCP-47 format
@@ -221,36 +295,63 @@ class AsyncRawTextToSpeechClient:
         speaker : typing.Optional[TextToSpeechSpeaker]
             The speaker voice to be used for the output audio.
 
-            **Default:** Anushka
+            **Default:** Anushka (for bulbul:v2), Aditya (for bulbul:v3-beta)
 
             **Model Compatibility (Speakers compatible with respective model):**
             - **bulbul:v2:**
               - Female: Anushka, Manisha, Vidya, Arya
               - Male: Abhilash, Karun, Hitesh
+            - **bulbul:v3-beta:**
+              - Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan, Shubh, Ashutosh, Advait, Amelia, Sophia
 
             **Note:** Speaker selection must match the chosen model version.
 
         pitch : typing.Optional[float]
             Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. The suitable range is between -0.75 and 0.75. Default is 0.0.
 
+            **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3-beta and will cause a validation error if provided.
+
         pace : typing.Optional[float]
-            Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. The suitable range is between 0.5 and 2.0. Default is 1.0.
+            Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. Default is 1.0.
+
+            **Model-specific ranges:**
+            - **bulbul:v2:** 0.3 to 3.0
+            - **bulbul:v3-beta:** 0.5 to 2.0
 
         loudness : typing.Optional[float]
             Controls the loudness of the audio. Lower values result in quieter audio, while higher values make it louder. The suitable range is between 0.3 and 3.0. Default is 1.0.
 
+            **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3-beta and will cause a validation error if provided.
+
         speech_sample_rate : typing.Optional[SpeechSampleRate]
-            Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz.
+            Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz.
+
+            **Model-specific defaults:**
+            - **bulbul:v2:** Default is 22050 Hz
+            - **bulbul:v3-beta:** Default is 24000 Hz
 
         enable_preprocessing : typing.Optional[bool]
-             Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text. Default is false.
+            Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text.
+
+            **Model-specific behavior:**
+            - **bulbul:v2:** Default is false
+            - **bulbul:v3-beta:** Automatically enabled (true) and cannot be disabled
 
         model : typing.Optional[TextToSpeechModel]
-            Specifies the model to use for text-to-speech conversion. Default is bulbul:v2.
+            Specifies the model to use for text-to-speech conversion.
+
+            **Available models:**
+            - **bulbul:v2:** Default model with pitch, loudness controls
+            - **bulbul:v3-beta:** Newer model with temperature control, improved quality
 
         output_audio_codec : typing.Optional[TextToSpeechOutputAudioCodec]
             Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics.
 
+        temperature : typing.Optional[float]
+            Controls the randomness of the output. Lower values make the output more focused and deterministic, while higher values make it more random. The suitable range is between 0.01 and 1.0. Default is 0.6.
+
+            **Note:** This parameter is only supported for bulbul:v3-beta. It has no effect on bulbul:v2.
+
         request_options : typing.Optional[RequestOptions]
             Request-specific configuration.
 
@@ -274,6 +375,7 @@ class AsyncRawTextToSpeechClient:
                 "enable_preprocessing": enable_preprocessing,
                 "model": model,
                 "output_audio_codec": output_audio_codec,
+                "temperature": temperature,
             },
             headers={
                 "content-type": "application/json",

sarvamai/text_to_speech_streaming/__init__.py

@@ -2,6 +2,6 @@
 
 # isort: skip_file
 
-from .types import TextToSpeechStreamingSendCompletionEvent
+from .types import TextToSpeechStreamingModel, TextToSpeechStreamingSendCompletionEvent
 
-__all__ = ["TextToSpeechStreamingSendCompletionEvent"]
+__all__ = ["TextToSpeechStreamingModel", "TextToSpeechStreamingSendCompletionEvent"]

sarvamai/text_to_speech_streaming/client.py

@@ -11,6 +11,7 @@ from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from .raw_client import AsyncRawTextToSpeechStreamingClient, RawTextToSpeechStreamingClient
 from .socket_client import AsyncTextToSpeechStreamingSocketClient, TextToSpeechStreamingSocketClient
+from .types.text_to_speech_streaming_model import TextToSpeechStreamingModel
 from .types.text_to_speech_streaming_send_completion_event import TextToSpeechStreamingSendCompletionEvent
 
 try:
@@ -38,7 +39,7 @@ class TextToSpeechStreamingClient:
     def connect(
         self,
         *,
-        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
+        model: typing.Optional[TextToSpeechStreamingModel] = None,
         send_completion_event: typing.Optional[TextToSpeechStreamingSendCompletionEvent] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -50,10 +51,16 @@ class TextToSpeechStreamingClient:
         The Try It playground may not provide the best experience for streaming audio.
         For optimal streaming performance, please use the SDK or implement your own WebSocket client.
 
