snakers4/silero-vad

Health v2 · maintenance only

Adoption not part of the score

10061 stars · 833 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Silero VAD is a pre-trained, enterprise-grade Voice Activity Detector model available via PyPI, runnable with PyTorch or ONNX Runtime. It detects speech segments in audio streams, including in real time, with a lightweight footprint.

Use cases

• detect speech segments in audio recordings
• run real-time voice activity detection in a streaming pipeline
• segment audio before feeding a speech-to-text model
• filter out silence and noise from voice recordings
• add voice activation to a voice assistant or command app
• run VAD on edge devices via onnxruntime

When to choose

• you need a fast, lightweight, pre-trained VAD without training your own model
• you need real-time speech detection with low latency
• you want ONNX support for deployment across architectures
• you're building ASR pipelines and need audio segmentation

When to avoid

• you need full speech recognition or transcription, not just speech detection
• you need speaker identification or diarization
• you can't use PyTorch or ONNX Runtime as dependencies

Facets

library · maturity stable

speech-recognition audio-processing machine-learning llm-inference speech-processing machine-learning python cross-platform voice-activity-detection vad onnx pytorch pre-trained-model real-time-audio audio natural-language-processing gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="snakers4/silero-vad")