# This file was auto-generated by Fern from our API Definition.

import typing_extensions
from ..types.configure_connection_data_model import ConfigureConnectionDataModel
from ..types.configure_connection_data_output_audio_bitrate import ConfigureConnectionDataOutputAudioBitrate
from ..types.configure_connection_data_output_audio_codec import ConfigureConnectionDataOutputAudioCodec
from ..types.configure_connection_data_speaker import ConfigureConnectionDataSpeaker
from ..types.configure_connection_data_target_language_code import ConfigureConnectionDataTargetLanguageCode


class ConfigureConnectionDataParams(typing_extensions.TypedDict):
    model: typing_extensions.NotRequired[ConfigureConnectionDataModel]
    """
    Specifies the model to use for text-to-speech conversion.
    - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
    - **bulbul:v3-beta**: Advanced model with temperature control (no pitch/loudness)
    """

    target_language_code: ConfigureConnectionDataTargetLanguageCode
    """
    The language of the text in BCP-47 format
    """

    speaker: ConfigureConnectionDataSpeaker
    """
    The speaker voice to be used for the output audio.
    
    **Model Compatibility:**
    - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
    - **bulbul:v3-beta:** aditya (default), 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_extensions.NotRequired[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:** NOT supported for bulbul:v3-beta. Will be ignored if provided.
    """

    pace: typing_extensions.NotRequired[float]
    """
    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_extensions.NotRequired[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:** NOT supported for bulbul:v3-beta. Will be ignored if provided.
    """

    temperature: typing_extensions.NotRequired[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:** Only supported for bulbul:v3-beta. Will be ignored for bulbul:v2.
    """

    speech_sample_rate: typing_extensions.NotRequired[int]
    """
    Specifies the sample rate of the output audio. Supported values are 
    8000, 16000, 22050, 24000 Hz.
    
    **Model-specific defaults:**
    - **bulbul:v2:** 22050 Hz
    - **bulbul:v3-beta:** 24000 Hz
    """

    enable_preprocessing: typing_extensions.NotRequired[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.
    
    **Model-specific defaults:**
    - **bulbul:v2:** false (optional)
    - **bulbul:v3-beta:** Always enabled (cannot be disabled)
    """

    output_audio_codec: typing_extensions.NotRequired[ConfigureConnectionDataOutputAudioCodec]
    """
    Audio codec (currently supports MP3 only, optimized for real-time playback)
    """

    output_audio_bitrate: typing_extensions.NotRequired[ConfigureConnectionDataOutputAudioBitrate]
    """
    Audio bitrate (choose from 5 supported bitrate options)
    """

    min_buffer_size: typing_extensions.NotRequired[int]
    """
    Minimum character length that triggers buffer flushing for TTS model processing
    """

    max_chunk_length: typing_extensions.NotRequired[int]
    """
    Maximum length for sentence splitting (adjust based on content length)
    """