# adblockradio/adblockradio

An adblocker for live radio streams and podcasts. Machine learning meets Shazam.

Repository: https://github.com/adblockradio/adblockradio
Canonical: https://ross.abutalabs.com/products/adblockradio
Homepage: https://www.adblockradio.com
Language: JavaScript
License: MPL-2.0
License Family: copyleft
Topics: machine-learning, ai, signal-processing, adblock, tensorflow, keras, shazam, adblockradio
Archived: true
Last push: 2021-04-10T14:07:10+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2977, "days_push": 1971, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1488, forks 63 (observed 2026-08-28T04:04:52.161161+00:00)

## What it is
Adblock Radio is a Node.js library that detects and blocks advertisements in live radio streams and podcasts using machine learning and audio fingerprinting. It decodes audio with ffmpeg, analyzes it with a neural network and a fingerprint matcher, and exposes a Readable stream of analysis results.

## Use cases
- skip ads in podcast downloads automatically
- mute or block ads in live radio streams
- detect known jingles or songs in audio via fingerprinting
- classify audio segments as ads vs content with a neural network
- build a custom radio player that filters commercials

## When to choose
- you need programmatic ad detection in radio or podcast audio
- you want to combine ML spectral analysis with fingerprint matching
- you are comfortable with an archived project and older Node.js versions

## When to avoid
- you need actively maintained software or modern Node.js support
- you want a ready-made end-user app rather than a library
- you need real-time performance on constrained hardware without tuning

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, audio-processing, speech-recognition
- domain: machine-learning, media, privacy
- platform: windows
- tags: adblock, radio, podcasts, audio-fingerprinting, shazam, tensorflow, keras, archived, stream-processing, audio, nodejs, linux, macos

## Member repositories
- adblockradio/adblockradio (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:52.161161+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 2026-08-30T04:33:43.704998+00:00, confidence not recorded.
  - readme: https://github.com/adblockradio/adblockradio (fetched 2026-08-28T04:04:52.161161+00:00, sha 657af45d9a8f)
  - homepage: https://www.adblockradio.com (fetched 2026-08-29T11:40:09.302797+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.