pipecat-ai

Smart Turn v3 is an open‑source semantic Voice Activity Detection (VAD) model that tells you whether a speaker has finished their turn by analysing the raw waveform, not the transcript. Blog post: Smart Turn v3 GitHub repo with training and inference code Datasets with training and inference code Backbone: Whisper Tiny encoder Head: shallow linear classifier Params: 8 M (int8) Checkpoint: 8 MB ONNX Please see the blog post and GitHub repo for more information on using the model, either standalone or with Pipecat.