+        **Model-Specific Notes:**
+        - **bulbul:v2:** Supports pitch, loudness, pace (0.3-3.0). Default sample rate: 22050 Hz.
+        - **bulbul:v3-beta:** Does NOT support pitch/loudness. Pace range: 0.5-2.0. Supports temperature parameter. Default sample rate: 24000 Hz. Preprocessing is always enabled.
+
         Parameters
         ----------
-        model : typing.Optional[typing.Literal["bulbul:v2"]]
-            Text to speech model to use
+        model : typing.Optional[TextToSpeechStreamingModel]
+            Text to speech model to use.
+            - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
+            - **bulbul:v3-beta**: Advanced model with temperature control (no pitch/loudness)
 
         send_completion_event : typing.Optional[TextToSpeechStreamingSendCompletionEvent]
             Enable completion event notifications when TTS generation finishes. When set to true, an event message will be sent when the final audio chunk has been generated.
@@ -117,7 +124,7 @@ class AsyncTextToSpeechStreamingClient:
     async def connect(
         self,
         *,
-        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
+        model: typing.Optional[TextToSpeechStreamingModel] = None,
         send_completion_event: typing.Optional[TextToSpeechStreamingSendCompletionEvent] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -129,10 +136,16 @@ class AsyncTextToSpeechStreamingClient:
         The Try It playground may not provide the best experience for streaming audio.
         For optimal streaming performance, please use the SDK or implement your own WebSocket client.
 
+        **Model-Specific Notes:**
+        - **bulbul:v2:** Supports pitch, loudness, pace (0.3-3.0). Default sample rate: 22050 Hz.
+        - **bulbul:v3-beta:** Does NOT support pitch/loudness. Pace range: 0.5-2.0. Supports temperature parameter. Default sample rate: 24000 Hz. Preprocessing is always enabled.
+
         Parameters
         ----------
-        model : typing.Optional[typing.Literal["bulbul:v2"]]
-            Text to speech model to use
+        model : typing.Optional[TextToSpeechStreamingModel]
+            Text to speech model to use.
+            - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
+            - **bulbul:v3-beta**: Advanced model with temperature control (no pitch/loudness)
 
         send_completion_event : typing.Optional[TextToSpeechStreamingSendCompletionEvent]
             Enable completion event notifications when TTS generation finishes. When set to true, an event message will be sent when the final audio chunk has been generated.

sarvamai/text_to_speech_streaming/raw_client.py

@@ -10,6 +10,7 @@ from ..core.api_error import ApiError
 from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ..core.request_options import RequestOptions
 from .socket_client import AsyncTextToSpeechStreamingSocketClient, TextToSpeechStreamingSocketClient
+from .types.text_to_speech_streaming_model import TextToSpeechStreamingModel
 from .types.text_to_speech_streaming_send_completion_event import TextToSpeechStreamingSendCompletionEvent
 
 try:
@@ -26,7 +27,7 @@ class RawTextToSpeechStreamingClient:
     def connect(
         self,
         *,
-        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
+        model: typing.Optional[TextToSpeechStreamingModel] = None,
         send_completion_event: typing.Optional[TextToSpeechStreamingSendCompletionEvent] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -38,10 +39,16 @@ class RawTextToSpeechStreamingClient:
         The Try It playground may not provide the best experience for streaming audio.
         For optimal streaming performance, please use the SDK or implement your own WebSocket client.
 
+        **Model-Specific Notes:**
+        - **bulbul:v2:** Supports pitch, loudness, pace (0.3-3.0). Default sample rate: 22050 Hz.
+        - **bulbul:v3-beta:** Does NOT support pitch/loudness. Pace range: 0.5-2.0. Supports temperature parameter. Default sample rate: 24000 Hz. Preprocessing is always enabled.
+
         Parameters
         ----------
-        model : typing.Optional[typing.Literal["bulbul:v2"]]
-            Text to speech model to use
+        model : typing.Optional[TextToSpeechStreamingModel]
+            Text to speech model to use.
+            - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
+            - **bulbul:v3-beta**: Advanced model with temperature control (no pitch/loudness)
 
         send_completion_event : typing.Optional[TextToSpeechStreamingSendCompletionEvent]
             Enable completion event notifications when TTS generation finishes. When set to true, an event message will be sent when the final audio chunk has been generated.
@@ -94,7 +101,7 @@ class AsyncRawTextToSpeechStreamingClient:
     async def connect(
         self,
         *,
-        model: typing.Optional[typing.Literal["bulbul:v2"]] = None,
+        model: typing.Optional[TextToSpeechStreamingModel] = None,
         send_completion_event: typing.Optional[TextToSpeechStreamingSendCompletionEvent] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
@@ -106,10 +113,16 @@ class AsyncRawTextToSpeechStreamingClient:
         The Try It playground may not provide the best experience for streaming audio.
         For optimal streaming performance, please use the SDK or implement your own WebSocket client.
 
+        **Model-Specific Notes:**
+        - **bulbul:v2:** Supports pitch, loudness, pace (0.3-3.0). Default sample rate: 22050 Hz.
+        - **bulbul:v3-beta:** Does NOT support pitch/loudness. Pace range: 0.5-2.0. Supports temperature parameter. Default sample rate: 24000 Hz. Preprocessing is always enabled.
+
         Parameters
         ----------
-        model : typing.Optional[typing.Literal["bulbul:v2"]]
-            Text to speech model to use
+        model : typing.Optional[TextToSpeechStreamingModel]
+            Text to speech model to use.
+            - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
+            - **bulbul:v3-beta**: Advanced model with temperature control (no pitch/loudness)
 
         send_completion_event : typing.Optional[TextToSpeechStreamingSendCompletionEvent]
             Enable completion event notifications when TTS generation finishes. When set to true, an event message will be sent when the final audio chunk has been generated.