Silero VAD

by snakers4 / Silero

Tiny, accurate voice-activity-detection model — runs on CPU.

TL;DR

Tiny, accurate voice-activity-detection model — runs on CPU.

Best for front-end VAD for any streaming ASR pipeline. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, macOS, Windows, Android, iOS, Edge

What it is

A few-MB pre-trained VAD that runs in milliseconds per chunk. MIT.

Best for: Front-end VAD for any streaming ASR pipeline.
Watch out for: Detects speech only, not phonemes; some false positives on music.

Install / use

pip install silero-vad

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeYes
Languages supported99
HIPAA eligibleNo

Silero VAD vs Whipscribe

FeatureSilero VADWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsNoYes
StreamingYesNo
Languages9999
PlatformsLinux, macOS, Windows, Android, iOS, EdgeWeb, API, MCP

Alternatives to Silero VAD

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.