# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.

from typing import List, Union, Optional
from typing_extensions import Literal, TypeAlias

from ...._models import BaseModel

__all__ = [
    "Session",
    "InputAudioNoiseReduction",
    "InputAudioTranscription",
    "Tool",
    "Tracing",
    "TracingTracingConfiguration",
    "TurnDetection",
]


class InputAudioNoiseReduction(BaseModel):
    type: Optional[Literal["near_field", "far_field"]] = None
    """Type of noise reduction.

    `near_field` is for close-talking microphones such as headphones, `far_field` is
    for far-field microphones such as laptop or conference room microphones.
    """


class InputAudioTranscription(BaseModel):
    language: Optional[str] = None
    """The language of the input audio.

    Supplying the input language in
    [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`)
    format will improve accuracy and latency.
    """

    model: Optional[str] = None
    """
    The model to use for transcription, current options are `gpt-4o-transcribe`,
    `gpt-4o-mini-transcribe`, and `whisper-1`.
    """

    prompt: Optional[str] = None
    """
    An optional text to guide the model's style or continue a previous audio
    segment. For `whisper-1`, the
    [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting).
    For `gpt-4o-transcribe` models, the prompt is a free text string, for example
    "expect words related to technology".
    """


class Tool(BaseModel):
    description: Optional[str] = None
    """
    The description of the function, including guidance on when and how to call it,
    and guidance about what to tell the user when calling (if anything).
    """

    name: Optional[str] = None
    """The name of the function."""

    parameters: Optional[object] = None
    """Parameters of the function in JSON Schema."""

    type: Optional[Literal["function"]] = None
    """The type of the tool, i.e. `function`."""


class TracingTracingConfiguration(BaseModel):
    group_id: Optional[str] = None
    """
    The group id to attach to this trace to enable filtering and grouping in the
    traces dashboard.
    """

    metadata: Optional[object] = None
    """
    The arbitrary metadata to attach to this trace to enable filtering in the traces
    dashboard.
    """

    workflow_name: Optional[str] = None
    """The name of the workflow to attach to this trace.

    This is used to name the trace in the traces dashboard.
    """


Tracing: TypeAlias = Union[Literal["auto"], TracingTracingConfiguration]


class TurnDetection(BaseModel):
    create_response: Optional[bool] = None
    """
    Whether or not to automatically generate a response when a VAD stop event
    occurs.
    """

    eagerness: Optional[Literal["low", "medium", "high", "auto"]] = None
    """Used only for `semantic_vad` mode.

    The eagerness of the model to respond. `low` will wait longer for the user to
    continue speaking, `high` will respond more quickly. `auto` is the default and
    is equivalent to `medium`.
    """

    interrupt_response: Optional[bool] = None
    """
    Whether or not to automatically interrupt any ongoing response with output to
    the default conversation (i.e. `conversation` of `auto`) when a VAD start event
    occurs.
    """

    prefix_padding_ms: Optional[int] = None
    """Used only for `server_vad` mode.

    Amount of audio to include before the VAD detected speech (in milliseconds).
    Defaults to 300ms.
    """

    silence_duration_ms: Optional[int] = None
    """Used only for `server_vad` mode.

    Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms.
    With shorter values the model will respond more quickly, but may jump in on
    short pauses from the user.
    """

    threshold: Optional[float] = None
    """Used only for `server_vad` mode.

    Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher
    threshold will require louder audio to activate the model, and thus might
    perform better in noisy environments.
    """

    type: Optional[Literal["server_vad", "semantic_vad"]] = None
    """Type of turn detection."""


class Session(BaseModel):
    id: Optional[str] = None
    """Unique identifier for the session that looks like `sess_1234567890abcdef`."""

    input_audio_format: Optional[Literal["pcm16", "g711_ulaw", "g711_alaw"]] = None
    """The format of input audio.

    Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. For `pcm16`, input audio must
    be 16-bit PCM at a 24kHz sample rate, single channel (mono), and little-endian
    byte order.
    """

    input_audio_noise_reduction: Optional[InputAudioNoiseReduction] = None
    """Configuration for input audio noise reduction.

