local_smart_turn_v3

Local turn analyzer for on-device ML inference using the smart-turn-v3 model.

This module provides a smart turn analyzer that uses an ONNX model for local end-of-turn detection without requiring network connectivity.

class pipecat.audio.turn.smart_turn.local_smart_turn_v3.LocalSmartTurnAnalyzerV3(*, smart_turn_model_path: str | None = None, cpu_count: int = 1, **kwargs)[source]

Bases: BaseSmartTurn

Local turn analyzer using the smart-turn-v3 ONNX model.

Provides end-of-turn detection using locally-stored ONNX model, enabling offline operation without network dependencies.

__init__(*, smart_turn_model_path: str | None = None, cpu_count: int = 1, **kwargs)[source]

Initialize the local ONNX smart-turn-v3 analyzer.

Parameters:

  • smart_turn_model_path – Path to the ONNX model file. If this is not set, the bundled smart-turn-v3.2-cpu model will be used.

  • cpu_count – The number of CPUs to use for inference. Defaults to 1.

  • **kwargs – Additional arguments passed to BaseSmartTurn.