# wiseman/py-webrtcvad

Python interface to the WebRTC Voice Activity Detector

Repository: https://github.com/wiseman/py-webrtcvad
Canonical: https://ross.abutalabs.com/products/py-webrtcvad
Language: C
License: NOASSERTION
License Family: other
Last push: 2024-07-04T02:23:24+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3784, "days_push": 791, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2496, forks 428 (observed 2026-08-28T04:06:56.712253+00:00)

## What it is
A Python wrapper around Google's WebRTC Voice Activity Detector, classifying short frames of 16-bit mono PCM audio as speech or non-speech. It is fast, lightweight, and commonly used as a preprocessing step for telephony and speech recognition pipelines.

## Use cases
- detect speech segments in a wav file
- filter out silence before running speech recognition
- voice activity detection for telephony audio
- split audio into voiced and unvoiced chunks
- python wrapper for webrtc vad
- trim silence from recorded audio

## When to choose
- you need fast, lightweight VAD on 16-bit mono PCM at 8/16/32/48 kHz
- you want a battle-tested C-based detector with a simple Python API
- you're preprocessing audio for ASR or telephony

## When to avoid
- your audio isn't 16-bit mono PCM at supported sample rates
- you need state-of-the-art neural VAD accuracy
- you need per-word timestamps or speaker diarization

## Facets
- artifact type: library
- maturity: maintenance
- function: speech-recognition, audio-processing, nlp
- domain: speech-processing
- platform: python, cross-platform
- tags: voice-activity-detection, webrtc, pcm-audio, vad, audio, natural-language-processing

## Member repositories
- wiseman/py-webrtcvad (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:56.712253+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:27:12.545451+00:00, confidence not recorded.
  - readme: https://github.com/wiseman/py-webrtcvad (fetched 2026-08-28T04:06:56.712253+00:00, sha 6077789b054d)
- Data as of 2026-08-30T08:39:29.467469+00:00.