sarvamai 0.1.22a4__py3-none-any.whl → 0.1.22a7__py3-none-any.whl

sarvamai/speech_to_text_translate_streaming/raw_client.py

@@ -32,11 +32,11 @@ class RawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.Iterator[SpeechToTextTranslateStreamingSocketClient]:
@@ -50,10 +50,10 @@ 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.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            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 supports sample rate 16000 and 8000.
+            - **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.
@@ -67,6 +67,10 @@ class RawSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input stream. Use this when sending raw PCM audio.
+            Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
+
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
 
@@ -81,8 +85,6 @@ class RawSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -91,6 +93,8 @@ class RawSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
         ws_url = ws_url + f"?{query_params}"
         headers = self._client_wrapper.get_headers()
         if api_subscription_key is not None:
@@ -124,11 +128,11 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         self,
         *,
         model: typing.Optional[typing.Literal["saaras:v2.5"]] = None,
-        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         sample_rate: typing.Optional[str] = None,
         high_vad_sensitivity: typing.Optional[SpeechToTextTranslateStreamingHighVadSensitivity] = None,
         vad_signals: typing.Optional[SpeechToTextTranslateStreamingVadSignals] = None,
         flush_signal: typing.Optional[SpeechToTextTranslateStreamingFlushSignal] = None,
+        input_audio_codec: typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec] = None,
         api_subscription_key: typing.Optional[str] = None,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> typing.AsyncIterator[AsyncSpeechToTextTranslateStreamingSocketClient]:
@@ -142,10 +146,10 @@ 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.
 
-        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
-            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 supports sample rate 16000 and 8000.
+            - **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.
@@ -159,6 +163,10 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         flush_signal : typing.Optional[SpeechToTextTranslateStreamingFlushSignal]
             Signal to flush the audio buffer and finalize transcription and translation
 
+        input_audio_codec : typing.Optional[SpeechToTextTranslateStreamingInputAudioCodec]
+            Audio codec/format of the input stream. Use this when sending raw PCM audio.
+            Supported values: wav, pcm_s16le, pcm_l16, pcm_raw.
+
         api_subscription_key : typing.Optional[str]
             API subscription key for authentication
 
@@ -173,8 +181,6 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
         query_params = httpx.QueryParams()
         if model is not None:
             query_params = query_params.add("model", model)
-        if input_audio_codec is not None:
-            query_params = query_params.add("input_audio_codec", input_audio_codec)
         if sample_rate is not None:
             query_params = query_params.add("sample_rate", sample_rate)
         if high_vad_sensitivity is not None:
@@ -183,6 +189,8 @@ class AsyncRawSpeechToTextTranslateStreamingClient:
             query_params = query_params.add("vad_signals", vad_signals)
         if flush_signal is not None:
             query_params = query_params.add("flush_signal", flush_signal)
+        if input_audio_codec is not None:
+            query_params = query_params.add("input_audio_codec", input_audio_codec)
         ws_url = ws_url + f"?{query_params}"
         headers = self._client_wrapper.get_headers()
         if api_subscription_key is not None:

sarvamai/speech_to_text_translate_streaming/types/speech_to_text_translate_streaming_input_audio_codec.py

@@ -3,31 +3,5 @@
 import typing
 
 SpeechToTextTranslateStreamingInputAudioCodec = typing.Union[
-    typing.Literal[
-        "wav",
-        "x-wav",
-        "wave",
-        "mp3",
-        "mpeg",
-        "mpeg3",
-        "x-mp3",
-        "x-mpeg-3",
-        "aac",
-        "x-aac",
-        "aiff",
-        "x-aiff",
-        "ogg",
-        "opus",
-        "flac",
-        "x-flac",
-        "mp4",
-        "x-m4a",
-        "amr",
-        "x-ms-wma",
-        "webm",
-        "pcm_s16le",
-        "pcm_l16",
-        "pcm_raw",
-    ],
-    typing.Any,
+    typing.Literal["wav", "pcm_s16le", "pcm_l16", "pcm_raw"], typing.Any
 ]

sarvamai/text/client.py

@@ -47,7 +47,6 @@ class TextClient:
         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,
@@ -125,10 +124,6 @@ class TextClient:
             - 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.
 
@@ -186,7 +181,6 @@ class TextClient:
             speaker_gender=speaker_gender,
             mode=mode,
             model=model,
-            enable_preprocessing=enable_preprocessing,
             output_script=output_script,
             numerals_format=numerals_format,
             request_options=request_options,
@@ -371,7 +365,6 @@ class AsyncTextClient:
         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,
@@ -449,10 +442,6 @@ class AsyncTextClient:
             - 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.
 
@@ -518,7 +507,6 @@ class AsyncTextClient:
             speaker_gender=speaker_gender,
             mode=mode,
             model=model,
-            enable_preprocessing=enable_preprocessing,
             output_script=output_script,
             numerals_format=numerals_format,
             request_options=request_options,

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