Voice Activity Detection Explained: VAD for Voice Agents
Voice activity detection explained for voice agents: how VAD scores call audio, why it is not end-of-turn detection, the four ways phone lines trip it up, and the setting that fixes each symptom.
Read the full guide →Deep Dives in This Series
Voice Activity Detection in Python: A Working Example
Voice activity detection in Python with Silero VAD on a real 8 kHz phone call. Install it, find speech segments, change one setting at a time, then stream it in 32 ms chunks the way a live voice agent does.
Open-Source VAD Models Compared for Phone Agents
A comparison of Silero, WebRTC VAD, TEN VAD, FireRedVAD, NVIDIA MarbleNet, pyannote and FunASR, seven open-source VAD models for voice agents, on licence terms, sample rate, size and whose benchmark says what.
LiveKit VAD vs Pipecat VAD: Every Setting and Its Default
LiveKit VAD and Pipecat VAD settings compared from each repo: the Silero thresholds, start and silence timers, turn and interruption options, and what to change for noisy phone lines.
WebRTC VAD vs Silero VAD: Which Works on Phone Calls
WebRTC VAD vs Silero VAD for voice agents: how each detects speech, where each fails on noisy 8 kHz phone audio, the published accuracy numbers and which one voice agent stacks ship.