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

import typing_extensions
from ..types.input_audio_codec import InputAudioCodec
from ..types.speech_to_text_translate_model import SpeechToTextTranslateModel


class SpeechToTextTranslateJobParametersParams(typing_extensions.TypedDict):
    prompt: typing_extensions.NotRequired[str]
    """
    Prompt to assist the transcription
    """

    model: typing_extensions.NotRequired[SpeechToTextTranslateModel]
    """
    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]
    """
    Enables speaker diarization, which identifies and separates different speakers in the audio.
     When set to true, the API will provide speaker-specific segments in the response.
     Note: This parameter is currently in Beta mode.
    """

    num_speakers: typing_extensions.NotRequired[int]
    """
    Number of speakers to be detected in the audio. This is used when with_diarization is set to true.
    """

    input_audio_codec: typing_extensions.NotRequired[InputAudioCodec]
    """
    Audio codec/format of uploaded files. The API automatically detects most formats; for PCM files (pcm_s16le, pcm_l16, pcm_raw), you must specify this parameter. PCM files are supported only at 16kHz sample rate.
    """