"""Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT."""

from __future__ import annotations
from .provideroptions import ProviderOptions, ProviderOptionsTypedDict
from .sttinputaudio import STTInputAudio, STTInputAudioTypedDict
from .stttimestampgranularity import STTTimestampGranularity
from openrouter.types import BaseModel, UNSET_SENTINEL, UnrecognizedStr
from pydantic import model_serializer
from typing import List, Literal, Optional, Union
from typing_extensions import NotRequired, TypedDict


class STTRequestProviderTypedDict(TypedDict):
    r"""Provider-specific passthrough configuration"""

    options: NotRequired[ProviderOptionsTypedDict]
    r"""Provider-specific options keyed by provider slug. Only options for the matched provider are forwarded; the rest are ignored. Unrecognized keys are silently dropped."""


class STTRequestProvider(BaseModel):
    r"""Provider-specific passthrough configuration"""

    options: Optional[ProviderOptions] = None
    r"""Provider-specific options keyed by provider slug. Only options for the matched provider are forwarded; the rest are ignored. Unrecognized keys are silently dropped."""

    @model_serializer(mode="wrap")
    def serialize_model(self, handler):
        optional_fields = set(["options"])
        serialized = handler(self)
        m = {}

        for n, f in type(self).model_fields.items():
            k = f.alias or n
            val = serialized.get(k, serialized.get(n))

            if val != UNSET_SENTINEL:
                if val is not None or k not in optional_fields:
                    m[k] = val

        return m


STTRequestResponseFormat = Union[
    Literal[
        "json",
        "verbose_json",
    ],
    UnrecognizedStr,
]
r"""Output format. \"json\" (default) returns { text, usage }. \"verbose_json\" additionally returns task, language, duration, and segment-level timestamps; only supported by OpenAI-compatible providers."""


class STTRequestTypedDict(TypedDict):
    r"""Speech-to-text request input. Accepts a JSON body with input_audio containing base64-encoded audio."""

    input_audio: STTInputAudioTypedDict
    r"""Base64-encoded audio to transcribe"""
    model: str
    r"""STT model identifier"""
    language: NotRequired[str]
    r"""ISO-639-1 language code (e.g., \"en\", \"ja\"). Auto-detected if omitted."""
    provider: NotRequired[STTRequestProviderTypedDict]
    r"""Provider-specific passthrough configuration"""
    response_format: NotRequired[STTRequestResponseFormat]
    r"""Output format. \"json\" (default) returns { text, usage }. \"verbose_json\" additionally returns task, language, duration, and segment-level timestamps; only supported by OpenAI-compatible providers."""
    temperature: NotRequired[float]
    r"""Sampling temperature for transcription"""
    timestamp_granularities: NotRequired[List[STTTimestampGranularity]]
    r"""Timestamp detail levels to include when response_format is \"verbose_json\". \"segment\" returns segment-level timestamps; \"word\" additionally returns word-level timestamps in the words array. Ignored unless response_format is \"verbose_json\"."""


class STTRequest(BaseModel):
    r"""Speech-to-text request input. Accepts a JSON body with input_audio containing base64-encoded audio."""

    input_audio: STTInputAudio
    r"""Base64-encoded audio to transcribe"""

    model: str
    r"""STT model identifier"""

    language: Optional[str] = None
    r"""ISO-639-1 language code (e.g., \"en\", \"ja\"). Auto-detected if omitted."""

    provider: Optional[STTRequestProvider] = None
    r"""Provider-specific passthrough configuration"""

    response_format: Optional[STTRequestResponseFormat] = None
    r"""Output format. \"json\" (default) returns { text, usage }. \"verbose_json\" additionally returns task, language, duration, and segment-level timestamps; only supported by OpenAI-compatible providers."""

    temperature: Optional[float] = None
    r"""Sampling temperature for transcription"""

    timestamp_granularities: Optional[List[STTTimestampGranularity]] = None
    r"""Timestamp detail levels to include when response_format is \"verbose_json\". \"segment\" returns segment-level timestamps; \"word\" additionally returns word-level timestamps in the words array. Ignored unless response_format is \"verbose_json\"."""

    @model_serializer(mode="wrap")
    def serialize_model(self, handler):
        optional_fields = set(
            [
                "language",
                "provider",
                "response_format",
                "temperature",
                "timestamp_granularities",
            ]
        )
        serialized = handler(self)
        m = {}

        for n, f in type(self).model_fields.items():
            k = f.alias or n
            val = serialized.get(k, serialized.get(n))

            if val != UNSET_SENTINEL:
                if val is not None or k not in optional_fields:
                    m[k] = val

        return m