172173174175176177178179180181182183184185186187188

classRealtimeRunConfig(TypedDict):"""Configuration for running a realtime agent session."""model_settings:NotRequired[RealtimeSessionModelSettings]"""Settings for the realtime model session."""output_guardrails:NotRequired[list[OutputGuardrail[Any]]]"""List of output guardrails to run on the agent's responses."""guardrails_settings:NotRequired[RealtimeGuardrailsSettings]"""Settings for guardrail execution."""tracing_disabled:NotRequired[bool]"""Whether tracing is disabled for this run."""async_tool_calls:NotRequired[bool]"""Whether function tool calls should run asynchronously. Defaults to True."""

 99100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145

classRealtimeSessionModelSettings(TypedDict):"""Model settings for a realtime model session."""model_name:NotRequired[RealtimeModelName]"""The name of the realtime model to use."""instructions:NotRequired[str]"""System instructions for the model."""prompt:NotRequired[Prompt]"""The prompt to use for the model."""modalities:NotRequired[list[Literal["text","audio"]]]"""The modalities the model should support."""voice:NotRequired[str]"""The voice to use for audio output."""speed:NotRequired[float]"""The speed of the model's responses."""input_audio_format:NotRequired[RealtimeAudioFormat|OpenAIRealtimeAudioFormats]"""The format for input audio streams."""output_audio_format:NotRequired[RealtimeAudioFormat|OpenAIRealtimeAudioFormats]"""The format for output audio streams."""input_audio_transcription:NotRequired[RealtimeInputAudioTranscriptionConfig]"""Configuration for transcribing input audio."""input_audio_noise_reduction:NotRequired[RealtimeInputAudioNoiseReductionConfig|None]"""Noise reduction configuration for input audio."""turn_detection:NotRequired[RealtimeTurnDetectionConfig]"""Configuration for detecting conversation turns."""tool_choice:NotRequired[ToolChoice]"""How the model should choose which tools to call."""tools:NotRequired[list[Tool]]"""List of tools available to the model."""handoffs:NotRequired[list[Handoff]]"""List of handoff configurations."""tracing:NotRequired[RealtimeModelTracingConfig|None]"""Configuration for request tracing."""

5152535455565758596061

classRealtimeInputAudioTranscriptionConfig(TypedDict):"""Configuration for audio transcription in realtime sessions."""language:NotRequired[str]"""The language code for transcription."""model:NotRequired[Literal["gpt-4o-transcribe","gpt-4o-mini-transcribe","whisper-1"]|str]"""The transcription model to use."""prompt:NotRequired[str]"""An optional prompt to guide transcription."""

6465666768

classRealtimeInputAudioNoiseReductionConfig(TypedDict):"""Noise reduction configuration for input audio."""type:NotRequired[Literal["near_field","far_field"]]"""Noise reduction mode to apply to input audio."""

7172737475767778798081828384858687888990919293949596

classRealtimeTurnDetectionConfig(TypedDict):"""Turn detection config. Allows extra vendor keys if needed."""type:NotRequired[Literal["semantic_vad","server_vad"]]"""The type of voice activity detection to use."""create_response:NotRequired[bool]"""Whether to create a response when a turn is detected."""eagerness:NotRequired[Literal["auto","low","medium","high"]]"""How eagerly to detect turn boundaries."""interrupt_response:NotRequired[bool]"""Whether to allow interrupting the assistant's response."""prefix_padding_ms:NotRequired[int]"""Padding time in milliseconds before turn detection."""silence_duration_ms:NotRequired[int]"""Duration of silence in milliseconds to trigger turn detection."""threshold:NotRequired[float]"""The threshold for voice activity detection."""idle_timeout_ms:NotRequired[int]"""Threshold for server-vad to trigger a response if the user is idle for this duration."""

148149150151152153154155156

classRealtimeGuardrailsSettings(TypedDict):"""Settings for output guardrails in realtime sessions."""debounce_text_length:NotRequired[int]"""    The minimum number of characters to accumulate before running guardrails on transcript    deltas. Defaults to 100. Guardrails run every time the accumulated text reaches    1x, 2x, 3x, etc. times this threshold.    """

107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147

classRealtimeModelConfig(TypedDict):"""Options for connecting to a realtime model."""api_key:NotRequired[str|Callable[[],MaybeAwaitable[str]]]"""The API key (or function that returns a key) to use when connecting. If unset, the model will    try to use a sane default. For example, the OpenAI Realtime model will try to use the    `OPENAI_API_KEY`  environment variable.    """url:NotRequired[str]"""The URL to use when connecting. If unset, the model will use a sane default. For example,    the OpenAI Realtime model will use the default OpenAI WebSocket URL.    """headers:NotRequired[dict[str,str]]"""The headers to use when connecting. If unset, the model will use a sane default.    Note that, when you set this, authorization header won't be set under the hood.    e.g., {"api-key": "your api key here"} for Azure OpenAI Realtime WebSocket connections.    """initial_model_settings:NotRequired[RealtimeSessionModelSettings]"""The initial model settings to use when connecting."""playback_tracker:NotRequired[RealtimePlaybackTracker]"""The playback tracker to use when tracking audio playback progress. If not set, the model will    use a default implementation that assumes audio is played immediately, at realtime speed.    A playback tracker is useful for interruptions. The model generates audio much faster than    realtime playback speed. So if there's an interruption, its useful for the model to know how    much of the audio has been played by the user. In low-latency scenarios, it's fine to assume    that audio is played back immediately at realtime speed. But in scenarios like phone calls or    other remote interactions, you can set a playback tracker that lets the model know when audio    is played to the user.    """call_id:NotRequired[str]"""Attach to an existing realtime call instead of creating a new session.    When provided, the transport connects using the `call_id` query string parameter rather than a    model name. This is used for SIP-originated calls that are accepted via the Realtime Calls API.    """

159160161162163164165166167168169

classRealtimeModelTracingConfig(TypedDict):"""Configuration for tracing in realtime model sessions."""workflow_name:NotRequired[str]"""The workflow name to use for tracing."""group_id:NotRequired[str]"""A group identifier to use for tracing, to link multiple traces together."""metadata:NotRequired[dict[str,Any]]"""Additional metadata to include with the trace."""

193194195196197198199200

classRealtimeUserInputText(TypedDict):"""A text input from the user."""type:Literal["input_text"]"""The type identifier for text input."""text:str"""The text content from the user."""

211212213214215216217218219220221

classRealtimeUserInputMessage(TypedDict):"""A message input from the user."""type:Literal["message"]"""The type identifier for message inputs."""role:Literal["user"]"""The role identifier for user messages."""content:list[RealtimeUserInputText|RealtimeUserInputImage]"""List of content items (text and image) in the message."""

4142434445464748

classRealtimeClientMessage(TypedDict):"""A raw message to be sent to the model."""type:str# explicitly required"""The type of the message."""other_data:NotRequired[dict[str,Any]]"""Merged into the message body."""