Silero VAD

by snakers4 / Silero

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

Looking at Silero VAD? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

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

Category
Open source
License
MIT
Stars
★ 9.9k
Last push
2026-07-16
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

Links

GitHub repo ↗

Silero VAD vs Whipscribe

FeatureSilero VADWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
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 ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.