    This can be set to `null` to turn off. Noise reduction filters audio added to
    the input audio buffer before it is sent to VAD and the model. Filtering the
    audio can improve VAD and turn detection accuracy (reducing false positives) and
    model performance by improving perception of the input audio.
    """

    input_audio_transcription: Optional[InputAudioTranscription] = None
    """
    Configuration for input audio transcription, defaults to off and can be set to
    `null` to turn off once on. Input audio transcription is not native to the
    model, since the model consumes audio directly. Transcription runs
    asynchronously through
    [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription)
    and should be treated as guidance of input audio content rather than precisely
    what the model heard. The client can optionally set the language and prompt for
    transcription, these offer additional guidance to the transcription service.
    """

    instructions: Optional[str] = None
    """The default system instructions (i.e.

    system message) prepended to model calls. This field allows the client to guide
    the model on desired responses. The model can be instructed on response content
    and format, (e.g. "be extremely succinct", "act friendly", "here are examples of
    good responses") and on audio behavior (e.g. "talk quickly", "inject emotion
    into your voice", "laugh frequently"). The instructions are not guaranteed to be
    followed by the model, but they provide guidance to the model on the desired
    behavior.

    Note that the server sets default instructions which will be used if this field
    is not set and are visible in the `session.created` event at the start of the
    session.
    """

    max_response_output_tokens: Union[int, Literal["inf"], None] = None
    """
    Maximum number of output tokens for a single assistant response, inclusive of
    tool calls. Provide an integer between 1 and 4096 to limit output tokens, or
    `inf` for the maximum available tokens for a given model. Defaults to `inf`.
    """

    modalities: Optional[List[Literal["text", "audio"]]] = None
    """The set of modalities the model can respond with.

    To disable audio, set this to ["text"].
    """

    model: Optional[
        Literal[
            "gpt-4o-realtime-preview",
            "gpt-4o-realtime-preview-2024-10-01",
            "gpt-4o-realtime-preview-2024-12-17",
            "gpt-4o-realtime-preview-2025-06-03",
            "gpt-4o-mini-realtime-preview",
            "gpt-4o-mini-realtime-preview-2024-12-17",
        ]
    ] = None
    """The Realtime model used for this session."""

    output_audio_format: Optional[Literal["pcm16", "g711_ulaw", "g711_alaw"]] = None
    """The format of output audio.

    Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. For `pcm16`, output audio is
    sampled at a rate of 24kHz.
    """

    speed: Optional[float] = None
    """The speed of the model's spoken response.

    1.0 is the default speed. 0.25 is the minimum speed. 1.5 is the maximum speed.
    This value can only be changed in between model turns, not while a response is
    in progress.
    """

    temperature: Optional[float] = None
    """Sampling temperature for the model, limited to [0.6, 1.2].

    For audio models a temperature of 0.8 is highly recommended for best
    performance.
    """

    tool_choice: Optional[str] = None
    """How the model chooses tools.

    Options are `auto`, `none`, `required`, or specify a function.
    """

    tools: Optional[List[Tool]] = None
    """Tools (functions) available to the model."""

    tracing: Optional[Tracing] = None
    """Configuration options for tracing.

    Set to null to disable tracing. Once tracing is enabled for a session, the
    configuration cannot be modified.

    `auto` will create a trace for the session with default values for the workflow
    name, group id, and metadata.
    """

    turn_detection: Optional[TurnDetection] = None
    """Configuration for turn detection, ether Server VAD or Semantic VAD.

    This can be set to `null` to turn off, in which case the client must manually
    trigger model response. Server VAD means that the model will detect the start
    and end of speech based on audio volume and respond at the end of user speech.
    Semantic VAD is more advanced and uses a turn detection model (in conjuction
    with VAD) to semantically estimate whether the user has finished speaking, then
    dynamically sets a timeout based on this probability. For example, if user audio
    trails off with "uhhm", the model will score a low probability of turn end and
    wait longer for the user to continue speaking. This can be useful for more
    natural conversations, but may have a higher latency.
    """

    voice: Union[
        str,
        Literal["alloy", "ash", "ballad", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer", "verse"],
        None,
    ] = None
    """The voice the model uses to respond.

    Voice cannot be changed during the session once the model has responded with
    audio at least once. Current voice options are `alloy`, `ash`, `ballad`,
    `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, and `verse`.
    """