Voice Activity Detection Python Packages

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

funasr

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

auditok

An audio/acoustic activity detection and audio segmentation tool

ffsubsync

Automagically synchronize subtitles with video.

sherpa-ncnn

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.

whisper-s2t

An Optimized Speech-to-Text Pipeline for the Whisper Model Supporting Multiple Inference Engine

inaspeechsegmenter

CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

funasr-onnx

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

omnivad

Cross-platform VAD & Audio Event Detection toolkit — Python (PyPI) + TypeScript (npm) + C API. DFSMN models ~2MB, 200x real-time. Runs everywhere: native, browser (WASM), Node.js.

fireredvad

A SOTA Industrial-Grade Voice Activity Detection & Audio Event Detection, supporting 100+ languages, outperforming Silero-VAD, TEN-VAD, FunASR-VAD and WebRTC-VAD

decibri

Cross-platform audio capture, playback, and voice activity detection for Python, Rust, and Node.js powered by a single Rust core.

diart

A python package to build AI-powered real-time audio applications

silero-vad-lite

Lightweight wrapper for Silero VAD using internal ONNX Runtime and with no python package dependencies

diarize

Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.

pywebrtc-audio

Python bindings for WebRTC's audio processing pipeline, bringing noise suppression, echo cancellation, automatic gain control, and voice activity detection to the Python ecosystem via pybind11.

pvcobra

On-device voice activity detection (VAD) powered by deep learning

attenlabs-saa

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

subaligner

Automatically synchronize and translate subtitles, or create new ones by transcribing, using pre-trained DNNs, Forced Alignments and Transformers. https://subaligner.readthedocs.io/

sherpa-ncnn-bin

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.

saa-livekit-client

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

funasr-torch

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

sherpa-ncnn-core

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, LicheePi4A etc.

saa-pipecat-client

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

livekit-plugins-tenvad

TEN VAD low-latency voice activity detection for real-time streaming, integrated with livekit-agents