Fix docstrings after #1811 Blingfire default tokenizer switch (#3812)

Author: mrkowalski

livekit-plugins/livekit-plugins-cartesia/livekit/plugins/cartesia/tts.py

@@ -118,7 +118,7 @@ def __init__(
             word_timestamps (bool, optional): Whether to add word timestamps to the output. Defaults to True.
             api_key (str, optional): The Cartesia API key. If not provided, it will be read from the CARTESIA_API_KEY environment variable.
             http_session (aiohttp.ClientSession | None, optional): An existing aiohttp ClientSession to use. If not provided, a new session will be created.
-            tokenizer (tokenize.SentenceTokenizer, optional): The tokenizer to use. Defaults to tokenize.basic.SentenceTokenizer(min_sentence_len=BUFFERED_WORDS_COUNT).
+            tokenizer (tokenize.SentenceTokenizer, optional): The tokenizer to use. Defaults to `livekit.agents.tokenize.blingfire.SentenceTokenizer`.
             text_pacing (tts.SentenceStreamPacer | bool, optional): Stream pacer for the TTS. Set to True to use the default pacer, False to disable.
             base_url (str, optional): The base URL for the Cartesia API. Defaults to "https://api.cartesia.ai".
         """  # noqa: E501

livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/tts.py

@@ -110,7 +110,7 @@ def __init__(
             streaming_latency (NotGivenOr[int]): Optimize for streaming latency, defaults to 0 - disabled. 4 for max latency optimizations. deprecated
             inactivity_timeout (int): Inactivity timeout in seconds for the websocket connection. Defaults to 300.
             auto_mode (bool): Reduces latency by disabling chunk schedule and buffers. Sentence tokenizer will be used to synthesize one sentence at a time. Defaults to True.
-            word_tokenizer (NotGivenOr[tokenize.WordTokenizer | tokenize.SentenceTokenizer]): Tokenizer for processing text. Defaults to basic WordTokenizer.
+            word_tokenizer (NotGivenOr[tokenize.WordTokenizer | tokenize.SentenceTokenizer]): Tokenizer for processing text. Defaults to basic WordTokenizer when auto_mode=False, `livekit.agents.tokenize.blingfire.SentenceTokenizer` otherwise.
             enable_ssml_parsing (bool): Enable SSML parsing for input text. Defaults to False.
             enable_logging (bool): Enable logging of the request. When set to false, zero retention mode will be used. Defaults to True.
             chunk_length_schedule (NotGivenOr[list[int]]): Schedule for chunk lengths, ranging from 50 to 500. Defaults are [120, 160, 250, 290].

livekit-plugins/livekit-plugins-google/livekit/plugins/google/tts.py

@@ -98,7 +98,7 @@ def __init__(
             volume_gain_db (float, optional): Volume gain in decibels. Default is 0.0. In the range [-96.0, 16.0]. Strongly recommended not to exceed +10 (dB).
             credentials_info (dict, optional): Dictionary containing Google Cloud credentials. Default is None.
             credentials_file (str, optional): Path to the Google Cloud credentials JSON file. Default is None.
-            tokenizer (tokenize.SentenceTokenizer, optional): Tokenizer for the TTS. Default is a basic sentence tokenizer.
+            tokenizer (tokenize.SentenceTokenizer, optional): Tokenizer for the TTS. Defaults to `livekit.agents.tokenize.blingfire.SentenceTokenizer`.
             custom_pronunciations (CustomPronunciations, optional): Custom pronunciations for the TTS. Default is None.
             use_streaming (bool, optional): Whether to use streaming synthesis. Default is True.
             enable_ssml (bool, optional): Whether to enable SSML support. Default is False.

livekit-plugins/livekit-plugins-minimax/livekit/plugins/minimax/tts.py

@@ -163,7 +163,7 @@ def __init__(
             timbre (int | None, optional): Corresponds to the "Nasal/Crisp" slider on the official page. Range: [-100, 100].
             sample_rate (TTSSampleRate, optional): The audio sample rate in Hz. Defaults to 24000.
             bitrate (TTSBitRate, optional): The audio bitrate in kbps. Defaults to 128000.
-            tokenizer (NotGivenOr[tokenize.SentenceTokenizer], optional): The sentence tokenizer to use. Defaults to NOT_GIVEN.
+            tokenizer (NotGivenOr[tokenize.SentenceTokenizer], optional): The sentence tokenizer to use. Defaults to `livekit.agents.tokenize.basic.SentenceTokenizer`.
             text_pacing (tts.SentenceStreamPacer | bool, optional): Enable text pacing for sentence-level timing control. Defaults to False.
             api_key (str | None, optional): The Minimax API key. Defaults to None.
             base_url (NotGivenOr[str], optional): The base URL for the Minimax API. Defaults to NOT_GIVEN.

livekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/tts.py

@@ -70,7 +70,7 @@ def __init__(
             sample_rate (int, optional): The audio sample rate in Hz. Defaults to 44100.
             api_key (str | None, optional): The Resemble API key. If not provided, it will be read from the RESEMBLE_API_KEY environment variable.
             http_session (aiohttp.ClientSession | None, optional): An existing aiohttp ClientSession to use. If not provided, a new session will be created.
-            tokenizer (tokenize.SentenceTokenizer, optional): The tokenizer to use. Defaults to tokenize.SentenceTokenizer().
+            tokenizer (tokenize.SentenceTokenizer, optional): The tokenizer to use. Defaults to `livekit.agents.tokenize.blingfire.SentenceTokenizer`.
             use_streaming (bool, optional): Whether to use streaming or not. Defaults to True.
         """  # noqa: E501
         super().__init__(

livekit-plugins/livekit-plugins-smallestai/livekit/plugins/smallestai/tts.py

@@ -86,7 +86,6 @@ def __init__(
             output_format: Output format of the audio.
             base_url: Base URL for the Smallest AI API.
             http_session: An existing aiohttp ClientSession to use.
-            tokenizer: The tokenizer to use for streaming.
         """
 
         super().__init__(

livekit-plugins/livekit-plugins-speechmatics/livekit/plugins/speechmatics/tts.py

@@ -57,7 +57,7 @@ def __init__(
             sample_rate (int): Sample rate of audio. Defaults to 16000.
             api_key (str): Speechmatics API key. If not provided, will look for SPEECHMATICS_API_KEY in environment.
             base_url (str): Base URL for Speechmatics TTS API. Defaults to "https://preview.tts.speechmatics.com"
-            word_tokenizer (tokenize.WordTokenizer): Tokenizer for processing text. Defaults to basic WordTokenizer.
+            word_tokenizer (tokenize.WordTokenizer): Tokenizer for processing text. Defaults to `livekit.agents.tokenize.basic.WordTokenizer`.
             http_session (aiohttp.ClientSession): Optional aiohttp session to use for requests.
         """
         super().__init__(

livekit-plugins/livekit-plugins-upliftai/livekit/plugins/upliftai/tts.py

@@ -119,7 +119,7 @@ def __init__(
                 - 'ULAW_8000_8': μ-law format, 8kHz, 8-bit
             sample_rate: Sample rate for audio output. Defaults to 22050
             num_channels: Number of audio channels. Defaults to 1 (mono)
-            word_tokenizer: Tokenizer for processing text
+            word_tokenizer: Tokenizer for processing text. Defaults to `livekit.agents.tokenize.basic.WordTokenizer`.
         """
         super().__init__(
             capabilities=tts.TTSCapabilities(