# ricky0123/vad

Voice activity detector (VAD) for the browser with a simple API

Repository: https://github.com/ricky0123/vad
Canonical: https://ross.abutalabs.com/products/vad
Homepage: https://www.vad.ricky0123.com
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: onnxruntime, silero-vad, speech-to-text, typescript, voice-activity-detection, web, web-audio-api
Last push: 2026-01-30T14:04:11+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 65, release rhythm 57, longevity 100
- inputs: {"age_days": 1416, "days_push": 215, "days_rel": 285, "gap_med": 0.0, "n_releases_24m": 11}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2043, forks 269 (observed 2026-08-28T04:06:08.715746+00:00)

## What it is
A JavaScript/TypeScript library that runs Silero VAD via ONNX Runtime Web to detect voice activity directly in the browser. It provides a simple API for microphone permission prompts and callbacks on audio segments containing speech, with a React wrapper package included.

## Use cases
- detect when a user is speaking in the browser
- send only speech segments of audio to a server for transcription
- show a speaking indicator animation during voice chat
- run voice activity detection client-side without a backend
- build a push-to-talk or voice-triggered web interface
- preprocess audio before speech-to-text in a web app

## When to choose
- you need accurate, real-time voice activity detection in a browser
- you want a simple callback-based API instead of raw ONNX model handling
- you're building a React app and want hooks for VAD
- you want to reduce audio sent to speech-to-text services by filtering silence

## When to avoid
- you need server-side Node.js VAD - node support is discontinued as of Oct 2024
- you need voice activity detection outside the browser (Python, mobile native, embedded)
- you need full speech recognition rather than just speech detection
- you require a permissively licensed dependency - the license is non-standard

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, audio-processing, machine-learning, sdk
- domain: speech-processing, web-development, machine-learning, frontend
- platform: browser
- tags: voice-activity-detection, silero-vad, onnx-runtime-web, web-audio-api, react, microphone, real-time-audio, audio, web-server, javascript, nodejs, typescript

## Member repositories
- ricky0123/vad (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:08.715746+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 2026-08-30T02:58:08.116061+00:00, confidence not recorded.
  - readme: https://github.com/ricky0123/vad (fetched 2026-08-28T04:06:08.715746+00:00, sha b2e305b0ae30)
  - homepage: https://www.vad.ricky0123.com (fetched 2026-08-29T10:38:25.877439+00:00, sha 2af9a1604315)
  - site_page: https://docs.vad.ricky0123.com (fetched 2026-08-29T10:38:25.888601+00:00, sha e2656e9bb956)
  - site_page: https://docs.vad.ricky0123.com/ (fetched 2026-08-29T10:38:25.886684+00:00, sha e2656e9bb956)
- Data as of 2026-08-30T08:39:29.467469+00:00.