Mirror what a transport would do: hand the prediction to the stream.

Return the :class:`SimulationContext` when this job is running under a simulation, or ``None`` for a normal/production session. Resol

Starts the background audio system, publishing the audio track and beginning playback of any configured ambient sound. If `a

A node in the processing pipeline that finalizes transcriptions from text segments. This node can be used to adjust or post-process

Validate that the speaker is compatible with the model version.

Resolve when rolling RMS exceeds `min_rms`, or raise on timeout.

Wait until the avatar participant has joined the room and published its video track. Raises ``asyncio.TimeoutError`` if it doesn't ar

Block until ``transport._ws`` is set.

Initialize a FallbackAdapter that manages multiple TTS instances. Args: tts (list[TTS]): A list of TTS instances to use

Create a new instance of SLNG TTS (based on Deepgram's architecture). Args: model (str): SLNG model identifier (e.g., "d

Create a new instance of Deepgram TTS. Args: model (str): TTS model to use. Defaults to "aura-2-andromeda-en".

Initialize the Baseten TTS. Args: api_key: Baseten API key, or ``BASETEN_API_KEY`` env var. model_endpoint:

Initialize the Gradium TTS. Args: api_key (str): Gradium API key, or `GRADIUM_API_KEY` env var. model_endpoi

Create a new instance of Respeecher TTS. Args: voice_id: ID of the voice to use. If not provided, a model-specific defau

Create a new instance of Smallest AI Lightning TTS. Args: api_key: Your Smallest AI API key. model: The TTS

Create a new instance of Fish Audio TTS. See https://docs.fish.audio/api-reference/endpoint/websocket/tts-live for more details

Create a new instance of ElevenLabs TTS. Args: voice_id (str): Voice ID. Defaults to `DEFAULT_VOICE_ID`. voi

Create a new instance of Cartesia TTS. See https://docs.cartesia.ai/reference/web-socket/stream-speech/stream-speech for more detail

Create a new instance of Uplift TTS. Args: base_url: Base URL for TTS service. Defaults to wss://api.upliftai.org

Create a new instance of Anthropic LLM. ``api_key`` must be set to your Anthropic API key, either using the argument or by setting

Create a new instance of NeuPhonic TTS. See https://docs.neuphonic.com for more details on the NeuPhonic API. Args:

Create a new instance of Google TTS. Credentials must be provided, either by using the ``credentials_info`` dict, or reading

Create a new instance of the Resemble TTS. See https://docs.app.resemble.ai/docs/text_to_speech/ for more documentation on all of th

Create a new instance of Inworld TTS. Args: api_key (str, optional): The Inworld API key. If not provide

Minimax TTS plugin Args: model (TTSModel | str, optional): The Minimax TTS model to use. Defaults to DEFAULT_MODEL.

Create a new instance of OpenAI TTS. ``api_key`` must be set to your OpenAI API key, either using the argument or by setting the

Create a new instance of Murf AI TTS. See https://murf.ai/api/docs/api-reference/text-to-speech/stream-input for more details on the

Publish a steady sine tone via the production `_ParticipantAudioOutput` helper, so the test exercises both the SDK and the agents-framework layer.

Build a ChatContext with system, user/assistant pairs, and interleaved tool calls.

Build the streaming configuration for Gladia API.

Drive `_InworldConnection._send_loop` against a fake websocket and return the first `create` packet it sends, as a parsed dict. The fake `sen

Run the real _connect_ws path and return the parsed session.create payload it sent.